(八:2020.08.27)CVPR 2020 追踪之论文纲要(译)

学术论文 同时被 2 个专栏收录
32 篇文章 1 订阅
11 篇文章 2 订阅

CVPR 2020 追踪之论文纲要(修正于2020.08.27)

讲在前面

  • 论坛很多博客都对论文做了总结和分类,但就医学领域而言,对这些论文的筛选信息显然需要更加精细的把控,所以自己对这1400篇的论文做一个大致从名称上的筛选,希望能找到些能解决当前问题的答案。
  • 论文链接建议直接Google论文名,比去各种论文或顶会网站找不知道快捷多少。
  • 下面皆为机器翻译,我会慢慢修正,但现在请结合。有兴趣的可以问我要处理这些论文并自动翻译的脚本。
  • Respect!

论文目录

论文概要
1.12-in-1 - Multi-Task Vision and Language Representation Learning
12合1-多任务视觉和语言表示学习
<从多个单分类到多分类>
2.15 Keypoints Is All You Need
15个关键点可以做所有事情
关于姿态识别
3.3D Human Mesh Regression With Dense Correspondence
具有密集对应关系的3D人体网格回归
2D图像到3D立体的估计
4.3D-MPA - Multi-Proposal Aggregation for 3D Semantic Instance Segmentation
3D-MPA-用于3D语义实例分割的多种策略集合
3D点云上进行实例分割
5.3D Packing for Self-Supervised Monocular Depth Estimation
用于自我监督单眼深度估计的3D包装
6.3D Part Guided Image Editing for Fine-Grained Object Understanding
3D零件引导的图像编辑,以了解细粒度的对象
7.3D Photography Using Context-Aware Layered Depth Inpainting
使用上下文感知分层深度修补的3D摄影
8.3DRegNet - A Deep Neural Network for 3D Point Registration
3DRegNet-用于3D点注册的深度神经网络
9.3D Sketch-Aware Semantic Scene Completion via Semi-Supervised Structure Prior
通过半监督结构先验的3D草图感知语义场景完成
10.3DSSD - Point-Based 3D Single Stage Object Detector
3DSSD-基于点的3D单级目标检测器
11.3DV - 3D Dynamic Voxel for Action Recognition in Depth Video
3DV-用于深度视频中动作识别的3D动态体素
12.3D-ZeF - A 3D Zebrafish Tracking Benchmark Dataset
3D-ZeF-3D Zebrafish跟踪基准数据集
13.3FabRec - Fast Few-Shot Face Alignment by Reconstruction
3FabRec-通过重建快速进行少量面部对准
14.4D Association Graph for Realtime Multi-Person Motion Capture Using Multiple Video Cameras
使用多个摄像机进行实时多人运动捕捉的4D关联图
15.4D Visualization of Dynamic Events From Unconstrained Multi-View Videos
来自不受约束的多视图视频的动态事件的4D可视化
16.A2dele - Adaptive and Attentive Depth Distiller for Efficient RGB-D Salient Object Detection
A2dele-用于高效RGB-D显着目标检测的自适应和精细深度蒸馏器
17.AANet - Adaptive Aggregation Network for Efficient Stereo Matching
AANet-高效的立体声匹配自适应聚合网络
18.ABCNet - Real-Time Scene Text Spotting With Adaptive Bezier-Curve Network
ABCNet-自适应贝塞尔曲线网络的实时场景文本点播
19.Accurate Estimation of Body Height From a Single Depth Image via a Four-Stage Developing Network
通过四阶段显影网络从单个深度图像准确估计身高
20.A Certifiably Globally Optimal Solution to Generalized Essential Matrix Estimation
广义基本矩阵估计的可认证的全局最优解
21.A Characteristic Function Approach to Deep Implicit Generative Modeling
深度隐式生成建模的特征函数方法
<隐式建模?>
22.Achieving Robustness in the Wild via Adversarial Mixing With Disentangled Representations
通过对抗的混合与纠缠的表示形式实现野外的鲁棒性
23.ACNe - Attentive Context Normalization for Robust Permutation-Equivariant Learning
ACNe-稳健置换等变学习的注意上下文标准化
24.A Context-Aware Loss Function for Action Spotting in Soccer Videos
足球视频中动作识别的情境感知损失功能
25.ActBERT - Learning Global-Local Video-Text Representations
ActBERT-学习全球本地视频文本表示
26.ActionBytes - Learning From Trimmed Videos to Localize Actions
ActionBytes-从修剪的视频中学习以本地化操作
27.Action Genome - Actions As Compositions of Spatio-Temporal Scene Graphs
动作基因组-动作作为时空场景图的组成
28.Action Modifiers - Learning From Adverbs in Instructional Videos
动作修饰语-从教学视频中的副词中学习
29.Action Segmentation With Joint Self-Supervised Temporal Domain Adaptation
具有联合自我监督的时间域自适应的动作细分
30.Active 3D Motion Visualization Based on Spatiotemporal Light-Ray Integration
基于时空光线集成的主动3D运动可视化
31.ActiveMoCap - Optimized Viewpoint Selection for Active Human Motion Capture
ActiveMoCap-针对主动人体动作捕捉的优化视点选择
32.Active Speakers in Context
上下文中的活跃发言人
33.Active Vision for Early Recognition of Human Actions
早期认识人类行为的积极愿景
34.Actor-Transformers for Group Activity Recognition
小组活动识别的演员/变形者
35.AdaBits - Neural Network Quantization With Adaptive Bit-Widths
AdaBits-具有自适应位宽的神经网络量化
36.AdaCoF - Adaptive Collaboration of Flows for Video Frame Interpolation
AdaCoF-视频帧插值流的自适应协作
37.AdaCoSeg - Adaptive Shape Co-Segmentation With Group Consistency Loss
AdaCoSeg-具有组一致性损失的自适应形状共分割
38.Adaptive Dilated Network With Self-Correction Supervision for Counting
具有自校正监督的自适应扩张网络计数
39.Adaptive Fractional Dilated Convolution Network for Image Aesthetics Assessment
自适应分数阶卷积网络用于图像美学评估
40.Adaptive Graph Convolutional Network With Attention Graph Clustering for Co-Saliency Detection
带有注意力图聚类的自适应图卷积网络用于共显着性检测
41.Adaptive Hierarchical Down-Sampling for Point Cloud Classification
点云分类的自适应分层下采样
42.Adaptive Interaction Modeling via Graph Operations Search
通过图操作搜索进行自适应交互建模
43.Adaptive Loss-Aware Quantization for Multi-Bit Networks
多位网络的自适应损耗感知量化
44.Adaptive Subspaces for Few-Shot Learning
少子学习的自适应子空间
45.AD-Cluster - Augmented Discriminative Clustering for Domain Adaptive Person Re-Identification
AD-Cluster-增强型鉴别聚类,用于域自适应人员重新识别
46.AdderNet - Do We Really Need Multiplications in Deep Learning -
AdderNet-我们真的需要深度学习中的乘法-
47.ADINet - Attribute Driven Incremental Network for Retinal Image Classification
ADINet-用于视网膜图像分类的属性驱动增量网络
48.A Disentangling Invertible Interpretation Network for Explaining Latent Representations
解释潜在表示的可解译可逆解释网络
49.Advancing High Fidelity Identity Swapping for Forgery Detection
推进高保真身份交换以进行伪造检测
50.Adversarial Camouflage - Hiding Physical-World Attacks With Natural Styles
对抗迷彩-以自然风格隐藏物理世界的攻击
论文概要
51.Adversarial Examples Improve Image Recognition
对抗示例可提高图像识别度
52.Adversarial Feature Hallucination Networks for Few-Shot Learning
很少学习的对抗性幻觉网络
53.Adversarial Latent Autoencoders
对抗性潜在自动编码器
54.AdversarialNAS - Adversarial Neural Architecture Search for GANs
AdversarialNAS-GAN的对抗性神经架构搜索
55.Adversarial Robustness - From Self-Supervised Pre-Training to Fine-Tuning
对抗性强健-从自我监督的预训练到微调
56.Adversarial Texture Optimization From RGB-D Scans
RGB-D扫描的对抗纹理优化
57.Adversarial Vertex Mixup - Toward Better Adversarially Robust Generalization
对抗性顶点混合-更好地对抗性强健的泛化
58.Advisable Learning for Self-Driving Vehicles by Internalizing Observation-to-Action Rules
通过内化观察行动规则,对无人驾驶车辆进行明智的学习
59.Affinity Graph Supervision for Visual Recognition
视觉识别的亲和图监督
60.A Graduated Filter Method for Large Scale Robust Estimation
大规模鲁棒估计的分级滤波器方法
61.Agriculture-Vision - A Large Aerial Image Database for Agricultural Pattern Analysis
农业视觉-用于农业模式分析的大型航空影像数据库
62.A Hierarchical Graph Network for 3D Object Detection on Point Clouds
点云上用于3D对象检测的分层图网络
63.ALFRED - A Benchmark for Interpreting Grounded Instructions for Everyday Tasks
ALFRED-解释日常任务的基础说明的基准
64.A Lighting-Invariant Point Processor for Shading
用于阴影的照明不变点处理器
65.Alleviation of Gradient Exploding in GANs - Fake Can Be Real
缓解GAN中的梯度爆炸-虚假可能是真实的
66.All in One Bad Weather Removal Using Architectural Search
使用建筑搜索一网打尽恶劣天气
67.A Local-to-Global Approach to Multi-Modal Movie Scene Segmentation
从局部到全局的多模式电影场景分割方法
68.A Model-Driven Deep Neural Network for Single Image Rain Removal
模型驱动的深度神经网络用于单幅图像去除雨水
69.A Morphable Face Albedo Model
可变形脸部反照率模型
70.A Multigrid Method for Efficiently Training Video Models
有效训练视频模型的多网格方法
71.A Multi-Hypothesis Approach to Color Constancy
颜色假设的多假设方法
72.A Multi-Task Mean Teacher for Semi-Supervised Shadow Detection
半监督阴影检测的多任务均值教师
73.An Adaptive Neural Network for Unsupervised Mosaic Consistency Analysis in Image Forensics
自适应神经网络在图像取证中无监督的马赛克一致性分析
74.Analyzing and Improving the Image Quality of StyleGAN
分析和改善StyleGAN的图像质量
75.An Efficient PointLSTM for Point Clouds Based Gesture Recognition
基于点云的手势识别的高效PointLSTM
76.An End-to-End Edge Aggregation Network for Moving Object Segmentation
用于移动对象分割的端到端边缘聚合网络
77.A Neural Rendering Framework for Free-Viewpoint Relighting
用于自由视点重新照明的神经渲染框架
78.AnimalWeb - A Large-Scale Hierarchical Dataset of Annotated Animal Faces
AnimalWeb-带注释动物脸的大规模分层数据集
79.An Internal Covariate Shift Bounding Algorithm for Deep Neural Networks by Unitizing Layers’ Outputs
通过统一图层输出将深度神经网络的内部协变量移位边界算法
80.An Investigation Into the Stochasticity of Batch Whitening
批量美白的随机性研究
81.Anisotropic Convolutional Networks for 3D Semantic Scene Completion
用于3D语义场景完成的各向异性卷积网络
82.A Novel Recurrent Encoder-Decoder Structure for Large-Scale Multi-View Stereo Reconstruction From an Open Aerial Dataset
从开放的航空数据集进行大规模多视图立体声重构的新型递归编码器-解码器结构
83.AOWS - Adaptive and Optimal Network Width Search With Latency Constraints
AOWS-具有延迟约束的自适应和最佳网络宽度搜索
84.A Physics-Based Noise Formation Model for Extreme Low-Light Raw Denoising
基于物理的极端​​微光原始降噪噪声形成模型
85.Appearance Shock Grammar for Fast Medial Axis Extraction From Real Images
从真实图像中快速提取中轴的外观冲击语法
86.Approximating shapes in images with low-complexity polygons
低复杂度多边形的图像中的近似形状
87.APQ - Joint Search for Network Architecture, Pruning and Quantization Policy
APQ-联合搜索网络体系结构,修剪和量化策略
88.A Programmatic and Semantic Approach to Explaining and Debugging Neural Network Based Object Detectors
一种解释和调试基于神经网络的对象检测器的程序和语义方法
89.A Quantum Computational Approach to Correspondence Problems on Point Sets
点集对应问题的量子计算方法
90.ARCH - Animatable Reconstruction of Clothed Humans
ARCH-穿衣服的人的动画重建
91.A Real-Time Cross-Modality Correlation Filtering Method for Referring Expression Comprehension
引用表达理解的实时跨模态相关滤波方法
92.ARShadowGAN - Shadow Generative Adversarial Network for Augmented Reality in Single Light Scenes
ARShadowGAN-用于在单光场景中增强现实的阴影生成对抗网络
93.Articulation-Aware Canonical Surface Mapping
清晰可辨的规范曲面映射
94.A Self-supervised Approach for Adversarial Robustness
一种自我监督的对抗鲁棒性方法
95.A Semi-Supervised Assessor of Neural Architectures
神经结构的半监督评估员
96.A Shared Multi-Attention Framework for Multi-Label Zero-Shot Learning
共享的多注意零标签学习多框架
97.ASLFeat - Learning Local Features of Accurate Shape and Localization
ASLFeat-学习局部形状的精确形状和定位
98.A Sparse Resultant Based Method for Efficient Minimal Solvers
基于稀疏结果的有效最小解法
99.A Spatial RNN Codec for End-to-End Image Compression
用于端到端图像压缩的空间RNN编解码器
100.A Spatiotemporal Volumetric Interpolation Network for 4D Dynamic Medical Image
4D动态医学图像的时空体积插值网络
<医学图像插值>
论文概要
101.Assessing Eye Aesthetics for Automatic Multi-Reference Eye In-Painting
评估眼睛美学以自动进行多参考眼内绘画
102.Assessing Image Quality Issues for Real-World Problems
针对实际问题评估图像质量问题
103.Associate-3Ddet - Perceptual-to-Conceptual Association for 3D Point Cloud Object Detection
Associate-3Ddet-3D点云对象检测的感知到概念关联
104.A Stochastic Conditioning Scheme for Diverse Human Motion Prediction
一种用于人类运动预测的随机条件方案
105.A Transductive Approach for Video Object Segmentation
视频对象分割的转导方法
106.Attack to Explain Deep Representation
攻击以解释深度表示
107.Attention-Aware Multi-View Stereo
注意力感知多视图立体声
108.Attention-Based Context Aware Reasoning for Situation Recognition
基于注意的情境感知推理
109.Attention Convolutional Binary Neural Tree for Fine-Grained Visual Categorization
细观视觉分类的注意卷积二叉神经树
110.Attention-Driven Cropping for Very High Resolution Facial Landmark Detection
注意力驱动的裁剪可实现非常高分辨率的面部地标检测
111.Attention-Guided Hierarchical Structure Aggregation for Image Matting
图像遮蔽的注意力指导层次结构聚合
112.Attention Mechanism Exploits Temporal Contexts - Real-Time 3D Human Pose Reconstruction
注意力机制利用时间上下文-实时3D人体姿势重构
113.Attention Scaling for Crowd Counting
人群计数的注意力扩展
114.Attentive Normalization for Conditional Image Generation
注意图像归一化
115.Attentive Weights Generation for Few Shot Learning via Information Maximization
通过信息最大化来进行少拍学习的专注权重生成
116.Attribution in Scale and Space
规模和空间归属
117.AugFPN - Improving Multi-Scale Feature Learning for Object Detection
AugFPN-改进用于对象检测的多尺度特征学习
118.Augmenting Colonoscopy Using Extended and Directional CycleGAN for Lossy Image Translation
使用扩展和定向CycleGAN增强结肠镜检查以进行有损图像转换
<医学损坏图像修复>
119.Augment Your Batch - Improving Generalization Through Instance Repetition
增加您的批次-通过实例重复提高通用性
120.A U-Net Based Discriminator for Generative Adversarial Networks
生成对抗网络的基于U-Net的鉴别器
unet
121.A Unified Object Motion and Affinity Model for Online Multi-Object Tracking
在线多对象跟踪的统一对象运动和相似性模型
122.A Unified Optimization Framework for Low-Rank Inducing Penalties
低排名诱导罚金的统一优化框架
123.Auto-Encoding Twin-Bottleneck Hashing
自动编码双瓶颈散列
124.Autolabeling 3D Objects With Differentiable Rendering of SDF Shape Priors
使用SDF形状先验的可区分渲染自动标记3D对象
125.Automatic Neural Network Compression by Sparsity-Quantization Joint Learning - A Constrained Optimization-Based Approach
稀疏量化联合学习的神经网络自动压缩-一种基于约束优化的方法
126.AutoTrack - Towards High-Performance Visual Tracking for UAV With Automatic Spatio-Temporal Regularization
AutoTrack-通过自动时空正则化实现对无人机的高性能视觉跟踪
127.Auto-Tuning Structured Light by Optical Stochastic Gradient Descent
通过光学随机梯度下降自动调谐结构光
128.Auxiliary Training - Towards Accurate and Robust Models
辅助培训-建立准确而稳健的模型
129.AvatarMe - Realistically Renderable 3D Facial Reconstruction - In-the-Wild -
AvatarMe-现实可渲染的3D面部重建-野外-
130.Averaging Essential and Fundamental Matrices in Collinear Camera Settings
在共线相机设置中平均基本矩阵和基本矩阵
131.BachGAN - High-Resolution Image Synthesis From Salient Object Layout
BachGAN-通过显着对象布局进行高分辨率图像合成
132.Background Data Resampling for Outlier-Aware Classification
用于离群值感知分类的背景数据重采样
133.Background Matting - The World Is Your Green Screen
背景抠图-世界就是您的绿屏
134.BANet - Bidirectional Aggregation Network With Occlusion Handling for Panoptic Segmentation
BANet-具有遮挡处理的双向聚合网络用于全景分割
135.Barycenters of Natural Images Constrained Wasserstein Barycenters for Image Morphing
自然图像的重心限制了Wasserstein图像变形的重心
136.Basis Prediction Networks for Effective Burst Denoising With Large Kernels
大颗粒有效突发消噪的基础预测网络
137.Bayesian Adversarial Human Motion Synthesis
贝叶斯对抗性人体运动综合
138.BBN - Bilateral-Branch Network With Cumulative Learning for Long-Tailed Visual Recognition
BBN-具有累积学习功能的双边分支网络,用于长尾视觉识别
139.BDD100K - A Diverse Driving Dataset for Heterogeneous Multitask Learning
BDD100K-用于异构多​​任务学习的多样化驾驶数据集
140.BEDSR-Net - A Deep Shadow Removal Network From a Single Document Image
BEDSR-Net-从单个文档图像中去除深色阴影的网络
141.Belief Propagation Reloaded - Learning BP-Layers for Labeling Problems
重装信仰传播-学习BP层解决标签问题
142.Benchmarking Adversarial Robustness on Image Classification
图像分类中的对抗鲁棒性基准测试
143.Benchmarking the Robustness of Semantic Segmentation Models
对语义分割模型的鲁棒性进行基准测试
语义分割鲁棒性测试
144.Better Captioning With Sequence-Level Exploration
通过序列级探索获得更好的字幕
145.Beyond Short-Term Snippet - Video Relation Detection With Spatio-Temporal Global Context
短期片段之外-具有时空全局上下文的视频关系检测
146.BFBox - Searching Face-Appropriate Backbone and Feature Pyramid Network for Face Detector
BFBox-为人脸检测器搜索适合于人脸的骨干和特征金字塔网络
147.Bi3D - Stereo Depth Estimation via Binary Classifications
Bi3D-通过二进制分类的立体声深度估计
148.BiDet - An Efficient Binarized Object Detector
BiDet-高效的二值化对象检测器
149.Bidirectional Graph Reasoning Network for Panoptic Segmentation
用于全景分割的双向图推理网络
150.Bi-Directional Interaction Network for Person Search
用于人员搜索的双向交互网络
论文概要
151.Bi-Directional Relationship Inferring Network for Referring Image Segmentation
用于参考图像分割的双向关系推断网络
图像分割
152.BidNet - Binocular Image Dehazing Without Explicit Disparity Estimation
BidNet-无明显视差估计的双目图像去雾
153.BiFuse - Monocular 360 Depth Estimation via Bi-Projection Fusion
BiFuse-通过双向投影融合进行单眼360深度估计
154.Binarizing MobileNet via Evolution-Based Searching
通过基于演化的搜索对MobileNet进行二值化
155.BlendedMVS - A Large-Scale Dataset for Generalized Multi-View Stereo Networks
BlendedMVS-适用于广义多视图立体声网络的大规模数据集
156.BlendMask - Top-Down Meets Bottom-Up for Instance Segmentation
BlendMask-自上而下与自下而上进行实例细分
157.Blindly Assess Image Quality in the Wild Guided by a Self-Adaptive Hyper Network
自适应超网络指导盲目评估野外图像质量
158.Block-Wisely Supervised Neural Architecture Search With Knowledge Distillation
带有知识蒸馏的块明智监督神经体系结构搜索
159.Blur Aware Calibration of Multi-Focus Plenoptic Camera
多焦点全光相机的模糊感知校准
160.Blurry Video Frame Interpolation
模糊视频帧插值
161.Bodies at Rest - 3D Human Pose and Shape Estimation From a Pressure Image Using Synthetic Data
静止的身体-使用合成数据从压力图像进行3D人体姿势和形状估计
162.Boosting Few-Shot Learning With Adaptive Margin Loss
通过自适应保证金损失促进少量学习
163.Boosting Semantic Human Matting With Coarse Annotations
使用粗注解增强语义人的表情
164.Boosting the Transferability of Adversarial Samples via Attention
通过注意提高对抗性样品的可转移性
165.Boundary-Aware 3D Building Reconstruction From a Single Overhead Image
从单个架空图像进行边界感知的3D建筑物重建
166.Breaking the Cycle - Colleagues Are All You Need
打破周期-您只需要同事
167.Bridging the Gap Between Anchor-Based and Anchor-Free Detection via Adaptive Training Sample Selection
通过自适应训练样本选择弥合基于锚的检测和无锚检测之间的差距
168.Bringing Old Photos Back to Life
将旧照片带入生活
169.BSP-Net - Generating Compact Meshes via Binary Space Partitioning
BSP-Net-通过二进制空间划分生成紧凑网格
170.Bundle Adjustment on a Graph Processor
图形处理器上的捆绑调整
171.Bundle Pooling for Polygonal Architecture Segmentation Problem
多边形池分割问题的捆绑池
172.Butterfly Transform - An Efficient FFT Based Neural Architecture Design
蝴蝶变换-基于FFT的高效神经网络设计
173.C2FNAS - Coarse-to-Fine Neural Architecture Search for 3D Medical Image Segmentation
C2FNAS-精细到精细的神经体系结构搜索3D医学图像分割
174.Camera On-Boarding for Person Re-Identification Using Hypothesis Transfer Learning
使用假设转移学习的机载人重新识别相机
175.Camera Trace Erasing
相机痕迹清除
176.Camouflaged Object Detection
伪装物体检测
177.Can Deep Learning Recognize Subtle Human Activities -
深度学习能否识别微妙的人类活动-
178.Can Facial Pose and Expression Be Separated With Weak Perspective Camera -
弱视摄像头可以将面部姿势和表情分开吗?
179.Can Weight Sharing Outperform Random Architecture Search - An Investigation With TuNAS
权重共享可以胜过随机架构搜索吗?-TuNAS调查
180.Can We Learn Heuristics for Graphical Model Inference Using Reinforcement Learning -
我们可以使用强化学习来学习图形模型推理的启发式-
181.CARP - Compression Through Adaptive Recursive Partitioning for Multi-Dimensional Images
CARP-通过自适应递归分区对多维图像进行压缩
182.Cars Can’t Fly Up in the Sky - Improving Urban-Scene Segmentation via Height-Driven Attention Networks
汽车无法飞上蓝天-通过高度驱动的注意力网络改善城市场景分割
183.CARS - Continuous Evolution for Efficient Neural Architecture Search
CARS-高效的神经架构搜索的持续发展
184.Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching
高分辨率多视图立体声和立体声匹配的级联成本量
185.Cascaded Deep Monocular 3D Human Pose Estimation With Evolutionary Training Data
具有进化训练数据的级联深层单眼3D人姿估计
186.Cascaded Deep Video Deblurring Using Temporal Sharpness Prior
使用时间优先级进行级联深视频去模糊
187.Cascaded Human-Object Interaction Recognition
级联的人-物体交互识别
188.Cascaded Refinement Network for Point Cloud Completion
用于点云完成的级联优化网络
189.Cascade EF-GAN - Progressive Facial Expression Editing With Local Focuses
级联EF-GAN-局部表情渐进式表情编辑
190.CascadePSP - Toward Class-Agnostic and Very High-Resolution Segmentation via Global and Local Refinement
CascadePSP-通过全局和局部优化实现与类无关和非常高分辨率的细分
191.Category-Level Articulated Object Pose Estimation
类别级铰接对象姿势估计
192.Celeb-DF - A Large-Scale Challenging Dataset for DeepFake Forensics
Celeb-DF-适用于DeepFake取证的大规模具有挑战性的数据集
193.CenterMask - Real-Time Anchor-Free Instance Segmentation
CenterMask-实时无锚实例分段
194.CenterMask - Single Shot Instance Segmentation With Point Representation
CenterMask-具有点表示的单镜头实例分割
195.Central Similarity Quantization for Efficient Image and Video Retrieval
中央相似量化实现有效的图像和视频检索
196.CentripetalNet - Pursuing High-Quality Keypoint Pairs for Object Detection
CentripetalNet-追求用于对象检测的高质量关键点对
197.C-Flow - Conditional Generative Flow Models for Images and 3D Point Clouds
C流-图像和3D点云的条件生成流模型
198.Channel Attention Based Iterative Residual Learning for Depth Map Super-Resolution
基于通道注意的迭代残差学习的深度图超分辨率
199.CIAGAN - Conditional Identity Anonymization Generative Adversarial Networks
CIAGAN-条件身份匿名化生成对抗网络
200.Circle Loss - A Unified Perspective of Pair Similarity Optimization
圆损失-对相似度优化的统一视角
论文概要
201.Classifying, Segmenting, and Tracking Object Instances in Video with Mask Propagation
使用遮罩传播对视频中的对象实例进行分类,分段和跟踪
202.Clean-Label Backdoor Attacks on Video Recognition Models
视频识别模型的干净标签后门攻击
203.Closed-Loop Matters - Dual Regression Networks for Single Image Super-Resolution
闭环问题-用于单图像超分辨率的双重回归网络
204.Cloth in the Wind - A Case Study of Physical Measurement Through Simulation
风中的布料-通过仿真进行物理测量的案例研究
205.ClusterFit - Improving Generalization of Visual Representations
ClusterFit-改进视觉表示的泛化
206.ClusterVO - Clustering Moving Instances and Estimating Visual Odometry for Self and Surroundings
ClusterVO-对移动实例进行聚类并估计自身和周围环境的视觉里程表
207.CNN-Generated Images Are Surprisingly Easy to Spot… for Now
CNN生成的图像现在非常容易发现…
208.COCAS - A Large-Scale Clothes Changing Person Dataset for Re-Identification
COCAS-用于重新识别的大规模换衣服人数据集
209.Cogradient Descent for Bilinear Optimization
双线性优化的共梯度下降
210.Coherent Reconstruction of Multiple Humans From a Single Image
从单个图像对多个人进行相干重建
211.Collaborative Distillation for Ultra-Resolution Universal Style Transfer
协作蒸馏实现超分辨率通用样式转换
212.Collaborative Motion Prediction via Neural Motion Message Passing
通过神经运动消息传递进行协同运动预测
213.ColorFool - Semantic Adversarial Colorization
ColorFool-语义对抗着色
214.Combating Noisy Labels by Agreement - A Joint Training Method with Co-Regularization
通过协议打击嘈杂的标签-具有共同规律性的联合培训方法
215.Combining Detection and Tracking for Human Pose Estimation in Videos
视频中人体姿势估计的组合检测和跟踪
216.Composed Query Image Retrieval Using Locally Bounded Features
使用局部有界特征的组合查询图像检索
217.Composing Good Shots by Exploiting Mutual Relations
利用相互关系构图
218.Compositional Convolutional Neural Networks - A Deep Architecture With Innate Robustness to Partial Occlusion
成分卷积神经网络-具有对部分遮挡的固有鲁棒性的深度架构
219.Compressed Volumetric Heatmaps for Multi-Person 3D Pose Estimation
用于多人3D姿势估计的压缩体积热图
220.Computing the Testing Error Without a Testing Set
在没有测试集的情况下计算测试误差
221.Computing Valid P-Values for Image Segmentation by Selective Inference
通过选择推理计算有效的P值进行图像分割
222.Conditional Channel Gated Networks for Task-Aware Continual Learning
用于任务感知的持续学习的条件通道门控网络
223.Conditional Gaussian Distribution Learning for Open Set Recognition
用于开放集识别的条件高斯分布学习
224.Connect-and-Slice - An Hybrid Approach for Reconstructing 3D Objects
连接和切片-重建3D对象的混合方法
225.CONSAC - Robust Multi-Model Fitting by Conditional Sample Consensus
CONSAC-通过条件样本共识进行稳健的多模型拟合
226.Context-Aware and Scale-Insensitive Temporal Repetition Counting
上下文感知和对规模不敏感的时间重复计数
227.Context-Aware Attention Network for Image-Text Retrieval
用于图像文本检索的上下文感知注意网络
228.Context Aware Graph Convolution for Skeleton-Based Action Recognition
基于骨骼的动作识别的上下文感知图卷积
229.Context-Aware Group Captioning via Self-Attention and Contrastive Features
通过自我注意和对比功能识别上下文的群组字幕
230.Context-Aware Human Motion Prediction
上下文感知的人体运动预测
231.Context Prior for Scene Segmentation
场景分割的上下文优先
232.Context R-CNN - Long Term Temporal Context for Per-Camera Object Detection
上下文R-CNN-用于每个摄像机对象检测的长期时间上下文
233.Contextual Residual Aggregation for Ultra High-Resolution Image Inpainting
用于超高分辨率图像修复的上下文残差聚合
234.Continual Learning With Extended Kronecker-Factored Approximate Curvature
用扩展的Kronecker因子近似曲率进行连续学习
235.ContourNet - Taking a Further Step Toward Accurate Arbitrary-Shaped Scene Text Detection
ContourNet-进一步迈向准确任意形状的场景文本检测
236.Controllable Orthogonalization in Training DNNs
训练DNN中的可控正交化
237.Controllable Person Image Synthesis With Attribute-Decomposed GAN
基于属性分解GAN的可控人像合成
238.Conv-MPN - Convolutional Message Passing Neural Network for Structured Outdoor Architecture Reconstruction
Conv-MPN-卷积消息传递神经网络,用于结构化室外体系结构重构
239.Convolution in the Cloud - Learning Deformable Kernels in 3D Graph Convolution Networks for Point Cloud Analysis
云中的卷积-学习3D图卷积网络中的可变形核以进行点云分析
240.CookGAN - Causality Based Text-to-Image Synthesis
CookGAN-基于因果关系的文本到图像合成
241.Cooling-Shrinking Attack - Blinding the Tracker With Imperceptible Noises
冷却收缩攻击-跟踪器发出难以察觉的噪音
242.Cops-Ref - A New Dataset and Task on Compositional Referring Expression Comprehension
Cops-Ref-有关复合指称表达理解的新数据集和任务
243.Copy and Paste GAN - Face Hallucination From Shaded Thumbnails
复制并粘贴GAN-阴影缩略图产生的幻觉
244.Correction Filter for Single Image Super-Resolution - Robustifying Off-the-Shelf Deep Super-Resolvers
用于单图像超分辨率的校正滤波器-稳定的深层超级解析器
245.Correlating Edge, Pose With Parsing
关联边缘,带解析姿势
246.Correlation-Guided Attention for Corner Detection Based Visual Tracking
基于角检测的视觉跟踪的相关指导注意力
247.Correspondence-Free Material Reconstruction using Sparse Surface Constraints
使用稀疏表面约束的无对应材料重建
248.Correspondence Networks With Adaptive Neighbourhood Consensus
自适应邻域共识的通信网络
249.Cost Volume Pyramid Based Depth Inference for Multi-View Stereo
基于成本量金字塔的多视图立体声深度推断
250.Counterfactual Samples Synthesizing for Robust Visual Question Answering
反事实样本的合成,用于健壮的视觉问答
251.Counterfactual Vision and Language Learning
反事实视野和语言学习
252.Counting Out Time - Class Agnostic Video Repetition Counting in the Wild
数出时间-野外不可知类的视频重复计数
253.CoverNet - Multimodal Behavior Prediction Using Trajectory Sets
CoverNet-使用轨迹集的多模式行为预测
254.CPR-GCN - Conditional Partial-Residual Graph Convolutional Network in Automated Anatomical Labeling of Coronary Arteries
CPR-GCN-冠状动脉自动解剖标记中的条件部分残差图卷积网络
255.Creating Something From Nothing - Unsupervised Knowledge Distillation for Cross-Modal Hashing
从零开始创造一切-跨模态哈希的无监督知识提炼
256.CRNet - Cross-Reference Networks for Few-Shot Segmentation
CRNet-少量分割的交叉引用网络
257.Cross-Batch Memory for Embedding Learning
跨批次记忆用于嵌入式学习
258.Cross-Domain Correspondence Learning for Exemplar-Based Image Translation
基于范例的图像翻译的跨域对应学习
259.Cross-Domain Detection via Graph-Induced Prototype Alignment
通过图诱导原型比对进行跨域检测
260.Cross-Domain Document Object Detection - Benchmark Suite and Method
跨域文档对象检测-基准套件和方法
261.Cross-Domain Face Presentation Attack Detection via Multi-Domain Disentangled Representation Learning
通过多域解缠表示学习进行跨域人脸呈现攻击检测
262.Cross-domain Object Detection through Coarse-to-Fine Feature Adaptation
通过粗到精特征适配进行跨域对象检测
263.Cross-Domain Semantic Segmentation via Domain-Invariant Interactive Relation Transfer
通过领域不变交互关系转移进行跨域语义分割
264.Cross-Modal Cross-Domain Moment Alignment Network for Person Search
用于人员搜索的跨模态跨域矩对准网络
265.Cross-Modal Deep Face Normals With Deactivable Skip Connections
具有可禁用的跳过连接的跨模态深面法线
266.Cross-Modality Person Re-Identification With Shared-Specific Feature Transfer
具有共享特定特征转移的跨模态人员重新识别
267.Cross-Modal Pattern-Propagation for RGB-T Tracking
用于RGB-T跟踪的跨模模式传播
268.Cross-Spectral Face Hallucination via Disentangling Independent Factors
通过解开独立因素进行的跨谱幻觉
269.Cross-View Correspondence Reasoning Based on Bipartite Graph Convolutional Network for Mammogram Mass Detection
基于二部图卷积网络的跨视图对应推理在乳腺X线摄影质量检测中的应用
270.Cross-View Tracking for Multi-Human 3D Pose Estimation at Over 100 FPS
超过100 FPS的多人3D姿势估计的跨视图跟踪
271.CurricularFace - Adaptive Curriculum Learning Loss for Deep Face Recognition
CurricularFace-深度课程识别的自适应课程学习损失
272.CvxNet - Learnable Convex Decomposition
CvxNet-可学习的凸分解
273.CycleISP - Real Image Restoration via Improved Data Synthesis
CycleISP-通过改进的数据综合还原真实图像
274.Cylindrical Convolutional Networks for Joint Object Detection and Viewpoint Estimation
圆柱卷积网络用于联合目标检测和视点估计
275.D2Det - Towards High Quality Object Detection and Instance Segmentation
D2Det-迈向高质量对象检测和实例分割
276.D3Feat - Joint Learning of Dense Detection and Description of 3D Local Features
D3Feat-密集检测的联合学习和3D局部特征的描述
277.D3S - A Discriminative Single Shot Segmentation Tracker
D3S-区别性单发细分跟踪器
278.D3VO - Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometry
D3VO-单眼视觉测深法的深度,姿势和不确定性
279.DaST - Data-Free Substitute Training for Adversarial Attacks
DaST-对抗攻击的无数据替代训练
280.Data-Efficient Semi-Supervised Learning by Reliable Edge Mining
通过可靠的边缘挖掘实现数据有效的半监督学习
281.Data-Free Knowledge Amalgamation via Group-Stack Dual-GAN
通过Group-Stack Dual-GAN进行无数据知识融合
282.Dataless Model Selection With the Deep Frame Potential
具有深框架潜力的无数据模型选择
283.Data Uncertainty Learning in Face Recognition
人脸识别中的数据不确定性学习
284.DAVD-Net - Deep Audio-Aided Video Decompression of Talking Heads
DAVD-Net-通话头的深层音频辅助视频解压缩
285.Deblurring by Realistic Blurring
通过逼真的模糊去模糊
286.Deblurring Using Analysis-Synthesis Networks Pair
使用分析综合网络对进行去模糊
287.Decoupled Representation Learning for Skeleton-Based Gesture Recognition
基于骨架的手势识别的解耦表示学习
288.Deep 3D Capture - Geometry and Reflectance From Sparse Multi-View Images
深度3D捕捉-稀疏多视图图像的几何形状和反射率
289.Deep 3D Portrait From a Single Image
来自单个图像的深3D肖像
290.Deep Active Learning for Biased Datasets via Fisher Kernel Self-Supervision
通过Fisher Kernel自我监督对有偏数据集进行深度主动学习
291.Deep Adversarial Decomposition - A Unified Framework for Separating Superimposed Images
深度对抗分解-分离叠加图像的统一框架
292.DeepCap - Monocular Human Performance Capture Using Weak Supervision
DeepCap-使用弱监督捕获单眼人类绩效
293.DeepDeform - Learning Non-Rigid RGB-D Reconstruction With Semi-Supervised Data
DeepDeform-使用半监督数据学习非刚性RGB-D重建
294.Deep Degradation Prior for Low-Quality Image Classification
劣质图像分类的深度降级先验
295.Deep Distance Transform for Tubular Structure Segmentation in CT Scans
用于CT扫描中的管状结构分割的深距离变换
296.DeepEMD - Few-Shot Image Classification With Differentiable Earth Mover’s Distance and Structured Classifiers
DeepEMD-带有可移动推土机距离和结构分类器的少量图像分类
297.DeeperForensics-1.0 - A Large-Scale Dataset for Real-World Face Forgery Detection
DeeperForensics-1.0-用于真实世界人脸伪造检测的大规模数据集
298.DeepFaceFlow - In-the-Wild Dense 3D Facial Motion Estimation
DeepFaceFlow-野外密集3D人脸运动估计
299.Deep Face Super-Resolution With Iterative Collaboration Between Attentive Recovery and Landmark Estimation
专注恢复与地标估计之间具有迭代协作的Deep Face超分辨率
300.Deep Facial Non-Rigid Multi-View Stereo
深面部非刚性多视图立体声
论文概要
301.Deep Fair Clustering for Visual Learning
视觉学习的深度公平集群
302.DeepFLASH - An Efficient Network for Learning-Based Medical Image Registration
DeepFLASH-用于基于学习的医学图像注册的高效网络
303.Deep Generative Model for Robust Imbalance Classification
稳健不平衡分类的深度生成模型
304.Deep Geometric Functional Maps - Robust Feature Learning for Shape Correspondence
深度几何功能图-形状对应的鲁棒特征学习
305.Deep Global Registration
深度全球注册
306.Deep Grouping Model for Unified Perceptual Parsing
用于统一感知解析的深度分组模型
307.Deep Homography Estimation for Dynamic Scenes
动态场景的深度单应估计
308.Deep Image Spatial Transformation for Person Image Generation
用于人像生成的深度图像空间变换
309.Deep Implicit Volume Compression
深层隐式体积压缩
310.Deep Iterative Surface Normal Estimation
深层迭代曲面法线估计
311.Deep Kinematics Analysis for Monocular 3D Human Pose Estimation
单眼3D人体姿势估计的深度运动学分析
312.Deep Learning for Handling Kernel - model Uncertainty in Image Deconvolution
用于处理内核的深度学习-图像反卷积中的模型不确定性
313.DeepLPF - Deep Local Parametric Filters for Image Enhancement
DeepLPF-用于图像增强的深度局部参数滤波器
314.Deep Metric Learning via Adaptive Learnable Assessment
通过自适应可学习评估进行深度度量学习
315.Deep Non-Line-of-Sight Reconstruction
深度非视线重建
316.Deep Optics for Single-Shot High-Dynamic-Range Imaging
用于单镜头高动态范围成像的深光学元件
317.Deep Parametric Shape Predictions Using Distance Fields
使用距离场的深参数形状预测
318.Deep Polarization Cues for Transparent Object Segmentation
深极化提示,用于透明物体分割
319.Deep Relational Reasoning Graph Network for Arbitrary Shape Text Detection
用于任意形状文本检测的深度关系推理图网络
320.Deep Representation Learning on Long-Tailed Data - A Learnable Embedding Augmentation Perspective
长尾数据的深度表示学习-可学习的嵌入增强视角
321.Deep Residual Flow for Out of Distribution Detection
深度剩余流,用于失配检测
322.Deep Semantic Clustering by Partition Confidence Maximisation
基于分区置信度最大化的深度语义聚类
323.Deep Shutter Unrolling Network
深度快门展开网络
324.Deep Snake for Real-Time Instance Segmentation
Deep Snake用于实时实例分段
325.Deep Spatial Gradient and Temporal Depth Learning for Face Anti-Spoofing
用于人脸反欺骗的深度空间梯度和时间深度学习
326.Deep Stereo Using Adaptive Thin Volume Representation With Uncertainty Awareness
使用具有不确定性意识的自适应瘦体积表示的深度立体声
327.Deepstrip - High-Resolution Boundary Refinement
Deepstrip-高分辨率边界细化
328.Deep Structure-Revealed Network for Texture Recognition
用于纹理识别的深层揭示网络
329.Deep Unfolding Network for Image Super-Resolution
用于图像超分辨率的深度展开网络
330.Deep White-Balance Editing
深白平衡编辑
331.DeFeat-Net - General Monocular Depth via Simultaneous Unsupervised Representation Learning
DeFeat-Net-通过同时无监督表示学习进行的一般单眼深度
332.Defending Against Model Stealing Attacks With Adaptive Misinformation
利用自适应错误信息防御模型窃取攻击
333.Defending Against Universal Attacks Through Selective Feature Regeneration
通过选择性特征再生防御普遍攻击
334.Defending and Harnessing the Bit-Flip Based Adversarial Weight Attack
防御和利用基于比特翻转的对抗权重攻击
335.Deformable Siamese Attention Networks for Visual Object Tracking
用于视觉对象跟踪的可变形暹罗注意网络
336.Deformation-Aware Unpaired Image Translation for Pose Estimation on Laboratory Animals
变形识别不成对图像转换对实验动物的姿态估计
337.Densely Connected Search Space for More Flexible Neural Architecture Search
密集连接的搜索空间,可实现更灵活的神经体系结构搜索
338.Dense Regression Network for Video Grounding
用于视频接地的密集回归网络
339.Density-Aware Feature Embedding for Face Clustering
用于面部聚类的密度感知特征嵌入
340.Density-Aware Graph for Deep Semi-Supervised Visual Recognition
深度半监督视觉识别的密度感知图
341.Density-Based Clustering for 3D Object Detection in Point Clouds
基于密度的点云中3D对象检测聚类
342.DEPARA - Deep Attribution Graph for Deep Knowledge Transferability
DEPARA-用于深度知识转移的深度归因图
343.Depth Sensing Beyond LiDAR Range
深度感应超出LiDAR范围
344.Designing Network Design Spaces
设计网络设计空间
345.Detailed 2D-3D Joint Representation for Human-Object Interaction
人与物体交互的详细2D-3D联合表示
346.Detail-recovery Image Deraining via Context Aggregation Networks
通过上下文聚合网络消除细节恢复图像
347.Detecting Adversarial Samples Using Influence Functions and Nearest Neighbors
使用影响函数和最近邻来检测对抗性样本
348.Detecting Attended Visual Targets in Video
检测视频中的视觉目标
349.Detection in Crowded Scenes - One Proposal, Multiple Predictions
拥挤场景中的检测-一个建议,多个预测
350.Determinant Regularization for Gradient-Efficient Graph Matching
行列式正则化用于梯度有效图匹配
论文概要
351.Differentiable Adaptive Computation Time for Visual Reasoning
视觉推理的微分自适应计算时间
352.Differentiable Volumetric Rendering - Learning Implicit 3D Representations Without 3D Supervision
可微分的体积渲染-在没有3D监督的情况下学习隐式3D表示
353.Differential Treatment for Stuff and Things - A Simple Unsupervised Domain Adaptation Method for Semantic Segmentation
东西的差异处理-语义分割的一种简单的无监督域自适应方法
354.Discovering Human Interactions With Novel Objects via Zero-Shot Learning
通过零射击学习发现人类与新颖物体的互动
355.Discovering Synchronized Subsets of Sequences - A Large Scale Solution
发现序列的同步子集-大规模解决方案
356.Discrete Model Compression With Resource Constraint for Deep Neural Networks
具有资源约束的深度神经网络离散模型压缩
357.Discriminative Multi-Modality Speech Recognition
区分性多模态语音识别
358.Disentangled and Controllable Face Image Generation via 3D Imitative-Contrastive Learning
通过3D模仿对比学习来解开和控制面部图像
359.Disentangled Image Generation Through Structured Noise Injection
通过结构化噪声注入产生纠缠图像
360.Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition
解开和统一图卷积用于基于骨骼的动作识别
361.Disentangling Physical Dynamics From Unknown Factors for Unsupervised Video Prediction
从未知因素中解开物理动力学,实现无监督视频预测
362.Disparity-Aware Domain Adaptation in Stereo Image Restoration
立体图像恢复中的视差感知域自适应
363.Disp R-CNN - Stereo 3D Object Detection via Shape Prior Guided Instance Disparity Estimation
Disp R-CNN-通过形状先导实例差异估计进行立体3D对象检测
364.Distilled Semantics for Comprehensive Scene Understanding from Videos
蒸馏语义,可从视频中全面了解场景
365.Distilling Cross-Task Knowledge via Relationship Matching
通过关系匹配提取跨任务知识
366.Distilling Effective Supervision From Severe Label Noise
从严重标签噪音中提取有效监管
367.Distilling Image Dehazing With Heterogeneous Task Imitation
异构任务模仿提取图像去雾
368.Distilling Knowledge From Graph Convolutional Networks
从图卷积网络中提取知识
369.Distortion Agnostic Deep Watermarking
不可知论的深水印
370.DIST - Rendering Deep Implicit Signed Distance Function With Differentiable Sphere Tracing
DIST-使用可微球跟踪绘制深隐式带符号距离函数
371.Distribution-Aware Coordinate Representation for Human Pose Estimation
用于人体姿势估计的分布感知坐标表示
372.Distribution-Induced Bidirectional Generative Adversarial Network for Graph Representation Learning
图表示学习的分布诱导双向生成对抗网络
373.Diverse Image Generation via Self-Conditioned GANs
通过自适应GAN生成多种图像
374.Diversified Arbitrary Style Transfer via Deep Feature Perturbation
通过深度特征扰动实现多种风格的任意转移
375.DLWL - Improving Detection for Lowshot Classes With Weakly Labelled Data
DLWL-改进带有弱标记数据的低射类的检测
376.DMCP - Differentiable Markov Channel Pruning for Neural Networks
DMCP-用于神经网络的微分马尔可夫信道修剪
377.DNU - Deep Non-Local Unrolling for Computational Spectral Imaging
DNU-用于计算光谱成像的深层非局部展开
378.DOA-GAN - Dual-Order Attentive Generative Adversarial Network for Image Copy-Move Forgery Detection and Localization
DOA-GAN-用于图像复制移动伪造检测和定位的双阶专心生成对抗网络
379.Domain Adaptation for Image Dehazing
图像去雾的域自适应
380.Domain Adaptive Image-to-Image Translation
域自适应图像到图像转换
381.Domain-Aware Visual Bias Eliminating for Generalized Zero-Shot Learning
消除领域感知的视觉偏差,实现广义零射击学习
382.Domain Balancing - Face Recognition on Long-Tailed Domains
域平衡-长尾域上的人脸识别
383.Domain Decluttering - Simplifying Images to Mitigate Synthetic-Real Domain Shift and Improve Depth Estimation
域消除-简化图像以减轻合成-真实域移位并改善深度估计
384.Don’t Even Look Once - Synthesizing Features for Zero-Shot Detection
甚至都不看一次-零延迟检测的综合功能
385.Don’t Hit Me! Glass Detection in Real-World Scenes
不要打我!真实场景中的玻璃检测
386.Don’t Judge an Object by Its Context - Learning to Overcome Contextual Bias
不要通过物体的语境来判断-学习克服语境的偏见。
387.DOPS - Learning to Detect 3D Objects and Predict Their 3D Shapes
DOPS-学习检测3D对象并预测其3D形状
388.DoveNet - Deep Image Harmonization via Domain Verification
DoveNet-通过域验证进行深度图像协调
389.DPGN - Distribution Propagation Graph Network for Few-Shot Learning
DPGN-少量学习的分布传播图网络
390.Dreaming to Distill - Data-Free Knowledge Transfer via DeepInversion
梦想蒸馏-通过DeepInversion进行无数据知识转移
391.DR Loss - Improving Object Detection by Distributional Ranking
DR损失-通过分布等级改进对象检测
392.DSGN - Deep Stereo Geometry Network for 3D Object Detection
DSGN-用于3D对象检测的深度立体几何网络
393.DSNAS - Direct Neural Architecture Search Without Parameter Retraining
DSNAS-直接神经体系结构搜索,无需参数重新训练
394.DualConvMesh-Net - Joint Geodesic and Euclidean Convolutions on 3D Meshes
DualConvMesh-Net-3D网格上的联合测地线和欧几里德卷积
395.DualSDF - Semantic Shape Manipulation Using a Two-Level Representation
DualSDF-使用两层表示法的语义形状操纵
396.Dual Super-Resolution Learning for Semantic Segmentation
用于语义分割的双重超分辨率学习
397.DuDoRNet - Learning a Dual-Domain Recurrent Network for Fast MRI Reconstruction With Deep T1 Prior
DuDoRNet-学习具有双域递归网络以使用Deep T1 Prior进行快速MRI重建
398.DUNIT - Detection-Based Unsupervised Image-to-Image Translation
DUNIT-基于检测的无监督图像到图像转换
399.Dynamic Convolution - Attention Over Convolution Kernels
动态卷积-对卷积核的关注
400.Dynamic Convolutions - Exploiting Spatial Sparsity for Faster Inference
动态卷积-利用空间稀疏性进行更快的推理
401.Dynamic Face Video Segmentation via Reinforcement Learning
通过强化学习进行动态人脸视频分割
402.Dynamic Fluid Surface Reconstruction Using Deep Neural Network
基于深度神经网络的动态流体表面重建
403.Dynamic Graph Message Passing Networks
动态图消息传递网络
404.Dynamic Hierarchical Mimicking Towards Consistent Optimization Objectives
朝着一致的优化目标进行动态层次模拟
405.Dynamic Multiscale Graph Neural Networks for 3D Skeleton Based Human Motion Prediction
基于3D骨架的人体运动预测的动态多尺度图神经网络
406.Dynamic Neural Relational Inference
动态神经关系推理
407.Dynamic Refinement Network for Oriented and Densely Packed Object Detection
用于定向和密集包装对象检测的动态优化网络
408.Dynamic Traffic Modeling From Overhead Imagery
头顶影像的动态流量建模
409.ECA-Net - Efficient Channel Attention for Deep Convolutional Neural Networks
ECA-Net-深度卷积神经网络的有效通道注意
410.EcoNAS - Finding Proxies for Economical Neural Architecture Search
EcoNAS-寻找经济型神经建筑搜索的代理
411.Editing in Style - Uncovering the Local Semantics of GANs
样式编辑-探索GAN的本地语义
412.Effectively Unbiased FID and Inception Score and Where to Find Them
有效无偏的FID和初始分数以及在何处找到它们
413.Efficient Adversarial Training With Transferable Adversarial Examples
高效的对抗训练,包括可转移的对抗示例
414.Efficient and Robust Shape Correspondence via Sparsity-Enforced Quadratic Assignment
通过稀疏性增强的二次分配实现高效且鲁棒的形状对应
415.Efficient Derivative Computation for Cumulative B-Splines on Lie Groups
李群上累积B样条的有效导数计算
416.EfficientDet - Scalable and Efficient Object Detection
EfficientDet-可扩展且高效的对象检测
417.Efficient Dynamic Scene Deblurring Using Spatially Variant Deconvolution Network With Optical Flow Guided Training
使用空间变解卷积网络和光流引导训练进行有效的动态场景去模糊
418.Efficient Neural Vision Systems Based on Convolutional Image Acquisition
基于卷积图像采集的高效神经视觉系统
419.Ego-Topo - Environment Affordances From Egocentric Video
Ego-Topo-以自我为中心的视频带来的环境负担
420.Embedding Expansion - Augmentation in Embedding Space for Deep Metric Learning
嵌入扩展-深度学习中嵌入空间的扩充
421.Embodied Language Grounding With 3D Visual Feature Representations
具有3D视觉特征表示的体现语言基础
422.EmotiCon - Context-Aware Multimodal Emotion Recognition Using Frege’s Principle
EmotiCon-使用弗雷格原理的情境感知多模式情感识别
423.End-to-End 3D Point Cloud Instance Segmentation Without Detection
无需检测的端到端3D点云实例分割
424.End-to-End Adversarial-Attention Network for Multi-Modal Clustering
用于多模式聚类的端到端对抗注意力网络
425.End-to-End Camera Calibration for Broadcast Videos
广播视频的端到端摄像机校准
426.End-to-End Illuminant Estimation Based on Deep Metric Learning
基于深度度量学习的端到端光源估计
427.End-to-End Learnable Geometric Vision by Backpropagating PnP Optimization
通过反向传播PnP优化实现端到端可学习的几何视觉
428.End-to-End Learning Local Multi-View Descriptors for 3D Point Clouds
3D点云的端到端学习本地多视图描述符
429.End-to-End Learning of Visual Representations From Uncurated Instructional Videos
从未经整理的教学视频中端到端学习视觉表示
430.End-to-End Model-Free Reinforcement Learning for Urban Driving Using Implicit Affordances
使用内隐负担实现端到端的无模型强化驾驶学习
431.End-to-End Optimization of Scene Layout
场景布局的端到端优化
432.End-to-End Pseudo-LiDAR for Image-Based 3D Object Detection
端到端伪LiDAR用于基于图像的3D对象检测
433.Enhanced Blind Face Restoration With Multi-Exemplar Images and Adaptive Spatial Feature Fusion
具有多示例图像和自适应空间特征融合的增强型盲脸修复
434.Enhanced Transport Distance for Unsupervised Domain Adaptation
增强的传输距离,实现无监督域自适应
435.Enhancing Cross-Task Black-Box Transferability of Adversarial Examples With Dispersion Reduction
通过减少色散增强对抗性示例的跨任务黑箱可传递性
436.Enhancing Generic Segmentation With Learned Region Representations
通过学习的区域表示法增强通用细分
437.Enhancing Intrinsic Adversarial Robustness via Feature Pyramid Decoder
通过特征金字塔解码器增强内在的对抗鲁棒性
438.ENSEI - Efficient Secure Inference via Frequency-Domain Homomorphic Convolution for Privacy-Preserving Visual Recognition
ENSEI-通过频域同态卷积进行有效的安全推理,以保护隐私
439.Ensemble Generative Cleaning With Feedback Loops for Defending Adversarial Attacks
集成带有反馈回路的生成式清洗以防御对抗性攻击
440.Epipolar Transformers
对极变压器
441.Episode-Based Prototype Generating Network for Zero-Shot Learning
基于情节的零射击学习原型生成网络
442.EPOS - Estimating 6D Pose of Objects With Symmetries
EPOS-估计具有对称性的对象的6D姿势
443.Equalization Loss for Long-Tailed Object Recognition
长尾物体识别的均衡损失
444.Erasing Integrated Learning - A Simple Yet Effective Approach for Weakly Supervised Object Localization
消除集成学习-用于弱监督对象定位的简单而有效的方法
445.Estimating Low-Rank Region Likelihood Maps
估计低秩区域可能性图
446.Eternal Sunshine of the Spotless Net - Selective Forgetting in Deep Networks
一尘不染的网络的永恒阳光-深度网络中的选择性遗忘
447.Evade Deep Image Retrieval by Stashing Private Images in the Hash Space
通过在哈希空间中存储私人图像来逃避深度图像检索
448.Evaluating Weakly Supervised Object Localization Methods Right
评估弱监督对象定位方法的权利
449.EventCap - Monocular 3D Capture of High-Speed Human Motions Using an Event Camera
EventCap-使用事件摄像机对高速人类动作进行单眼3D捕获
450.Event Probability Mask (EPM) and Event Denoising Convolutional Neural Network (EDnCNN) for Neuromorphic Cameras
用于神经形态相机的事件概率掩码(EPM)和事件去噪卷积神经网络(EDnCNN)
451.EventSR - From Asynchronous Events to Image Reconstruction, Restoration, and Super-Resolution via End-to-End Adversarial Learning
EventSR-从异步事件到通过端到端对抗学习的图像重建,恢复和超分辨率
452.Evolving Losses for Unsupervised Video Representation Learning
无监督视频表示学习中不断发展的损失
453.Exemplar Normalization for Learning Deep Representation
学习深度表示的样本归一化
454.Explainable Object-Induced Action Decision for Autonomous Vehicles
自主车辆的可解释的对象诱导动作决策
455.Explaining Knowledge Distillation by Quantifying the Knowledge
通过量化知识解释知识蒸馏
456.Exploit Clues From Views - Self-Supervised and Regularized Learning for Multiview Object Recognition
从视图利用线索-用于多视图对象识别的自我监督和规则学习
457.Exploiting Joint Robustness to Adversarial Perturbations
利用对抗攻击的联合鲁棒性
458.Explorable Super Resolution
可探索的超分辨率
459.Exploring Bottom-Up and Top-Down Cues With Attentive Learning for Webly Supervised Object Detection
通过专心学习探索自下而上和自上而下的提示以进行Web监督对象检测
460.Exploring Categorical Regularization for Domain Adaptive Object Detection
探索领域自适应对象检测的分类正则化
461.Exploring Category-Agnostic Clusters for Open-Set Domain Adaptation
探索与类别无关的集群以进行开放集域适配
462.Exploring Data Aggregation in Policy Learning for Vision-Based Urban Autonomous Driving
在基于视觉的城市自动驾驶策略学习中探索数据聚合
463.Exploring Self-Attention for Image Recognition
探索图像识别的自我注意
464.Exploring Spatial-Temporal Multi-Frequency Analysis for High-Fidelity and Temporal-Consistency Video Prediction
探索时空多频分析以实现高保真和时间一致性视频预测
465.Exploring Unlabeled Faces for Novel Attribute Discovery
探索未标记的面孔以发现新颖的属性
466.Extremely Dense Point Correspondences Using a Learned Feature Descriptor
使用学习的特征描述符的极密点对应
467.Extreme Relative Pose Network Under Hybrid Representations
混合表示下的极端相对姿势网络
468.FaceScape - A Large-Scale High Quality 3D Face Dataset and Detailed Riggable 3D Face Prediction
FaceScape-大规模高质量3D人脸数据集和详细的可固定3D人脸预测
469.Face X-Ray for More General Face Forgery Detection
面部X射线可进行更一般的面部伪造检测
470.Factorized Higher-Order CNNs With an Application to Spatio-Temporal Emotion Estimation
分解高阶CNN在时空情感估计中的应用
471.FALCON - A Fourier Transform Based Approach for Fast and Secure Convolutional Neural Network Predictions
FALCON-基于傅立叶变换的快速安全卷积神经网络预测方法
472.Fantastic Answers and Where to Find Them - Immersive Question-Directed Visual Attention
奇妙的答案以及在哪里找到它们-沉浸式的问题导向视觉注意
473.Fashion Editing With Adversarial Parsing Learning
对抗分析学习的时尚编辑
474.Fashion Outfit Complementary Item Retrieval
时尚服装补充品检索
475.FastDVDnet - Towards Real-Time Deep Video Denoising Without Flow Estimation
FastDVDnet-无需流量估算即可实现实时深度视频降噪
476.Fast(er) Reconstruction of Shredded Text Documents via Self-Supervised Deep Asymmetric Metric Learning
通过自我监督的深度非对称度量学习来快速重建切碎的文本文档
477.Fast MSER
快速MSER
478.Fast-MVSNet - Sparse-to-Dense Multi-View Stereo With Learned Propagation and Gauss-Newton Refinement
Fast-MVSNet-具有学习的传播和高斯牛顿细化功能的稀疏到密集的多视图立体声
479.Fast Soft Color Segmentation
快速柔和的色彩分割
480.Fast Sparse ConvNets
快速稀疏卷积网络
481.Fast Symmetric Diffeomorphic Image Registration with Convolutional Neural Networks
卷积神经网络的快速对称双态图像配准
482.Fast Template Matching and Update for Video Object Tracking and Segmentation
用于视频对象跟踪和分段的快速模板匹配和更新
483.Fast Texture Synthesis via Pseudo Optimizer
通过伪优化器快速纹理合成
484.Fast Video Object Segmentation With Temporal Aggregation Network and Dynamic Template Matching
时间聚合网络和动态模板匹配的快速视频对象分割
485.FBNetV2 - Differentiable Neural Architecture Search for Spatial and Channel Dimensions
FBNetV2-用于空间和通道尺寸的可区分神经架构搜索
486.F-BRS - Rethinking Backpropagating Refinement for Interactive Segmentation
F-BRS-重新考虑反向传播的细化以进行交互式细分
487.FDA - Fourier Domain Adaptation for Semantic Segmentation
FDA-用于语义分割的傅里叶域自适应
488.FeatureFlow - Robust Video Interpolation via Structure-to-Texture Generation
FeatureFlow-通过结构到纹理生成的强大视频插值
489.Feature-Metric Registration - A Fast Semi-Supervised Approach for Robust Point Cloud Registration Without Correspondences
特征度量注册-无需通信的鲁棒点云注册的快速半监督方法
490.Few Sample Knowledge Distillation for Efficient Network Compression
少量样本知识提炼可实现有效的网络压缩
491.Few-Shot Class-Incremental Learning
少量课堂增量学习
492.Few-Shot Learning of Part-Specific Probability Space for 3D Shape Segmentation
用于3D形状分割的零件特定概率空间的少量学习
493.Few-Shot Learning via Embedding Adaptation With Set-to-Set Functions
通过嵌入自适应与Set-to-Set功能进行少量学习
494.Few-Shot Object Detection With Attention-RPN and Multi-Relation Detector
带有注意力-RPN和多关系检测器的少量目标检测
495.Few-Shot Open-Set Recognition Using Meta-Learning
使用元学习的少量开放式识别
496.Few-Shot Pill Recognition
少药丸识别
497.Few-Shot Video Classification via Temporal Alignment
通过时间对齐进行少量视频分类
498.FGN - Fully Guided Network for Few-Shot Instance Segmentation
FGN-少量实例分割的全向导网络
499.Filter Grafting for Deep Neural Networks
深度神经网络的过滤器嫁接
500.Filter Response Normalization Layer - Eliminating Batch Dependence in the Training of Deep Neural Networks
过滤器响应归一化层-在深度神经网络训练中消除批次依赖
论文概要
501.Fine-Grained Generalized Zero-Shot Learning via Dense Attribute-Based Attention
通过基于密集属性的注意力进行细粒度的广义零射击学习
502.Fine-Grained Image-to-Image Transformation Towards Visual Recognition
细化图像到图像的视觉识别转换
503.Fine-Grained Video-Text Retrieval With Hierarchical Graph Reasoning
带有分层图推理的细粒度视频文本检索
504.FineGym - A Hierarchical Video Dataset for Fine-Grained Action Understanding
FineGym-用于细粒度动作理解的分层视频数据集
505.Fixed-Point Back-Propagation Training
定点反向传播训练
506.Flow2Stereo - Effective Self-Supervised Learning of Optical Flow and Stereo Matching
Flow2Stereo-光流和立体匹配的有效自我监督学习
507.Flow Contrastive Estimation of Energy-Based Models
能量模型的流量对比估计
508.FM2u-Net - Face Morphological Multi-Branch Network for Makeup-Invariant Face Verification
FM2u-Net-用于化妆不变脸部验证的脸部形态多分支网络
509.FOAL - Fast Online Adaptive Learning for Cardiac Motion Estimation
FOAL-用于心脏运动估计的快速在线自适应学习
510.FocalMix - Semi-Supervised Learning for 3D Medical Image Detection
FocalMix-用于3D医学图像检测的半监督学习
511.Focus on Defocus - Bridging the Synthetic to Real Domain Gap for Depth Estimation
专注于散焦-桥接合成器到真实域差距以进行深度估计
512.Footprints and Free Space From a Single Color Image
单色图像中的足迹和自由空间
513.Foreground-Aware Relation Network for Geospatial Object Segmentation in High Spatial Resolution Remote Sensing Imagery
高分辨率遥感影像中地理空间目标分割的前景感知关系网
514.Forward and Backward Information Retention for Accurate Binary Neural Networks
精确的二进制神经网络的前向和后向信息保留
515.FReeNet - Multi-Identity Face Reenactment
FReeNet-多身份人脸重现
516.Frequency Domain Compact 3D Convolutional Neural Networks
频域紧凑型3D卷积神经网络
517.FroDO - From Detections to 3D Objects
FroDO-从检测到3D对象
518.From Depth What Can You See - Depth Completion via Auxiliary Image Reconstruction
从深度您能看到什么-通过辅助图像重建实现深度
519.From Fidelity to Perceptual Quality - A Semi-Supervised Approach for Low-Light Image Enhancement
从保真到感知质量-低光图像增强的半监督方法
520.From Image Collections to Point Clouds With Self-Supervised Shape and Pose Networks
从图像集合到具有自我监督形状和姿势网络的点云
521.From Paris to Berlin - Discovering Fashion Style Influences Around the World
从巴黎到柏林-探索时尚风格在世界范围内的影响
522.From Patches to Pictures (PaQ-2-PiQ) - Mapping the Perceptual Space of Picture Quality
从补丁到图片(PaQ-2-PiQ)-映射图片质量的感知空间
523.From Two Rolling Shutters to One Global Shutter
从两个卷帘门到一个全局卷帘门
524.Front2Back - Single View 3D Shape Reconstruction via Front to Back Prediction
Front2Back-通过前后预测进行单视图3D形状重建
525.FSS-1000 - A 1000-Class Dataset for Few-Shot Segmentation
FSS-1000-适用于少量分割的1000类数据集
526.Fusing Wearable IMUs With Multi-View Images for Human Pose Estimation - A Geometric Approach
将可穿戴IMU与多视图图像融合以进行人体姿势估计-一种几何方法
527.Fusion-Aware Point Convolution for Online Semantic 3D Scene Segmentation
用于在线语义3D场景分割的融合感知点卷积
528.Future Video Synthesis With Object Motion Prediction
具有对象运动预测的未来视频合成
529.G2L-Net - Global to Local Network for Real-Time 6D Pose Estimation With Embedding Vector Features
G2L-Net-全局到本地网络,用于具有嵌入矢量功能的实时6D姿势估计
530.G3AN - Disentangling Appearance and Motion for Video Generation
G3AN-解析视频生成的外观和动作
531.GaitPart - Temporal Part-Based Model for Gait Recognition
GaitPart-基于时间部分的步态识别模型
532.Gait Recognition via Semi-supervised Disentangled Representation Learning to Identity and Covariate Features
通过半监督解缠表示学习步态识别身份和协变量特征
533.GAMIN - Generative Adversarial Multiple Imputation Network for Highly Missing Data
GAMIN-高度丢失数据的生成式对抗多插补网络
534.GAN Compression - Efficient Architectures for Interactive Conditional GANs
GAN压缩-用于交互式条件GAN的高效架构
535.GanHand - Predicting Human Grasp Affordances in Multi-Object Scenes
GanHand-预测多对象场景中的人类掌握度
536.Gated Channel Transformation for Visual Recognition
门控通道变换,用于视觉识别
537.Gate-Shift Networks for Video Action Recognition
用于视频动作识别的Gate-Shift网络
538.gDLS - - Generalized Pose-and-Scale Estimation Given Scale and Gravity Priors
gDLS–给定尺度和重力先验的广义姿势和尺度估计
539.Generalized ODIN - Detecting Out-of-Distribution Image Without Learning From Out-of-Distribution Data
通用ODIN-在不从分布数据中学习的情况下,检测分布图像
540.Generalized Product Quantization Network for Semi-Supervised Image Retrieval
用于半监督图像检索的广义产品量化网络
541.Generalized Zero-Shot Learning via Over-Complete Distribution
通过过度完全分布进行广义零射击学习
542.Generalizing Hand Segmentation in Egocentric Videos With Uncertainty-Guided Model Adaptation
具有不确定性指导的模型自适应在以自我为中心的视频中进行手分割
543.Generating 3D People in Scenes Without People
在没有人的场景中生成3D人
544.Generating Accurate Pseudo-Labels in Semi-Supervised Learning and Avoiding Overconfident Predictions via Hermite Polynomial Activations
在半监督学习中生成准确的伪标签,并通过Hermite多项式激活避免过度自信的预测
545.Generating and Exploiting Probabilistic Monocular Depth Estimates
生成和利用概率单眼深度估计
546.Generative-Discriminative Feature Representations for Open-Set Recognition
开放集识别的生成-区分特征表示
547.Generative Hybrid Representations for Activity Forecasting With No-Regret Learning
无遗憾学习的活动预测的生成混合表示
548.GeoDA - A Geometric Framework for Black-Box Adversarial Attacks
GeoDA-黑匣子对抗攻击的几何框架
549.Geometrically Principled Connections in Graph Neural Networks
图神经网络中的几何原理连接
550.Geometric Structure Based and Regularized Depth Estimation From 360 Indoor Imagery
基于360度室内影像的几何结构和深度估计。
论文概要
551.Geometry and Learning Co-Supported Normal Estimation for Unstructured Point Cloud
非结构化点云的几何和学习共同支持正态估计
552.Geometry-Aware Satellite-to-Ground Image Synthesis for Urban Areas
适用于城市的几何感知卫星到地面图像合成
553.GhostNet - More Features From Cheap Operations
GhostNet-廉价运营带来的更多功能
554.GHUM & GHUML - Generative 3D Human Shape and Articulated Pose Models
GHUM&GHUML-生成性3D人体形状和关节姿势模型
555.GIFnets - Differentiable GIF Encoding Framework
GIFnets-可区分的GIF编码框架
556.Global-Local Bidirectional Reasoning for Unsupervised Representation Learning of 3D Point Clouds
用于3D点云的无监督表示学习的全局局部双向推理
557.Global-Local GCN - Large-Scale Label Noise Cleansing for Face Recognition
全球本地GCN-用于面部识别的大规模标签噪声清除
558.Globally Optimal Contrast Maximisation for Event-Based Motion Estimation
基于事件的运动估计的全局最优对比度最大化
559.Global Optimality for Point Set Registration Using Semidefinite Programming
使用半定规划的点集配准的全局最优性
560.Global Texture Enhancement for Fake Face Detection in the Wild
用于野外假脸检测的全局纹理增强
561.GLU-Net - Global-Local Universal Network for Dense Flow and Correspondences
GLU-Net-致密流和对应关系的全球本地通用网络
562.GNN3DMOT - Graph Neural Network for 3D Multi-Object Tracking With 2D-3D Multi-Feature Learning
GNN3DMOT-用于2D-3D多特征学习的3D多目标跟踪的图形神经网络
563.Going Deeper With Lean Point Networks
通过精益点网络更深入
564.Gold Seeker - Information Gain From Policy Distributions for Goal-Oriented Vision-and-Langauge Reasoning
黄金搜索者-面向目标的视觉和语言推理从策略分发中获得的信息
565.Google Landmarks Dataset v2 - A Large-Scale Benchmark for Instance-Level Recognition and Retrieval
Google Landmarks Dataset v2-实例级识别和检索的大型基准
566.GP-NAS - Gaussian Process Based Neural Architecture Search
GP-NAS-基于高斯过程的神经架构搜索
567.GPS-Net - Graph Property Sensing Network for Scene Graph Generation
GPS-Net-用于场景图生成的图属性传感网络
568.Gradually Vanishing Bridge for Adversarial Domain Adaptation
对抗域适应的逐渐消失的桥梁
569.Graph Embedded Pose Clustering for Anomaly Detection
图嵌入姿势聚类用于异常检测
570.Graph-Guided Architecture Search for Real-Time Semantic Segmentation
基于图的体系结构搜索,用于实时语义分割
571.Graph Structured Network for Image-Text Matching
用于图文匹配的图结构网络
572.Graph-Structured Referring Expression Reasoning in the Wild
图结构化的野外表达推理
573.GraphTER - Unsupervised Learning of Graph Transformation Equivariant Representations via Auto-Encoding Node-Wise Transformations
GraphTER-通过自动编码节点明智变换来无监督学习图变换等变表示
574.GrappaNet - Combining Parallel Imaging With Deep Learning for Multi-Coil MRI Reconstruction
GrappaNet-将并行成像与深度学习相结合以进行多线圈MRI重建
575.GraspNet-1Billion - A Large-Scale Benchmark for General Object Grasping
GraspNet-1Billion-通用对象捕获的大规模基准
576.GreedyNAS - Towards Fast One-Shot NAS With Greedy Supernet
GreedyNAS-通过贪婪的超级网络实现快速一键式NAS
577.Grid-GCN for Fast and Scalable Point Cloud Learning
Grid-GCN用于快速和可扩展的点云学习
578.GroupFace - Learning Latent Groups and Constructing Group-Based Representations for Face Recognition
GroupFace-学习潜在组并构建基于组的表示以进行人脸识别
579.Group Sparsity - The Hinge Between Filter Pruning and Decomposition for Network Compression
组稀疏性-过滤器修剪与网络压缩分解之间的铰链
580.G-TAD - Sub-Graph Localization for Temporal Action Detection
G-TAD-用于时间动作检测的子图定位
581.Guided Variational Autoencoder for Disentanglement Learning
纠缠学习的引导变分自动编码器
582.Gum-Net - Unsupervised Geometric Matching for Fast and Accurate 3D Subtomogram Image Alignment and Averaging
Gum-Net-无监督的几何匹配,可实现快速,准确的3D子图图像对齐和平均
583.HAMBox - Delving Into Mining High-Quality Anchors on Face Detection
HAMBox-深入挖掘面部检测中的高质量锚点
584.HandVoxNet - Deep Voxel-Based Network for 3D Hand Shape and Pose Estimation From a Single Depth Map
HandVoxNet-基于深度体素的网络,可从单个深度图进行3D手形和姿势估计
585.Hardware-in-the-Loop End-to-End Optimization of Camera Image Processing Pipelines
摄像机图像处理管道的硬件在环端到端优化
586.Harmonizing Transferability and Discriminability for Adapting Object Detectors
协调可转移性和可分辨性以适应目标检测器
587.HCNAF - Hyper-Conditioned Neural Autoregressive Flow and its Application for Probabilistic Occupancy Map Forecasting
HCNAF-超条件神经自回归流及其在概率占用图预测中的应用
588.Height and Uprightness Invariance for 3D Prediction From a Single View
从单个视图进行3D预测的高度和垂直度不变性
589.Heterogeneous Knowledge Distillation Using Information Flow Modeling
使用信息流建模的异构知识提炼
590.Hi-CMD - Hierarchical Cross-Modality Disentanglement for Visible-Infrared Person Re-Identification
Hi-CMD-可视化红外人员重新识别的分层跨模态解缠
591.Hierarchical Clustering With Hard-Batch Triplet Loss for Person Re-Identification
具有硬批量三重损失的层次聚类,用于人员重新识别
592.Hierarchical Conditional Relation Networks for Video Question Answering
视频问题回答的分层条件关系网络
593.Hierarchical Feature Embedding for Attribute Recognition
分层特征嵌入的属性识别
594.Hierarchical Graph Attention Network for Visual Relationship Detection
视觉关系检测的层次图注意力网络
595.Hierarchical Human Parsing With Typed Part-Relation Reasoning
具有类型化的部分关系推理的分层人工解析
596.Hierarchically Robust Representation Learning
分层鲁棒表示学习
597.Hierarchical Pyramid Diverse Attention Networks for Face Recognition
分层金字塔多元注意网络用于人脸识别
598.Hierarchical Scene Coordinate Classification and Regression for Visual Localization
视觉场景的分层场景坐标分类和回归
599.High-Dimensional Convolutional Networks for Geometric Pattern Recognition
用于几何图案识别的高维卷积网络
600.HigherHRNet - Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation
HigherHRNet-用于自下而上的人体姿势估计的规模感知表示学习
论文概要
601.High-Frequency Component Helps Explain the Generalization of Convolutional Neural Networks
高频分量有助于解释卷积神经网络的泛化
602.High-Order Information Matters - Learning Relation and Topology for Occluded Person Re-Identification
高阶信息事项-学习关系和拓扑结构,用于对被禁者的重新识别
603.High-Performance Long-Term Tracking With Meta-Updater
使用Meta-Updater进行高性能的长期跟踪
604.High-Resolution Daytime Translation Without Domain Labels
没有域标签的高分辨率白天翻译
605.Hit-Detector - Hierarchical Trinity Architecture Search for Object Detection
Hit-Detector-用于对象检测的分层三位一体体系结构搜索
606.Holistically-Attracted Wireframe Parsing
整体吸引的线框解析
607.HOnnotate - A Method for 3D Annotation of Hand and Object Poses
HOnnotate-手和对象姿势的3D注释方法
608.HOPE-Net - A Graph-Based Model for Hand-Object Pose Estimation
HOPE-Net-基于图的手部姿势估计模型
609.How Does Noise Help Robustness - Explanation and Exploration under the Neural SDE Framework
噪声如何增强鲁棒性-神经SDE框架下的解释和探索
610.How Much Time Do You Have - Modeling Multi-Duration Saliency
您有多少时间-对多工期显着性建模
611.How to Train Your Deep Multi-Object Tracker
如何训练您的深度多对象跟踪器
612.How Useful Is Self-Supervised Pretraining for Visual Tasks -
自我监督的视觉任务预训练有多有用-
613.HRank - Filter Pruning Using High-Rank Feature Map
HRank-使用高等级特征图进行过滤修剪
614.HUMBI - A Large Multiview Dataset of Human Body Expressions
HUMBI-人体表达的大型多视图数据集
615.HVNet - Hybrid Voxel Network for LiDAR Based 3D Object Detection
HVNet-基于LiDAR的3D目标检测的混合体素网络
616.HybridPose - 6D Object Pose Estimation Under Hybrid Representations
HybridPose-混合表示下的6D对象姿态估计
617.Hyperbolic Image Embeddings
双曲图像嵌入
618.Hyperbolic Visual Embedding Learning for Zero-Shot Recognition
双曲视觉嵌入学习用于零发Rec识别
619.Hypergraph Attention Networks for Multimodal Learning
用于多模式学习的超图注意力网络
620.HyperSTAR - Task-Aware Hyperparameters for Deep Networks
HyperSTAR-用于深度网络的任务感知超参数
621.IDA-3D - Instance-Depth-Aware 3D Object Detection From Stereo Vision for Autonomous Driving
IDA-3D-用于自动驾驶的立体视觉实例深度感知3D对象检测
622.ILFO - Adversarial Attack on Adaptive Neural Networks
ILFO-自适应神经网络的对抗攻击
623.Image2StyleGAN++ - How to Edit the Embedded Images -
Image2StyleGAN +±如何编辑嵌入的图像-
624.Image Based Virtual Try-On Network From Unpaired Data
来自未配对数据的基于映像的虚拟试穿网络
625.Image Demoireing with Learnable Bandpass Filters
使用可学习的带通滤波器进行图像降级
626.Image Processing Using Multi-Code GAN Prior
使用多代码GAN Prior进行图像处理
627.Image Search With Text Feedback by Visiolinguistic Attention Learning
通过视觉语言注意力学习的文本反馈进行图像搜索
628.Image Super-Resolution With Cross-Scale Non-Local Attention and Exhaustive Self-Exemplars Mining
跨尺度非局部注意和穷举自样本挖掘的图像超分辨率
629.Imitative Non-Autoregressive Modeling for Trajectory Forecasting and Imputation
弹道预测和归因的模拟非自回归建模
630.Implicit Functions in Feature Space for 3D Shape Reconstruction and Completion
特征空间中的隐式函数用于3D形状重构和完成
631.Improved Few-Shot Visual Classification
改进的少量视觉分类
632.Improving Action Segmentation via Graph-Based Temporal Reasoning
通过基于图的时间推理改进动作细分
633.Improving Confidence Estimates for Unfamiliar Examples
改善不熟悉示例的置信度估计
634.Improving Convolutional Networks With Self-Calibrated Convolutions
通过自校准卷积改进卷积网络
635.Improving One-Shot NAS by Suppressing the Posterior Fading
通过抑制后退衰落改善单发NAS
636.Improving the Robustness of Capsule Networks to Image Affine Transformations
提高胶囊网络对图像仿射变换的鲁棒性
637.IMRAM - Iterative Matching With Recurrent Attention Memory for Cross-Modal Image-Text Retrieval
IMRAM-与递归注意存储器的迭代匹配,用于跨模态图像-文本检索
638.ImVoteNet - Boosting 3D Object Detection in Point Clouds With Image Votes
ImVoteNet-利用图像投票增强点云中的3D对象检测
639.Incremental Few-Shot Object Detection
增量式少量射击对象检测
640.Incremental Learning in Online Scenario
在线场景中的增量学习
641.In Defense of Grid Features for Visual Question Answering
防御网格特征以进行视觉问答
642.Inducing Hierarchical Compositional Model by Sparsifying Generator Network
稀疏生成器网络推导分层组成模型
643.Inferring Attention Shift Ranks of Objects for Image Saliency
为图像显着性推断对象的注意力转移等级
644.Inflated Episodic Memory With Region Self-Attention for Long-Tailed Visual Recognition
具有区域自我注意的膨胀式情节记忆,用于长尾视觉识别
645.Information-Driven Direct RGB-D Odometry
信息驱动的直接RGB-D里程表
646.In Perfect Shape - Certifiably Optimal 3D Shape Reconstruction From 2D Landmarks
完美的形状-可从2D地标可靠地优化3D形状重建
647.Instance-Aware, Context-Focused, and Memory-Efficient Weakly Supervised Object Detection
实例感知,上下文关注和内存有效的弱监督对象检测
648.Instance-Aware Image Colorization
实例感知的图像着色
649.Instance Credibility Inference for Few-Shot Learning
少量学习的实例可信度推断
650.Instance Guided Proposal Network for Person Search
用于人员搜索的实例指导投标网络
论文概要
651.Instance Segmentation of Biological Images Using Harmonic Embeddings
使用谐波嵌入的生物图像实例分割
652.Instance Shadow Detection
实例阴影检测
653.Intelligent Home 3D - Automatic 3D-House Design From Linguistic Descriptions Only
智能家居3D-仅基于语言描述的自动3D房屋设计
654.Interactive Image Segmentation With First Click Attention
初次点击注意的交互式图像分割
655.Interactive Multi-Label CNN Learning With Partial Labels
带有部分标签的交互式多标签CNN学习
656.Interactive Object Segmentation With Inside-Outside Guidance
内外引导的交互式对象分割
657.Interactive Two-Stream Decoder for Accurate and Fast Saliency Detection
交互式两码流解码器,可进行精确,快速的显着性检测
658.Interpretable and Accurate Fine-grained Recognition via Region Grouping
通过区域分组可解释且准确的细粒度识别
659.Interpreting the Latent Space of GANs for Semantic Face Editing
解释GAN的潜在空间以进行语义人脸编辑
660.Inter-Region Affinity Distillation for Road Marking Segmentation
区域间亲和力蒸馏用于道路标记分割
661.Inter-Task Association Critic for Cross-Resolution Person Re-Identification
跨任务人员重新识别的任务间协会批评
662.IntrA - 3D Intracranial Aneurysm Dataset for Deep Learning
IntrA-深度学习的3D颅内动脉瘤数据集
663.Intra- and Inter-Action Understanding via Temporal Action Parsing
通过时间动作解析进行动作内和动作间理解
664.Intuitive, Interactive Beard and Hair Synthesis With Generative Models
直观,交互式胡须和具有生成模型的头发合成
665.Inverse Rendering for Complex Indoor Scenes - Shape, Spatially-Varying Lighting and SVBRDF From a Single Image
复杂室内场景的逆向渲染-单个图像的形状,空间变化的照明和SVBRDF
666.iTAML - An Incremental Task-Agnostic Meta-learning Approach
iTAML-一种与任务无关的增量式元学习方法
667.Iterative Answer Prediction With Pointer-Augmented Multimodal Transformers for TextVQA
用于TextVQA的指针增强型多模态变压器的迭代答案预测
668.Iterative Context-Aware Graph Inference for Visual Dialog
可视对话框的迭代上下文感知图推理
669.Iteratively-Refined Interactive 3D Medical Image Segmentation With Multi-Agent Reinforcement Learning
具有多智能体强化学习的迭代式交互式3D医学图像分割
670.JA-POLS - A Moving-Camera Background Model via Joint Alignment and Partially-Overlapping Local Subspaces
JA-POLS-通过联合对齐和部分重叠的局部子空间的运动相机背景模型
671.JL-DCF - Joint Learning and Densely-Cooperative Fusion Framework for RGB-D Salient Object Detection
JL-DCF-用于RGB-D显着目标检测的联合学习和密集合作融合框架
672.Joint 3D Instance Segmentation and Object Detection for Autonomous Driving
联合3D实例分割和自动驾驶对象检测
673.Joint Demosaicing and Denoising With Self Guidance
自我指导联合去马赛克和去噪
674.Joint Filtering of Intensity Images and Neuromorphic Events for High-Resolution Noise-Robust Imaging
强度图像和神经形态事件的联合滤波,用于高分辨率噪声鲁棒成像
675.Joint Graph-Based Depth Refinement and Normal Estimation
基于图的联合深度细化和法线估计
676.Joint Semantic Segmentation and Boundary Detection Using Iterative Pyramid Contexts
使用迭代金字塔上下文的联合语义分割和边界检测
677.Joint Spatial-Temporal Optimization for Stereo 3D Object Tracking
立体3D物体跟踪的时空联合优化
678.Joint Texture and Geometry Optimization for RGB-D Reconstruction
用于RGB-D重建的联合纹理和几何优化
679.Joint Training of Variational Auto-Encoder and Latent Energy-Based Model
变分自动编码器和潜能模型的联合训练
680.Just Go With the Flow - Self-Supervised Scene Flow Estimation
随心所欲-自我监督的场景流估计
681.KeypointNet - A Large-Scale 3D Keypoint Dataset Aggregated From Numerous Human Annotations
KeypointNet-从众多人类注释中聚合的大规模3D关键点数据集
682.KeyPose - Multi-View 3D Labeling and Keypoint Estimation for Transparent Objects
KeyPose-透明对象的多视图3D标注和关键点估计
683.KFNet - Learning Temporal Camera Relocalization Using Kalman Filtering
KFNet-使用卡尔曼滤波学习时间相机的重新定位
684.Knowledge As Priors - Cross-Modal Knowledge Generalization for Datasets Without Superior Knowledge
先验知识-没有高级知识的数据集的跨模式知识泛化
685.L2-GCN - Layer-Wise and Learned Efficient Training of Graph Convolutional Networks
L2-GCN-图卷积网络的层明智学习型有效训练
686.Label Decoupling Framework for Salient Object Detection
用于显着对象检测的标签解耦框架
687.Label Distribution Learning on Auxiliary Label Space Graphs for Facial Expression Recognition
用于面部表情识别的辅助标签空间图上的标签分布学习
688.Large-Scale Object Detection in the Wild From Imbalanced Multi-Labels
不平衡多标签在野外进行大规模目标检测
689.Large Scale Video Representation Learning via Relational Graph Clustering
通过关系图聚类的大规模视频表示学习
690.LatentFusion - End-to-End Differentiable Reconstruction and Rendering for Unseen Object Pose Estimation
LatentFusion-看不见的对象姿势估计的端到端可微重构和渲染
691.Learn2Perturb - An End-to-End Feature Perturbation Learning to Improve Adversarial Robustness
Learn2Perturb-端到端特征扰动学习,可提高对抗性的鲁棒性
692.Learned Image Compression With Discretized Gaussian Mixture Likelihoods and Attention Modules
离散高斯混合似然和注意力模块的学习图像压缩
693.Learning 3D Semantic Scene Graphs From 3D Indoor Reconstructions
从3D室内重建中学习3D语义场景图
694.Learning a Dynamic Map of Visual Appearance
学习视觉外观的动态图
695.Learning a Neural 3D Texture Space From 2D Exemplars
从2D范例中学习神经3D纹理空间
696.Learning a Neural Solver for Multiple Object Tracking
学习用于多目标跟踪的神经求解器
697.Learning a Reinforced Agent for Flexible Exposure Bracketing Selection
学习用于灵活选择包围曝光的增强剂
698.Learning Augmentation Network via Influence Functions
通过影响功能学习增强网络
699.Learning a Unified Sample Weighting Network for Object Detection
学习用于对象检测的统一样本加权网络
700.Learning a Weakly-Supervised Video Actor-Action Segmentation Model With a Wise Selection
通过明智选择学习弱监督的视频演员-动作细分模型
论文概要
701.Learning Better Lossless Compression Using Lossy Compression
使用有损压缩学习更好的无损压缩
702.Learning by Analogy - Reliable Supervision From Transformations for Unsupervised Optical Flow Estimation
类比学习-通过无监督光流估计的变换可靠地进行监督
703.Learning Canonical Shape Space for Category-Level 6D Object Pose and Size Estimation
学习规范形状空间以进行类别级6D对象姿势和大小估计
704.Learning Combinatorial Solver for Graph Matching
学习组合求解器进行图匹配
705.Learning Deep Network for Detecting 3D Object Keypoints and 6D Poses
学习深度网络以检测3D对象关键点和6D姿势
706.Learning Depth-Guided Convolutions for Monocular 3D Object Detection
学习用于单眼3D对象检测的深度引导卷积
707.Learning Dynamic Relationships for 3D Human Motion Prediction
学习动态关系以进行3D人体运动预测
708.Learning Dynamic Routing for Semantic Segmentation
学习用于语义分割的动态路由
709.Learning Event-Based Motion Deblurring
学习基于事件的运动去模糊
710.Learning Fast and Robust Target Models for Video Object Segmentation
学习快速而强大的视频对象分割目标模型
711.Learning Filter Pruning Criteria for Deep Convolutional Neural Networks Acceleration
深度卷积神经网络加速的学习过滤器修剪标准
712.Learning Formation of Physically-Based Face Attributes
基于身体的面部属性的学习形式
713.Learning for Video Compression With Hierarchical Quality and Recurrent Enhancement
具有分层质量和递归增强的视频压缩学习
714.Learning From Noisy Anchors for One-Stage Object Detection
向嘈杂的锚点学习以进行一阶段对象检测
715.Learning From Synthetic Animals
向合成动物学习
716.Learning From Web Data With Self-Organizing Memory Module
使用自组织存储模块从Web数据中学习
717.Learning Fused Pixel and Feature-Based View Reconstructions for Light Fields
学习融合的像素和基于特征的光场视图重建
718.Learning Generative Models of Shape Handles
学习形状手柄的生成模型
719.Learning Geocentric Object Pose in Oblique Monocular Images
学习倾斜单眼图像中的地心物体姿势
720.Learning Human-Object Interaction Detection Using Interaction Points
使用交互点学习人对象交互检测
721.Learning Identity-Invariant Motion Representations for Cross-ID Face Reenactment
学习身份不变的运动表示形式以进行交叉ID人脸重现
722.Learning Individual Speaking Styles for Accurate Lip to Speech Synthesis
学习个别的说话风格,以实现准确的口语合成
723.Learning Instance Occlusion for Panoptic Segmentation
全景分割的学习实例遮挡
724.Learning Integral Objects With Intra-Class Discriminator for Weakly-Supervised Semantic Segmentation
使用类内鉴别器学习积分对象以进行弱监督的语义分割
725.Learning Interactions and Relationships Between Movie Characters
学习电影角色之间的互动和关系
726.Learning in the Frequency Domain
在频域学习
727.Learning Invariant Representation for Unsupervised Image Restoration
学习用于无监督图像恢复的不变表示
728.Learning Longterm Representations for Person Re-Identification Using Radio Signals
学习长期表示以使用无线电信号进行人员重新识别
729.Learning Memory-Guided Normality for Anomaly Detection
学习记忆指导的正常性以进行异常检测
730.Learning Meta Face Recognition in Unseen Domains
在看不见的领域中学习元脸识别
731.Learning Multi-Granular Hypergraphs for Video-Based Person Re-Identification
学习基于视频的人重新识别的多粒度超图
732.Learning Multi-Object Tracking and Segmentation From Automatic Annotations
从自动注释中学习多对象跟踪和分段
733.Learning Multiview 3D Point Cloud Registration
学习Multiview 3D点云注册
734.Learning Multi-View Camera Relocalization With Graph Neural Networks
使用图神经网络学习多视图相机重新定位
735.Learning Nanoscale Motion Patterns of Vesicles in Living Cells
学习活细胞中囊泡的纳米尺度运动模式。
736.Learning Oracle Attention for High-Fidelity Face Completion
了解Oracle对高保真面部完成的关注
737.Learning Physics-Guided Face Relighting Under Directional Light
在定向光下学习物理引导的面部重新照明
738.Learning Rank-1 Diffractive Optics for Single-Shot High Dynamic Range Imaging
学习等级1衍射光学器件用于单次高动态范围成像
739.Learning Representations by Predicting Bags of Visual Words
通过预测视觉单词袋来学习表示形式
740.Learning Saliency Propagation for Semi-Supervised Instance Segmentation
学习显着性传播用于半监督实例细分
741.Learning Selective Self-Mutual Attention for RGB-D Saliency Detection
学习用于RGB-D显着性检测的选择性自我注意
742.Learning Situational Driving
学习情境驾驶
743.Learning Temporal Co-Attention Models for Unsupervised Video Action Localization
学习时间协同注意模型的无监督视频动作本地化
744.Learning Texture Invariant Representation for Domain Adaptation of Semantic Segmentation
学习纹理不变表示以进行语义分割领域的适应
745.Learning Texture Transformer Network for Image Super-Resolution
学习纹理变压器网络以实现图像超分辨率
746.Learning the Redundancy-Free Features for Generalized Zero-Shot Object Recognition
学习无冗余功能以进行广义零散物体识别
747.Learning to Autofocus
学习自动对焦
748.Learning to Cartoonize Using White-Box Cartoon Representations
学习使用白盒卡通表示来卡通化
749.Learning to Cluster Faces via Confidence and Connectivity Estimation
通过置信度和连通性估计学习将面孔聚类
750.Learning to Detect Important People in Unlabelled Images for Semi-Supervised Important People Detection
学会检测未标记图像中的重要人物以进行​​半监督的重要人物检测
论文概要
751.Learning to Discriminate Information for Online Action Detection
学习区分信息以进行在线动作检测
752.Learning to Dress 3D People in Generative Clothing
学习让3D人穿着有创造力的服装
753.Learning to Evaluate Perception Models Using Planner-Centric Metrics
学习使用计划者中心指标评估感知模型
754.Learning to Forget for Meta-Learning
学习忘记元学习
755.Learning to Generate 3D Training Data Through Hybrid Gradient
学习通过混合梯度生成3D训练数据
756.Learning to Have an Ear for Face Super-Resolution
学习聆听面部超分辨率
757.Learning to Learn Cropping Models for Different Aspect Ratio Requirements
学习学习不同长宽比要求的裁剪模型
758.Learning to Learn Single Domain Generalization
学习学习单域泛化
759.Learning to Manipulate Individual Objects in an Image
学习操纵图像中的单个对象
760.Learning to Measure the Static Friction Coefficient in Cloth Contact
学习测量布接触中的静摩擦系数
761.Learning to Observe - Approximating Human Perceptual Thresholds for Detection of Suprathreshold Image Transformations
学习观察-逼近人类感知阈值以检测超阈值图像转换
762.Learning to Optimize Non-Rigid Tracking
学习优化非刚性跟踪
763.Learning to Optimize on SPD Manifolds
学习优化SPD流形
764.Learning to Restore Low-Light Images via Decomposition-and-Enhancement
学习通过分解和增强来还原弱光图像
765.Learning to See Through Obstructions
学会看透障碍物
766.Learning to Segment 3D Point Clouds in 2D Image Space
学习在2D图像空间中分割3D点云
767.Learning to Segment the Tail
学习分割尾巴
768.Learning to Select Base Classes for Few-Shot Classification
学习选择基本类别进行少分类
769.Learning to Shadow Hand-Drawn Sketches
学习阴影手绘草图
770.Learning to Simulate Dynamic Environments With GameGAN
学习使用GameGAN模拟动态环境
771.Learning to Structure an Image With Few Colors
学习构建颜色很少的图像
772.Learning to Super Resolve Intensity Images From Events
学会从事件中超级分辨强度图像
773.Learning to Transfer Texture From Clothing Images to 3D Humans
学习将纹理从服装图像转移到3D人体
774.Learning Unseen Concepts via Hierarchical Decomposition and Composition
通过分层分解和组合学习看不见的概念
775.Learning Unsupervised Hierarchical Part Decomposition of 3D Objects From a Single RGB Image
从单个RGB图像中学习3D对象的无监督分层分解
776.Learning User Representations for Open Vocabulary Image Hashtag Prediction
学习用户表示形式的开放式词汇图像标签预测
777.Learning Video Object Segmentation From Unlabeled Videos
从未标记的视频中学习视频对象分割
778.Learning Video Stabilization Using Optical Flow
使用光流学习视频稳定
779.Learning Visual Emotion Representations From Web Data
从Web数据学习视觉情感表示
780.Learning Visual Motion Segmentation Using Event Surfaces
使用事件表面学习视觉运动分割
781.Learning Weighted Submanifolds With Variational Autoencoders and Riemannian Variational Autoencoders
用变分自动编码器和黎曼变分自动编码器学习加权子流形
782.Learning When and Where to Zoom With Deep Reinforcement Learning
通过深度强化学习来学习何时何地进行缩放
783.Learn to Augment - Joint Data Augmentation and Network Optimization for Text Recognition
学习增强-用于文本识别的联合数据增强和网络优化
784.Leveraging 2D Data to Learn Textured 3D Mesh Generation
利用2D数据学习纹理3D网格生成
785.Leveraging Photometric Consistency Over Time for Sparsely Supervised Hand-Object Reconstruction
利用随时间变化的光度一致性进行稀疏监督的手对象重建
786.LG-GAN - Label Guided Adversarial Network for Flexible Targeted Attack of Point Cloud Based Deep Networks
LG-GAN-标签导向对抗网络,用于基于点云的深度网络的灵活定向攻击
787.LiDAR-Based Online 3D Video Object Detection With Graph-Based Message Passing and Spatiotemporal Transformer Attention
基于LiDAR的在线3D视频对象检测以及基于图的消息传递和时空变压器注意
788.LiDARsim - Realistic LiDAR Simulation by Leveraging the Real World
LiDARsim-利用现实世界进行逼真的LiDAR仿真
789.Light Field Spatial Super-Resolution via Deep Combinatorial Geometry Embedding and Structural Consistency Regularization
通过深组合几何嵌入和结构一致性正则化实现光场空间超分辨率
790.Lighthouse - Predicting Lighting Volumes for Spatially-Coherent Illumination
灯塔-预测空间相干照明的照明量
791.Light-weight Calibrator - A Separable Component for Unsupervised Domain Adaptation
轻量级校准器-用于无监督域自适应的可分离组件
792.Lightweight Multi-View 3D Pose Estimation Through Camera-Disentangled Representation
通过摄像头分解表示的轻量级多视图3D姿势估计
793.Lightweight Photometric Stereo for Facial Details Recovery
轻巧的光度学立体声,可恢复面部细节
794.Listen to Look - Action Recognition by Previewing Audio
聆听外观-通过预览音频进行动作识别
795.Local Class-Specific and Global Image-Level Generative Adversarial Networks for Semantic-Guided Scene Generation
用于语义指导场景生成的局部特定类和全局图像级生成对抗网络
796.Local Context Normalization - Revisiting Local Normalization
本地上下文规范化-重新审视本地规范化
797.Local Deep Implicit Functions for 3D Shape
3D形状的局部深层隐式函数
798.Local-Global Video-Text Interactions for Temporal Grounding
局部-全局视频-文本交互以进行临时接地
799.Local Implicit Grid Representations for 3D Scenes
3D场景的局部隐式网格表示
800.Local Non-Rigid Structure-From-Motion From Diffeomorphic Mappings
不同形态映射的局部非刚动构造
论文概要
801.Looking at the Right Stuff - - Guided Semantic-Gaze for Autonomous Driving
看着正确的东西–自动驾驶引导的语义注视
802.Look-Into-Object - Self-Supervised Structure Modeling for Object Recognition
查找对象-用于对象识别的自监督结构建模
803.Low-Rank Compression of Neural Nets - Learning the Rank of Each Layer
神经网络的低秩压缩-学习每一层的等级
804.LSM - Learning Subspace Minimization for Low-Level Vision
LSM-针对低视力的学习子空间最小化
805.LT-Net - Label Transfer by Learning Reversible Voxel-Wise Correspondence for One-Shot Medical Image Segmentation
LT-Net-通过学习可逆的Voxel-Wise对应来进行单次医学图像分割的标签转移
806.LUVLi Face Alignment - Estimating Landmarks’ Location, Uncertainty, and Visibility Likelihood
LUVLi人脸对齐-估计地标的位置,不确定性和可见性可能性
807.M2m - Imbalanced Classification via Major-to-Minor Translation
M2m-通过重大到次要翻译的不平衡分类
808.MAGSAC++, a Fast, Reliable and Accurate Robust Estimator
MAGSAC ++,一种快速,可靠且准确的稳健估计器
809.Maintaining Discrimination and Fairness in Class Incremental Learning
在班级增量学习中保持歧视和公平
810.Making Better Mistakes - Leveraging Class Hierarchies With Deep Networks
更好地犯错误-利用深层网络利用类层次结构
811.ManiGAN - Text-Guided Image Manipulation
ManiGAN-文本引导的图像处理
812.MANTRA - Memory Augmented Networks for Multiple Trajectory Prediction
MANTRA-用于多轨迹预测的内存增强网络
813.Mapillary Street-Level Sequences - A Dataset for Lifelong Place Recognition
枫叶街道级序列-终身场所识别的数据集
814.MARMVS - Matching Ambiguity Reduced Multiple View Stereo for Efficient Large Scale Scene Reconstruction
MARMVS-匹配歧义减少了多视图立体声,可进行高效的大规模场景重建
815.Mask Encoding for Single Shot Instance Segmentation
单镜头实例分割的蒙版编码
816.MaskFlownet - Asymmetric Feature Matching With Learnable Occlusion Mask
MaskFlownet-具有可学习遮挡遮罩的非对称特征匹配
817.MaskGAN - Towards Diverse and Interactive Facial Image Manipulation
MaskGAN-走向多样化和交互式的面部图像处理
818.MAST - A Memory-Augmented Self-Supervised Tracker
MAST-记忆增强的自我监督跟踪器
819.MCEN - Bridging Cross-Modal Gap between Cooking Recipes and Dish Images with Latent Variable Model
MCEN-使用潜在变量模型弥合烹饪食谱和菜品图像之间的跨模态差距
820.McFlow - Monte Carlo Flow Models for Data Imputation
数据插补的McFlow-蒙特卡洛流模型
821.MEBOW - Monocular Estimation of Body Orientation in the Wild
MEBOW-野外身体定向的单眼估计
822.MemNAS - Memory-Efficient Neural Architecture Search With Grow-Trim Learning
MemNAS-通过成长修剪学习实现内存有效的神经体系结构搜索
823.Memory Aggregation Networks for Efficient Interactive Video Object Segmentation
用于高效交互式视频对象分割的内存聚合网络
824.Memory-Efficient Hierarchical Neural Architecture Search for Image Denoising
内存有效的分层神经体系结构图像降噪搜索
825.Memory Enhanced Global-Local Aggregation for Video Object Detection
用于视频对象检测的内存增强全局全局聚合
826.Meshed-Memory Transformer for Image Captioning
用于图像字幕的网状存储器变压器
827.Mesh-Guided Multi-View Stereo With Pyramid Architecture
具有金字塔体系结构的网格引导多视图立体声
828.Meshlet Priors for 3D Mesh Reconstruction
用于3D网格重建的Meshlet先验
829.MetaFuse - A Pre-trained Fusion Model for Human Pose Estimation
MetaFuse-用于人体姿势估计的预训练融合模型
830.MetaIQA - Deep Meta-Learning for No-Reference Image Quality Assessment
MetaIQA-用于无参考图像质量评估的深度元学习
831.Meta-Learning of Neural Architectures for Few-Shot Learning
神经体系结构的元学习,支持少量学习
832.METAL - Minimum Effort Temporal Activity Localization in Untrimmed Videos
METAL-未修饰视频中的最小努力时间活动本地化
833.Meta-Transfer Learning for Zero-Shot Super-Resolution
元传输学习,实现零射击的超高分辨率
834.MiLeNAS - Efficient Neural Architecture Search via Mixed-Level Reformulation
MiLeNAS-通过混合级重构实现高效的神经体系结构搜索
835.MINA - Convex Mixed-Integer Programming for Non-Rigid Shape Alignment
MINA-用于非刚性形状对准的凸混合整数编程
836.MineGAN - Effective Knowledge Transfer From GANs to Target Domains With Few Images
MineGAN-有效的知识从GAN到目标域的有效转移,图像很少
837.Minimal Solutions for Relative Pose With a Single Affine Correspondence
单仿射对应的相对姿势的最小解
838.Minimal Solutions to Relative Pose Estimation From Two Views Sharing a Common Direction With Unknown Focal Length
从两个视角共享焦距未知的公共方向的相对姿态估计的最小解
839.Minimal Solvers for 3D Scan Alignment With Pairs of Intersecting Lines
最小解算器,用于3D扫描与成对的相交线对齐
840.Minimizing Discrete Total Curvature for Image Processing
最小化图像处理的离散总曲率
841.MISC - Multi-Condition Injection and Spatially-Adaptive Compositing for Conditional Person Image Synthesis
MISC-用于条件人员图像合成的多条件注入和空间自适应合成
842.Mitigating Bias in Face Recognition Using Skewness-Aware Reinforcement Learning
使用偏斜度增强学习减轻人脸识别中的偏差
843.MixNMatch - Multifactor Disentanglement and Encoding for Conditional Image Generation
MixNMatch-用于条件图像生成的多因子解缠和编码
844.Mixture Dense Regression for Object Detection and Human Pose Estimation
用于目标检测和人体姿势估计的混合密度回归
845.MLCVNet - Multi-Level Context VoteNet for 3D Object Detection
MLCVNet-用于3D对象检测的多级上下文投票网
846.M-LVC - Multiple Frames Prediction for Learned Video Compression
M-LVC-学习视频压缩的多帧预测
847.MMTM - Multimodal Transfer Module for CNN Fusion
MMTM-用于CNN融合的多模式传输模块
848.MnasFPN - Learning Latency-Aware Pyramid Architecture for Object Detection on Mobile Devices
MnasFPN-学习延迟感知金字塔体系结构,用于移动设备上的对象检测
849.Mnemonics Training - Multi-Class Incremental Learning Without Forgetting
助记符训练-多级增量学习而不会忘记
850.Modality Shifting Attention Network for Multi-Modal Video Question Answering
多模态视频问答的模态转移注意网络
论文概要
851.Model Adaptation - Unsupervised Domain Adaptation Without Source Data
模型适应-没有源数据的无监督域适应
852.Modeling Biological Immunity to Adversarial Examples
对对抗性实例进行生物免疫建模
853.Modeling the Background for Incremental Learning in Semantic Segmentation
为语义分割中的增量学习背景建模
854.Momentum Contrast for Unsupervised Visual Representation Learning
无监督视觉表示学习的动量对比
855.Monocular Real-Time Hand Shape and Motion Capture Using Multi-Modal Data
使用多模态数据的单眼实时手形和运动捕捉
856.MonoPair - Monocular 3D Object Detection Using Pairwise Spatial Relationships
MonoPair-使用成对空间关系的单眼3D对象检测
857.MoreFusion - Multi-object Reasoning for 6D Pose Estimation from Volumetric Fusion
MoreFusion-基于体积融合的6D姿势估计的多对象推理
858.More Grounded Image Captioning by Distilling Image-Text Matching Model
通过提取图像-文本匹配模型来更扎实的图像字幕
859.MotionNet - Joint Perception and Motion Prediction for Autonomous Driving Based on Bird’s Eye View Maps
MotionNet-基于鸟瞰图的自动驾驶的联合感知和运动预测
860.Moving in the Right Direction - A Regularization for Deep Metric Learning
朝着正确的方向前进-深度度量学习的规则化
861.MPM - Joint Representation of Motion and Position Map for Cell Tracking
MPM-用于细胞跟踪的运动和位置图的联合表示
862.MSeg - A Composite Dataset for Multi-Domain Semantic Segmentation
MSeg-用于多域语义分割的复合数据集
863.MSG-GAN - Multi-Scale Gradients for Generative Adversarial Networks
MSG-GAN-生成对抗性网络的多尺度梯度
864.MTL-NAS - Task-Agnostic Neural Architecture Search Towards General-Purpose Multi-Task Learning
MTL-NAS-面向任务多用途学习的与任务无关的神经体系结构搜索
865.Multi-Dimensional Pruning - A Unified Framework for Model Compression
多维修剪-用于模型压缩的统一框架
866.Multi-Domain Learning for Accurate and Few-Shot Color Constancy
多域学习,可实现精确且稳定的色彩稳定
867.Multi-Granularity Reference-Aided Attentive Feature Aggregation for Video-Based Person Re-Identification
基于视频的人重新识别的多粒度参考辅助注意特征聚合
868.Multimodal Categorization of Crisis Events in Social Media
社交媒体中危机事件的多模式分类
869.Multi-Modal Domain Adaptation for Fine-Grained Action Recognition
细粒度动作识别的多模态域自适应
870.Multimodal Future Localization and Emergence Prediction for Objects in Egocentric View With a Reachability Prior
具有可到达性先验的自我中心视图中的对象的多峰未来定位和涌现预测
871.Multi-Modal Graph Neural Network for Joint Reasoning on Vision and Scene Text
视觉与场景文本联合推理的多模态图神经网络
872.Multi-Modality Cross Attention Network for Image and Sentence Matching
图像和句子匹配的多模式交叉注意网络
873.Multi-Mutual Consistency Induced Transfer Subspace Learning for Human Motion Segmentation
人体运动分割的多核一致性诱导转移子空间学习
874.Multi-Path Learning for Object Pose Estimation Across Domains
跨域对象姿势估计的多路径学习
875.Multi-Path Region Mining for Weakly Supervised 3D Semantic Segmentation on Point Clouds
多路径区域挖掘,用于点云上的弱监督3D语义分割
876.Multiple Anchor Learning for Visual Object Detection
用于视觉对象检测的多锚学习
877.Multi-Scale Boosted Dehazing Network With Dense Feature Fusion
具有密集特征融合的多尺度增强除雾网络
878.Multi-scale Domain-adversarial Multiple-instance CNN for Cancer Subtype Classification with Unannotated Histopathological Images
具有无注释组织病理学图像的癌症亚型分类的多尺度域对抗多实例CNN
879.Multi-Scale Fusion Subspace Clustering Using Similarity Constraint
使用相似性约束的多尺度融合子空间聚类
880.Multi-Scale Interactive Network for Salient Object Detection
用于显着目标检测的多尺度交互式网络
881.Multi-Scale Progressive Fusion Network for Single Image Deraining
用于单图像排水的多尺度渐进融合网络
882.Multi-Task Collaborative Network for Joint Referring Expression Comprehension and Segmentation
用于联合引用表达理解和分段的多任务协作网络
883.Multiview-Consistent Semi-Supervised Learning for 3D Human Pose Estimation
用于3D人体姿势估计的多视点一致半监督学习
884.Multi-View Neural Human Rendering
多视图神经人体渲染
885.Music Gesture for Visual Sound Separation
用于视觉声音分离的音乐手势
886.MUXConv - Information Multiplexing in Convolutional Neural Networks
MUXConv-卷积神经网络中的信息复用
887.NAS-FCOS - Fast Neural Architecture Search for Object Detection
NAS-FCOS-用于对象检测的快速神经体系结构搜索
888.Nested Scale-Editing for Conditional Image Synthesis
嵌套比例编辑用于条件图像合成
889.NestedVAE - Isolating Common Factors via Weak Supervision
NestedVAE-通过弱监督隔离公共因素
890.NETNet - Neighbor Erasing and Transferring Network for Better Single Shot Object Detection
NETNet-邻居擦除和传输网络可更好地检测单发目标
891.Network Adjustment - Channel Search Guided by FLOPs Utilization Ratio
网络调整-以FLOP利用率指导的频道搜索
892.Neural Architecture Search for Lightweight Non-Local Networks
神经架构搜索轻量级非本地网络
893.Neural Blind Deconvolution Using Deep Priors
使用深度先验的神经盲反卷积
894.Neural Cages for Detail-Preserving 3D Deformations
保持细节3D变形的神经笼
895.Neural Contours - Learning to Draw Lines From 3D Shapes
神经轮廓-学习从3D形状绘制线条
896.Neural Data Server - A Large-Scale Search Engine for Transfer Learning Data
神经数据服务器-用于传输学习数据的大型搜索引擎
897.Neural Head Reenactment with Latent Pose Descriptors
具有潜在姿势描述符的神经头部重演
898.Neural Implicit Embedding for Point Cloud Analysis
神经隐式嵌入的点云分析
899.Neural Network Pruning With Residual-Connections and Limited-Data
带有残留连接和受限数据的神经网络修剪
900.Neural Networks Are More Productive Teachers Than Human Raters - Active Mixup for Data-Efficient Knowledge Distillation From a Blackbox Model
神经网络比人类评价者更具生产力-从黑匣子模型中主动混合数据有效的知识提炼
论文概要
901.Neural Point Cloud Rendering via Multi-Plane Projection
通过多平面投影进行神经点云渲染
902.Neural Pose Transfer by Spatially Adaptive Instance Normalization
通过空间自适应实例归一化的神经姿势传递
903.NeuralScale - Efficient Scaling of Neurons for Resource-Constrained Deep Neural Networks
NeuralScale-资源受限的深度神经网络的神经元有效缩放
904.Neural Topological SLAM for Visual Navigation
用于视觉导航的神经拓扑SLAM
905.Neural Voxel Renderer - Learning an Accurate and Controllable Rendering Tool
神经体素渲染器-学习准确且可控的渲染工具
906.Neuromorphic Camera Guided High Dynamic Range Imaging
神经形态相机指导的高动态范围成像
907.NMS by Representative Region - Towards Crowded Pedestrian Detection by Proposal Pairing
NMS代表区域-通过提案配对实现行人拥挤检测
908.Noise-Aware Fully Webly Supervised Object Detection
感知噪声的完全网络监控对象检测
909.Noise Modeling, Synthesis and Classification for Generic Object Anti-Spoofing
通用对象反欺骗的噪声建模,合成和分类
910.Noise Robust Generative Adversarial Networks
噪声鲁棒的生成对抗网络
911.Noisier2Noise - Learning to Denoise From Unpaired Noisy Data
Noisier2Noise-学习从不成对的嘈杂数据中去噪
912.Non-Adversarial Video Synthesis With Learned Priors
具有学习先验的非专业视频合成
913.Non-Line-of-Sight Surface Reconstruction Using the Directional Light-Cone Transform
使用定向光锥变换的非视线表面重建
914.Non-Local Neural Networks With Grouped Bilinear Attentional Transforms
具有分组双线性注意变换的非局部神经网络
915.Nonparametric Object and Parts Modeling With Lie Group Dynamics
具有李群动力学的非参数对象和零件建模
916.Normal Assisted Stereo Depth Estimation
普通辅助立体声深度估计
917.Normalized and Geometry-Aware Self-Attention Network for Image Captioning
用于图像字幕的归一化和几何感知自注意网络
918.Normalizing Flows With Multi-Scale Autoregressive Priors
使用多尺度自回归先验标准化流
919.Norm-Aware Embedding for Efficient Person Search
规范感知嵌入,可进行有效的人员搜索
920.Novel Object Viewpoint Estimation Through Reconstruction Alignment
通过重构对齐的新型对象视点估计
921.Novel View Synthesis of Dynamic Scenes With Globally Coherent Depths From a Monocular Camera
单眼相机的具有全局相干深度的动态场景的新型视图合成
922.nuScenes - A Multimodal Dataset for Autonomous Driving
nuScenes-用于自动驾驶的多模式数据集
923.OASIS - A Large-Scale Dataset for Single Image 3D in the Wild
OASIS-野外单图像3D的大规模数据集
924.Object-Occluded Human Shape and Pose Estimation From a Single Color Image
单色图像中物体遮挡的人体形状和姿势估计
925.Object Relational Graph With Teacher-Recommended Learning for Video Captioning
具有教师推荐学习功能的对象关系图,用于视频字幕
926.OccuSeg - Occupancy-Aware 3D Instance Segmentation
OccuSeg-占用感知3D实例分割
927.OctSqueeze - Octree-Structured Entropy Model for LiDAR Compression
OctSqueeze-用于LiDAR压缩的八进制结构熵模型
928.Offset Bin Classification Network for Accurate Object Detection
偏移箱分类网络,用于精确的目标检测
929.Old Is Gold - Redefining the Adversarially Learned One-Class Classifier Training Paradigm
老是黄金-重新定义对抗性学习的一类分类器训练范式
930.One Man’s Trash Is Another Man’s Treasure - Resisting Adversarial Examples by Adversarial Examples
一个人的垃圾就是另一个人的宝藏-通过对抗示例抵抗对抗示例
931.One-Shot Adversarial Attacks on Visual Tracking With Dual Attention
双重关注的视觉跟踪一击式攻击
932.One-Shot Domain Adaptation for Face Generation
一键式域自适应以生成人脸
933.On Isometry Robustness of Deep 3D Point Cloud Models Under Adversarial Attacks
对抗攻击下深3D点云模型的等距稳健性
934.On Joint Estimation of Pose, Geometry and svBRDF From a Handheld Scanner
手持式扫描仪的姿势,几何形状和svBRDF联合估计
935.Online Deep Clustering for Unsupervised Representation Learning
在线深度聚类的无监督表示学习
936.Online Depth Learning Against Forgetting in Monocular Videos
在线深度学习防止单眼视频遗忘
937.Online Joint Multi-Metric Adaptation From Frequent Sharing-Subset Mining for Person Re-Identification
频繁共享子集挖掘的在线联合多指标适应,用于人员重新识别
938.Online Knowledge Distillation via Collaborative Learning
通过协作学习进行在线知识蒸馏
939.On Positive-Unlabeled Classification in GAN
关于GAN中的未标记分类
940.On the Acceleration of Deep Learning Model Parallelism With Staleness
用陈旧性促进深度学习模型并行化
941.On the Detection of Digital Face Manipulation
关于数字面部操纵的检测
942.On the Distribution of Minima in Intrinsic-Metric Rotation Averaging
关于本征度量旋转平均中的最小值分布
943.On the General Value of Evidence, and Bilingual Scene-Text Visual Question Answering
证据的一般价值与双语场景文本视觉问答
944.On the Regularization Properties of Structured Dropout
关于结构化辍学的正则化性质
945.On the Uncertainty of Self-Supervised Monocular Depth Estimation
自监督单眼深度估计的不确定性
946.On Translation Invariance in CNNs - Convolutional Layers Can Exploit Absolute Spatial Location
CNN中的翻译不变性-卷积层可以利用绝对空间位置
947.On Vocabulary Reliance in Scene Text Recognition
论场景文本识别中的词汇依赖
948.Oops! Predicting Unintentional Action in Video
糟糕!预测视频中的意外动作
949.Open Compound Domain Adaptation
开放复合域适应
950.Optical Flow in Dense Foggy Scenes Using Semi-Supervised Learning
使用半监督学习的浓雾场景中的光流
论文概要
951.Optical Flow in the Dark
黑暗中的光流
952.Optical Non-Line-of-Sight Physics-Based 3D Human Pose Estimation
基于光学非视线物理的3D人体姿势估计
953.Optimal least-squares solution to the hand-eye calibration problem
手眼校准问题的最佳最小二乘解
954.Optimizing Rank-Based Metrics With Blackbox Differentiation
使用黑盒区分法优化基于排名的指标
955.Orderless Recurrent Models for Multi-Label Classification
多标签分类的无序递归模型
956.Organ at Risk Segmentation for Head and Neck Cancer Using Stratified Learning and Neural Architecture Search
使用分层学习和神经体系结构搜索的头颈癌风险器官分割
957.OrigamiNet - Weakly-Supervised, Segmentation-Free, One-Step, Full Page Text Recognition by learning to unfold
OrigamiNet-通过学习展开来弱监督,无分段,一步,全页文本识别
958.Orthogonal Convolutional Neural Networks
正交卷积神经网络
959.Overcoming Classifier Imbalance for Long-Tail Object Detection With Balanced Group Softmax
通过平衡组Softmax克服分类器不平衡,用于长尾物体检测
960.Overcoming Multi-Model Forgetting in One-Shot NAS With Diversity Maximization
通过多样性最大化克服一发NAS中的多模型遗忘
961.P2B - Point-to-Box Network for 3D Object Tracking in Point Clouds
P2B-点对盒网络,用于点云中的3D对象跟踪
962.PADS - Policy-Adapted Sampling for Visual Similarity Learning
PADS-适用于视觉相似性学习的策略采样
963.Painting Many Pasts - Synthesizing Time Lapse Videos of Paintings
绘画许多过去-合成绘画的延时录像
964.PANDA - A Gigapixel-Level Human-Centric Video Dataset
PANDA-千兆像素级以人为中心的视频数据集
965.PandaNet - Anchor-Based Single-Shot Multi-Person 3D Pose Estimation
PandaNet-基于锚的单发多人3D姿势估计
966.Panoptic-Based Image Synthesis
基于全景的图像合成
967.Panoptic-DeepLab - A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation
Panoptic-DeepLab-用于自下而上的全景分割的简单,强大且快速的基准
968.Parsing-Based View-Aware Embedding Network for Vehicle Re-Identification
基于解析的视图识别嵌入网络,用于车辆重新识别
969.Part-Aware Context Network for Human Parsing
用于人解析的部分感知上下文网络
970.Partial Weight Adaptation for Robust DNN Inference
鲁棒DNN推理的局部权重自适应
971.PaStaNet - Toward Human Activity Knowledge Engine
PaStaNet-走向人类活动知识引擎
972.PatchVAE - Learning Local Latent Codes for Recognition
PatchVAE-学习本地潜在代码以进行识别
973.Pathological Retinal Region Segmentation From OCT Images Using Geometric Relation Based Augmentation
使用基于几何关系的增强从OCT图像进行病理性视网膜区域分割
974.Pattern-Structure Diffusion for Multi-Task Learning
用于多任务学习的模式-结构扩散
975.Peek-a-Boo - Occlusion Reasoning in Indoor Scenes With Plane Representations
捉迷藏-具有平面表示的室内场景中的遮挡推理
976.Perceptual Quality Assessment of Smartphone Photography
智能手机摄影的感知质量评估
977.Perspective Plane Program Induction From a Single Image
从单个图像透视平面程序归纳
978.PFCNN - Convolutional Neural Networks on 3D Surfaces Using Parallel Frames
PFCNN-使用平行框架的3D表面卷积神经网络
979.PF-Net - Point Fractal Network for 3D Point Cloud Completion
PF-Net-3D点云完成的点分形网络
980.PFRL - Pose-Free Reinforcement Learning for 6D Pose Estimation
PFRL-用于6D姿势估计的无姿势强化学习
981.Phase Consistent Ecological Domain Adaptation
相位一致的生态域适应
982.Photometric Stereo via Discrete Hypothesis-and-Test Search
通过离散假设和测试搜索进行光度学立体
983.PhraseCut - Language-Based Image Segmentation in the Wild
PhraseCut-野外基于语言的图像分割
984.PhysGAN - Generating Physical-World-Resilient Adversarial Examples for Autonomous Driving
PhysGAN-生成自动驾驶的物理世界弹性对抗示例
985.Physically Realizable Adversarial Examples for LiDAR Object Detection
用于LiDAR目标检测的可物理实现的对抗示例
986.PIFuHD - Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization
PIFuHD-用于高分辨率3D人类数字化的多层像素对齐隐式函数
987.Pixel Consensus Voting for Panoptic Segmentation
像素共识投票进行全景分割
988.Plug-and-Play Algorithms for Large-Scale Snapshot Compressive Imaging
大规模快照压缩成像的即插即用算法
989.P-nets - Deep Polynomial Neural Networks
P网-深度多项式神经网络
990.PnPNet - End-to-End Perception and Prediction With Tracking in the Loop
PnPNet-跟踪中的端到端感知和预测
991.PointASNL - Robust Point Clouds Processing Using Nonlocal Neural Networks With Adaptive Sampling
PointASNL-使用具有自适应采样的非局部神经网络处理鲁棒点云
992.PointAugment - An Auto-Augmentation Framework for Point Cloud Classification
PointAugment-点云分类的自动增强框架
993.Point Cloud Completion by Skip-Attention Network With Hierarchical Folding
具有分层折叠的跳过注意力网络的点云完成
994.PointGMM - A Neural GMM Network for Point Clouds
PointGMM-用于点云的神经GMM网络
995.Point-GNN - Graph Neural Network for 3D Object Detection in a Point Cloud
Point-GNN-点云中用于3D对象检测的图神经网络
996.PointGroup - Dual-Set Point Grouping for 3D Instance Segmentation
PointGroup-用于3D实例分割的双重设置点分组
997.PointPainting - Sequential Fusion for 3D Object Detection
点画-用于3D对象检测的顺序融合
998.PointRend - Image Segmentation As Rendering
PointRend-图像分割作为渲染
999.Polarized Non-Line-of-Sight Imaging
偏振非视线成像
1000.Polarized Reflection Removal With Perfect Alignment in the Wild
在野外完美对准后的偏振光去除
论文概要
1001.PolarMask - Single Shot Instance Segmentation With Polar Representation
PolarMask-具有Polar表示的单发实例分割
1002.PolarNet - An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentation
PolarNet-在线LiDAR点云语义分割的改进网格表示
1003.Polishing Decision-Based Adversarial Noise With a Customized Sampling
通过自定义采样抛光基于决策的对抗性噪声
1004.PolyTransform - Deep Polygon Transformer for Instance Segmentation
PolyTransform-用于实例分割的深多边形转换器
1005.Pose-Guided Visible Part Matching for Occluded Person ReID
闭塞者ReID的姿势指导可见部分匹配
1006.PPDM - Parallel Point Detection and Matching for Real-Time Human-Object Interaction Detection
PPDM-并行点检测和匹配,用于实时人-物体交互检测
1007.PQ-NET - A Generative Part Seq2Seq Network for 3D Shapes
PQ-NET-用于3D形状的通用零件Seq2Seq网络
1008.PREDICT & CLUSTER - Unsupervised Skeleton Based Action Recognition
预测和集群-基于无监督骨架的动作识别
1009.Predicting Cognitive Declines Using Longitudinally Enriched Representations for Imaging Biomarkers
使用纵向丰富的表示法成像生物标志物预测认知下降。
1010.Predicting Goal-Directed Human Attention Using Inverse Reinforcement Learning
使用逆向强化学习预测目标导向的人类注意力
1011.Predicting Lymph Node Metastasis Using Histopathological Images Based on Multiple Instance Learning With Deep Graph Convolution
基于深度图卷积的多实例学习的组织病理学图像预测淋巴结转移
1012.Predicting Semantic Map Representations From Images Using Pyramid Occupancy Networks
使用金字塔占用网络从图像预测语义地图表示
1013.Predicting Sharp and Accurate Occlusion Boundaries in Monocular Depth Estimation Using Displacement Fields
使用位移场预测单眼深度估计中的精确锐利遮挡边界
1014.Prime Sample Attention in Object Detection
目标检测中的主要样本注意
1015.Prior Guided GAN Based Semantic Inpainting
事先指导的基于GAN的语义修复
1016.Private-kNN - Practical Differential Privacy for Computer Vision
Private-kNN-计算机视觉的实用差异隐私
1017.ProAlignNet - Unsupervised Learning for Progressively Aligning Noisy Contours
ProAlignNet-用于逐步对齐嘈杂轮廓的无监督学习
1018.Probabilistic Pixel-Adaptive Refinement Networks
概率像素自适应细化网络
1019.Probabilistic Regression for Visual Tracking
视觉跟踪的概率回归
1020.Probabilistic Structural Latent Representation for Unsupervised Embedding
无监督嵌入的概率结构潜在表示
1021.Probabilistic Video Prediction From Noisy Data With a Posterior Confidence
具有后验置信度的噪声数据概率视频预测
1022.Probability Weighted Compact Feature for Domain Adaptive Retrieval
域自适应检索的概率加权紧凑特征
1023.Progressive Adversarial Networks for Fine-Grained Domain Adaptation
细粒度域自适应的渐进对抗网络
1024.Progressive Mirror Detection
渐进镜检测
1025.Progressive Relation Learning for Group Activity Recognition
团体关系识别的渐进式关系学习
1026.Projection & Probability-Driven Black-Box Attack
投影和概率驱动的黑匣子攻击
1027.PropagationNet - Propagate Points to Curve to Learn Structure Information
PropagationNet-传播点到曲线以学习结构信息
1028.Proxy Anchor Loss for Deep Metric Learning
深度度量学习的代理锚丢失
1029.PSGAN - Pose and Expression Robust Spatial-Aware GAN for Customizable Makeup Transfer
PSGAN-用于自定义化妆转移的姿势和表情稳健的空间感知GAN
1030.PULSE - Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models
PULSE-通过生成模型的潜在空间探索进行自我监督的照片上采样
1031.PuppeteerGAN - Arbitrary Portrait Animation With Semantic-Aware Appearance Transformation
PuppeteerGAN-具有语义感知外观转换的任意人像动画
1032.Putting Visual Object Recognition in Context
将视觉对象识别置于上下文中
1033.PVN3D - A Deep Point-Wise 3D Keypoints Voting Network for 6DoF Pose Estimation
PVN3D-用于6DoF姿势估计的深点明智3D关键点投票网络
1034.PV-RCNN - Point-Voxel Feature Set Abstraction for 3D Object Detection
PV-RCNN-用于3D对象检测的点体素特征集抽象
1035.QEBA - Query-Efficient Boundary-Based Blackbox Attack
QEBA-基于查询的基于边界的黑盒攻击
1036.Quasi-Newton Solver for Robust Non-Rigid Registration
拟牛顿求解器,用于鲁棒的非刚性配准
1037.Quaternion Product Units for Deep Learning on 3D Rotation Groups
在3D旋转组上进行深度学习的四元数乘积单元
1038.RandLA-Net - Efficient Semantic Segmentation of Large-Scale Point Clouds
RandLA-Net-大规模点云的有效语义分割
1039.RankMI - A Mutual Information Maximizing Ranking Loss
RankMI-最大化排名损失的相互信息
1040.RDCFace - Radial Distortion Correction for Face Recognition
RDCFace-径向失真校正的人脸识别
1041.Real-Time Panoptic Segmentation From Dense Detections
密集检测的实时全景分割
1042.Real-World Person Re-Identification via Degradation Invariance Learning
通过退化不变性学习对现实世界中的人进行重新识别
1043.Reciprocal Learning Networks for Human Trajectory Prediction
人体轨迹预测的对等学习网络
1044.Recognizing Objects From Any View With Object and Viewer-Centered Representations
使用对象和以查看者为中心的表示从任何视图中识别对象
1045.Reconstruct Locally, Localize Globally - A Model Free Method for Object Pose Estimation
本地重建,全局本地化-一种用于对象姿势估计的无模型方法
1046.Recurrent Feature Reasoning for Image Inpainting
图像修复的递归特征推理
1047.Recursive Least-Squares Estimator-Aided Online Learning for Visual Tracking
递归最小二乘估计器辅助的在线学习的视觉跟踪
1048.Recursive Social Behavior Graph for Trajectory Prediction
递归社会行为图用于轨迹预测
1049.ReDA - Reinforced Differentiable Attribute for 3D Face Reconstruction
ReDA-增强的3D人脸重建微分属性
1050.Reference-Based Sketch Image Colorization Using Augmented-Self Reference and Dense Semantic Correspondence
使用增强型自参考和密集语义对应的基于参考的草图图像着色
论文概要
1051.Referring Image Segmentation via Cross-Modal Progressive Comprehension
通过跨模态渐进理解引用图像分割
1052.Reflection Scene Separation From a Single Image
反射场景与单个图像的分离
1053.Regularization on Spatio-Temporally Smoothed Feature for Action Recognition
用于动作识别的时空平滑特征的正则化
1054.Regularizing Class-Wise Predictions via Self-Knowledge Distillation
通过自学知识蒸馏对明智的预测进行正则化
1055.Regularizing CNN Transfer Learning With Randomised Regression
使用随机回归对CNN转移学习进行正则化
1056.Regularizing Discriminative Capability of CGANs for Semi-Supervised Generative Learning
正则化CGAN的判别能力用于半监督式生成学习
1057.Regularizing Neural Networks via Minimizing Hyperspherical Energy
通过最小化超球形能量来规范神经网络
1058.Reinforced Feature Points - Optimizing Feature Detection and Description for a High-Level Task
增强的特征点-优化高级任务的特征检测和描述
1059.Relation-Aware Global Attention for Person Re-Identification
重新认识个人的重新认识关系
1060.Relative Interior Rule in Block-Coordinate Descent
块坐标下降中的相对内部规则
1061.Reliable Weighted Optimal Transport for Unsupervised Domain Adaptation
无监督域自适应的可靠加权最优传输
1062.Residual Feature Aggregation Network for Image Super-Resolution
用于图像超分辨率的残差特征聚合网络
1063.Resolution Adaptive Networks for Efficient Inference
分辨率自适应网络以进行有效推理
1064.ReSprop - Reuse Sparsified Backpropagation
ReSprop-重用稀疏反向传播
1065.Rethinking Class-Balanced Methods for Long-Tailed Visual Recognition From a Domain Adaptation Perspective
从域适应的角度重新思考长尾视觉识别的类平衡方法
1066.Rethinking Classification and Localization for Object Detection
重新考虑目标检测的分类和定位
1067.Rethinking Computer-Aided Tuberculosis Diagnosis
对计算机辅助结核诊断的反思
1068.Rethinking Data Augmentation for Image Super-resolution - A Comprehensive Analysis and a New Strategy
重新思考数据增强的图像超分辨率-综合分析和新策略
1069.Rethinking Depthwise Separable Convolutions - How Intra-Kernel Correlations Lead to Improved MobileNets
重新思考深度可分离卷积-内核内相关如何导致改进的MobileNet
1070.Rethinking Differentiable Search for Mixed-Precision Neural Networks
对混合精度神经网络的可微搜索的重新思考
1071.Rethinking Performance Estimation in Neural Architecture Search
对神经架构搜索中性能评估的反思
1072.Rethinking the Route Towards Weakly Supervised Object Localization
重新思考通往弱监督对象本地化的途径
1073.Rethinking Zero-Shot Video Classification - End-to-End Training for Realistic Applications
重新思考零摄视频分类-实际应用的端到端培训
1074.RetinaFace - Single-Shot Multi-Level Face Localisation in the Wild
RetinaFace-野外单发多级面部定位
1075.Retina-Like Visual Image Reconstruction via Spiking Neural Model
通过尖刺神经模型进行类似于视网膜的视觉图像重建
1076.RetinaTrack - Online Single Stage Joint Detection and Tracking
RetinaTrack-在线单级关节检测和跟踪
1077.Reusing Discriminators for Encoding - Towards Unsupervised Image-to-Image Translation
重用鉴别符进行编码-走向无监督的图像到图像翻译
1078.RevealNet - Seeing Behind Objects in RGB-D Scans
RevealNet-在RGB-D扫描中看到物体背后
1079.REVERIE - Remote Embodied Visual Referring Expression in Real Indoor Environments
REVERIE-真实室内环境中的远程体现视觉参照表达
1080.Reverse Perspective Network for Perspective-Aware Object Counting
反向透视网络用于透视感知对象计数
1081.Revisiting Knowledge Distillation via Label Smoothing Regularization
通过标签平滑正则化重新访问知识蒸馏
1082.Revisiting Pose-Normalization for Fine-Grained Few-Shot Recognition
再谈姿势归一化以细粒度的少量识别
1083.Revisiting Saliency Metrics - Farthest-Neighbor Area Under Curve
重访显着性指标-曲线下最远的邻居区域
1084.Revisiting the Sibling Head in Object Detector
再探对象检测器中的同级头
1085.RGBD-Dog - Predicting Canine Pose from RGBD Sensors
RGBD狗-从RGBD传感器预测犬的姿势
1086.RiFeGAN - Rich Feature Generation for Text-to-Image Synthesis From Prior Knowledge
RiFeGAN-从先验知识生成用于文本到图像合成的丰富功能
1087.RL-CycleGAN - Reinforcement Learning Aware Simulation-to-Real
RL-CycleGAN-增强学习感知模拟
1088.RMP-SNN - Residual Membrane Potential Neuron for Enabling Deeper High-Accuracy and Low-Latency Spiking Neural Network
RMP-SNN-残膜电位神经元,可实现更深的高精度和低延迟的尖峰神经网络
1089.ROAM - Recurrently Optimizing Tracking Model
ROAM-循环优化跟踪模型
1090.RoboTHOR - An Open Simulation-to-Real Embodied AI Platform
RoboTHOR-一个开放的模拟到真实的嵌入式AI平台
1091.Robust 3D Self-Portraits in Seconds
几秒钟内强大的3D自画像
1092.Robust Design of Deep Neural Networks Against Adversarial Attacks Based on Lyapunov Theory
基于李雅普诺夫理论的深度神经网络对抗攻击的鲁棒设计
1093.Robust Homography Estimation via Dual Principal Component Pursuit
通过双主成分追踪进行稳健的单应性估计
1094.Robust Learning Through Cross-Task Consistency
通过跨任务一致性进行稳定的学习
1095.Robustness Guarantees for Deep Neural Networks on Videos
视频上深度神经网络的鲁棒性保证
1096.Robust Object Detection Under Occlusion With Context-Aware CompositionalNets
上下文感知的CompositionalNets在遮挡下进行稳健的对象检测
1097.Robust Partial Matching for Person Search in the Wild
野外人物搜索的鲁棒部分匹配
1098.Robust Reference-Based Super-Resolution With Similarity-Aware Deformable Convolution
鲁棒的基于参考的超分辨率,具有可感知相似性的可变形卷积
1099.Robust Superpixel-Guided Attentional Adversarial Attack
强大的超像素引导注意力对抗攻击
1100.Rotate-and-Render - Unsupervised Photorealistic Face Rotation From Single-View Images
旋转和渲染-单视图图像的无监督真实感人脸旋转
论文概要
1101.Rotation Consistent Margin Loss for Efficient Low-Bit Face Recognition
旋转一致的余量损失,可实现高效的低位人脸识别
1102.Rotation Equivariant Graph Convolutional Network for Spherical Image Classification
旋转等变图卷积网络用于球面图像分类
1103.RoutedFusion - Learning Real-Time Depth Map Fusion
RoutedFusion-学习实时深度图融合
1104.RPM-Net - Robust Point Matching Using Learned Features
RPM-Net-使用学习的功能进行稳健的点匹配
1105.S3VAE - Self-Supervised Sequential VAE for Representation Disentanglement and Data Generation
S3VAE-用于表示解开和数据生成的自我监督顺序VAE
1106.SaccadeNet - A Fast and Accurate Object Detector
SaccadeNet-快速准确的物体检测器
1107.SAINT - Spatially Aware Interpolation NeTwork for Medical Slice Synthesis
SAINT-用于医学切片合成的空间感知插值网络
1108.Salience-Guided Cascaded Suppression Network for Person Re-Identification
显着指导的级联抑制网络用于人员重新识别
1109.SAL - Sign Agnostic Learning of Shapes From Raw Data
SAL-根据原始数据进行形状的符号不可知学习
1110.Same Features, Different Day - Weakly Supervised Feature Learning for Seasonal Invariance
相同的特征,不同的日子-季节性不变的弱监督特征学习
1111.SampleNet - Differentiable Point Cloud Sampling
SampleNet-可微分点云采样
1112.SAM - The Sensitivity of Attribution Methods to Hyperparameters
SAM-归因方法对超参数的敏感性
1113.SAPIEN - A SimulAted Part-Based Interactive ENvironment
SAPIEN-模拟的基于零件的交互式环境
1114.Satellite Image Time Series Classification With Pixel-Set Encoders and Temporal Self-Attention
像素集编码器和时间自关注的卫星图像时间序列分类
1115.Say As You Wish - Fine-Grained Control of Image Caption Generation With Abstract Scene Graphs
随心所欲-用抽象场景图对图像标题生成进行精细控制
1116.Scalability in Perception for Autonomous Driving - Waymo Open Dataset
自动驾驶感知的可伸缩性-Waymo开放数据集
1117.Scalable Uncertainty for Computer Vision With Functional Variational Inference
具有功能变分推理的计算机视觉可扩展不确定性
1118.Scale-Equalizing Pyramid Convolution for Object Detection
标度均衡金字塔卷积用于目标检测
1119.Scale-Space Flow for End-to-End Optimized Video Compression
端到端优化视频压缩的比例空间流
1120.SCATTER - Selective Context Attentional Scene Text Recognizer
SCATTER-选择性上下文注意场景文本识别器
1121.Scene-Adaptive Video Frame Interpolation via Meta-Learning
通过元学习进行场景自适应视频帧插值
1122.Scene Recomposition by Learning-Based ICP
通过基于学习的ICP进行场景重组
1123.ScopeFlow - Dynamic Scene Scoping for Optical Flow
ScopeFlow-用于光流的动​​态场景范围
1124.SCOUT - Self-Aware Discriminant Counterfactual Explanations
侦察员-自我识别的反事实解释
1125.ScrabbleGAN - Semi-Supervised Varying Length Handwritten Text Generation
ScrabbleGAN-半监督可变长度手写文本生成
1126.Screencast Tutorial Video Understanding
屏幕录像教程视频理解
1127.SCT - Set Constrained Temporal Transformer for Set Supervised Action Segmentation
SCT-用于集合监督动作分段的集合约束时间变压器
1128.SDC-Depth - Semantic Divide-and-Conquer Network for Monocular Depth Estimation
SDC-Depth-用于单眼深度估计的语义分而治之网络
1129.SDFDiff - Differentiable Rendering of Signed Distance Fields for 3D Shape Optimization
SDFDiff-用于3D形状优化的有符号距离场的微分渲染
1130.SEAN - Image Synthesis With Semantic Region-Adaptive Normalization
SEAN-具有语义区域自适应归一化的图像合成
1131.Searching Central Difference Convolutional Networks for Face Anti-Spoofing
搜索中央差分卷积网络以进行面部反欺骗
1132.Searching for Actions on the Hyperbole
搜索有关夸张的动作
1133.Search to Distill - Pearls Are Everywhere but Not the Eyes
搜寻蒸馏-珍珠无处不在,但眼睛不在
1134.SEED - Semantics Enhanced Encoder-Decoder Framework for Scene Text Recognition
SEED-用于场景文本识别的语义增强编解码器框架
1135.Seeing Around Street Corners - Non-Line-of-Sight Detection and Tracking In-the-Wild Using Doppler Radar
在街道拐角处看到-使用多普勒雷达进行的非视线检测和野外追踪
1136.Seeing the World in a Bag of Chips
一袋筹码看世界
1137.Seeing Through Fog Without Seeing Fog - Deep Multimodal Sensor Fusion in Unseen Adverse Weather
透过雾却看不到雾-在看不见的不利天气中进行深度多模态传感器融合
1138.Seeing without Looking - Contextual Rescoring of Object Detections for AP Maximization
视而不见-用于AP最大化的目标检测的上下文记录
1139.SegGCN - Efficient 3D Point Cloud Segmentation With Fuzzy Spherical Kernel
SegGCN-具有模糊球核的高效3D点云分割
1140.Selective Transfer With Reinforced Transfer Network for Partial Domain Adaptation
增强传输网络的选择性传输,用于部分域适配
1141.Select, Supplement and Focus for RGB-D Saliency Detection
选择,补充和聚焦以进行RGB-D显着性检测
1142.Select to Better Learn - Fast and Accurate Deep Learning Using Data Selection From Nonlinear Manifolds
选择更好地学习-使用来自非线性流形的数据选择进行快速而准确的深度学习
1143.Self2Self With Dropout - Learning Self-Supervised Denoising From Single Image
带有辍学功能的Self2Self-从单个图像中学习自我监督降噪
1144.Self-Learning Video Rain Streak Removal - When Cyclic Consistency Meets Temporal Correspondence
自学视频去除雨水条纹-循环一致性遇到时间对应时
1145.Self-Learning With Rectification Strategy for Human Parsing
带有纠正策略的自学习功能,用于人类解析
1146.Self-Robust 3D Point Recognition via Gather-Vector Guidance
通过聚集矢量制导的自鲁棒3D点识别
1147.Self-Supervised 3D Human Pose Estimation via Part Guided Novel Image Synthesis
通过部分引导的新型图像合成进行自我监督的3D人体姿势估计
1148.Self-Supervised Deep Visual Odometry With Online Adaptation
具有在线适应功能的自我监督式深度视觉测程
1149.Self-Supervised Domain-Aware Generative Network for Generalized Zero-Shot Learning
自我监督的领域感知生成网络,用于广义零射击学习
1150.Self-Supervised Equivariant Attention Mechanism for Weakly Supervised Semantic Segmentation
弱监督语义分割的自监督等变注意机制
论文概要
1151.Self-Supervised Human Depth Estimation From Monocular Videos
单眼视频的自我监督人类深度估计
1152.Self-Supervised Learning of Interpretable Keypoints From Unlabelled Videos
自我监督学习未标注视频中的关键点
1153.Self-Supervised Learning of Pretext-Invariant Representations
自主不变表示形式表示的学习
1154.Self-Supervised Learning of Video-Induced Visual Invariances
视频诱导的视觉不变性的自我监督学习
1155.Self-Supervised Monocular Scene Flow Estimation
自监督单眼场景流估计
1156.Self-Supervised Monocular Trained Depth Estimation Using Self-Attention and Discrete Disparity Volume
使用自我注意和离散视差量的自我监督单眼训练深度估计
1157.Self-Supervised Scene De-Occlusion
自我监督场景去遮挡
1158.Self-Supervised Viewpoint Learning From Image Collections
从图像集中进行自我监督的观点学习
1159.Self-Trained Deep Ordinal Regression for End-to-End Video Anomaly Detection
自训练式深序回归用于端到端视频异常检测
1160.Self-Training With Noisy Student Improves ImageNet Classification
带有噪音的学生进行自我训练可改善ImageNet分类
1161.Semantically Multi-Modal Image Synthesis
语义多模态图像合成
1162.Semantic Correspondence as an Optimal Transport Problem
语义对应作为最佳运输问题
1163.Semantic Drift Compensation for Class-Incremental Learning
课堂增量学习的语义漂移补偿
1164.Semantic Image Manipulation Using Scene Graphs
使用场景图的语义图像处理
1165.Semantic Pyramid for Image Generation
用于图像生成的语义金字塔
1166.Semantics-Guided Neural Networks for Efficient Skeleton-Based Human Action Recognition
语义指导的神经网络,用于基于骨骼的有效人类动作识别
1167.Semi-Supervised Learning for Few-Shot Image-to-Image Translation
半监督学习,少量图像到图像的翻译
1168.Semi-Supervised Semantic Image Segmentation With Self-Correcting Networks
具有自校正网络的半监督语义图像分割
1169.Semi-Supervised Semantic Segmentation With Cross-Consistency Training
具有交叉一致性训练的半监督语义分割
1170.Separating Particulate Matter From a Single Microscopic Image
从单个显微图像中分离出颗粒物
1171.Sequential 3D Human Pose and Shape Estimation From Point Clouds
点云的顺序3D人类姿势和形状估计
1172.Sequential Mastery of Multiple Visual Tasks - Networks Naturally Learn to Learn and Forget to Forget
顺序掌握多个视觉任务-网络自然学会了学习而忘记了
1173.Sequential Motif Profiles and Topological Plots for Offline Signature Verification
用于脱机签名验证的顺序主题配置文件和拓扑图
1174.SER-FIQ - Unsupervised Estimation of Face Image Quality Based on Stochastic Embedding Robustness
SER-FIQ-基于随机嵌入鲁棒性的人脸图像质量无监督估计
1175.SESS - Self-Ensembling Semi-Supervised 3D Object Detection
SESS-自组装半监督3D对象检测
1176.Set-Constrained Viterbi for Set-Supervised Action Segmentation
集约束维特比用于集监督动作细分
1177.Severity-Aware Semantic Segmentation With Reinforced Wasserstein Training
强化的Wasserstein训练可识别严重性的语义分割
1178.SGAS - Sequential Greedy Architecture Search
SGAS-顺序贪婪架构搜索
1179.SG-NN - Sparse Generative Neural Networks for Self-Supervised Scene Completion of RGB-D Scans
SG-NN-用于RGB-D扫描的自我监督场景完成的稀疏生成神经网络
1180.Shape correspondence using anisotropic Chebyshev spectral CNNs
使用各向异性切比雪夫光谱CNN的形状对应
1181.Shape Reconstruction by Learning Differentiable Surface Representations
通过学习微分的表面表示来重构形状
1182.SharinGAN - Combining Synthetic and Real Data for Unsupervised Geometry Estimation
SharinGAN-结合合成数据和实数据进行无监督的几何估计
1183.Shoestring - Graph-Based Semi-Supervised Classification With Severely Limited Labeled Data
Shoestring-具有严格受限标签数据的基于图的半监督分类
1184.Show, Edit and Tell - A Framework for Editing Image Captions
显示,编辑和讲述-编辑图像标题的框架
1185.SiamCAR - Siamese Fully Convolutional Classification and Regression for Visual Tracking
SiamCAR-用于视觉跟踪的暹罗完全卷积分类和回归
1186.Siamese Box Adaptive Network for Visual Tracking
用于视觉跟踪的连体盒自适应网络
1187.Siam R-CNN - Visual Tracking by Re-Detection
Siam R-CNN-通过重新检测进行视觉跟踪
1188.Sideways - Depth-Parallel Training of Video Models
横向-视频模型的深度并行训练
1189.Sign Language Transformers - Joint End-to-End Sign Language Recognition and Translation
手语变形金刚-端到端联合手语识别和翻译
1190.Single-Image HDR Reconstruction by Learning to Reverse the Camera Pipeline
通过学习反向摄像头管道来重建单图像HDR
1191.Single Image Optical Flow Estimation With an Event Camera
事件摄像机的单图像光流估计
1192.Single Image Reflection Removal Through Cascaded Refinement
通过级联细化去除单个图像反射
1193.Single Image Reflection Removal With Physically-Based Training Images
基于物理训练图像的单图像反射去除
1194.Single-Shot Monocular RGB-D Imaging Using Uneven Double Refraction
使用不均匀双折射的单镜头单眼RGB-D成像
1195.Single-Side Domain Generalization for Face Anti-Spoofing
人脸反欺骗的单面域一般化
1196.Single-Stage 6D Object Pose Estimation
单阶段6D对象姿势估计
1197.Single-Stage Semantic Segmentation From Image Labels
图像标签的单阶段语义分割
1198.Single-Step Adversarial Training With Dropout Scheduling
具有辍学计划的单步对抗训练
1199.Single-View View Synthesis With Multiplane Images
具有多平面图像的单视图合成
1200.Skeleton-Based Action Recognition With Shift Graph Convolutional Network
移位图卷积网络的基于骨架的动作识别
论文概要
1201.Sketch-BERT - Learning Sketch Bidirectional Encoder Representation From Transformers by Self-Supervised Learning of Sketch Gestalt
Sketch-BERT-通过草图格式塔的自学学习,从变压器学习草图双向编码器表示
1202.Sketchformer - Transformer-Based Representation for Sketched Structure
Sketchformer-草绘结构的基于变压器的表示形式
1203.Sketch Less for More - On-the-Fly Fine-Grained Sketch-Based Image Retrieval
少画草图,多画草图-实时细粒度基于草图的图像检索
1204.SketchyCOCO - Image Generation From Freehand Scene Sketches
SketchyCOCO-从徒手绘制的场景草图生成图像
1205.SLV - Spatial Likelihood Voting for Weakly Supervised Object Detection
SLV-用于弱监督对象检测的空间可能性投票
1206.SmallBigNet - Integrating Core and Contextual Views for Video Classification
SmallBigNet-集成核心视图和上下文视图进行视频分类
1207.Smoothing Adversarial Domain Attack and P-Memory Reconsolidation for Cross-Domain Person Re-Identification
平滑对抗域攻击和P记忆整合,以实现跨域人员重新识别
1208.Smooth Shells - Multi-Scale Shape Registration With Functional Maps
平滑壳-使用功能图进行多尺度形状配准
1209.Social-STGCNN - A Social Spatio-Temporal Graph Convolutional Neural Network for Human Trajectory Prediction
Social-STGCNN-用于人类轨迹预测的社会时空图卷积神经网络
1210.Softmax Splatting for Video Frame Interpolation
用于视频帧插值的Softmax Splatting
1211.Solving Jigsaw Puzzles With Eroded Boundaries
解决具有侵蚀边界的拼图游戏
1212.Solving Mixed-Modal Jigsaw Puzzle for Fine-Grained Sketch-Based Image Retrieval
解决混合模态拼图以细粒度基于草图的图像检索
1213.Something-Else - Compositional Action Recognition With Spatial-Temporal Interaction Networks
时空交互网络的事物组合动作识别
1214.SOS - Selective Objective Switch for Rapid Immunofluorescence Whole Slide Image Classification
SOS-用于快速免疫荧光全玻片图像分类的选择性物镜开关
1215.Space-Time-Aware Multi-Resolution Video Enhancement
时空感知多分辨率视频增强
1216.SPARE3D - A Dataset for SPAtial REasoning on Three-View Line Drawings
SPARE3D-在三视图线图上进行空间推理的数据集
1217.Sparse Layered Graphs for Multi-Object Segmentation
用于多对象分割的稀疏分层图
1218.Spatially Attentive Output Layer for Image Classification
用于图像分类的空间关注输出层
1219.Spatially-Attentive Patch-Hierarchical Network for Adaptive Motion Deblurring
自适应运动去模糊的空间关注面-递阶网络
1220.Spatial Pyramid Based Graph Reasoning for Semantic Segmentation
基于空间金字塔的语义分割图推理
1221.Spatial-Temporal Graph Convolutional Network for Video-Based Person Re-Identification
基于时空图卷积网络的基于视频的人员重新识别
1222.Spatiotemporal Fusion in 3D CNNs - A Probabilistic View
3D CNN中的时空融合-概率视图
1223.Spatio-Temporal Graph for Video Captioning With Knowledge Distillation
具有知识提取功能的视频字幕时空图
1224.Speech2Action - Cross-Modal Supervision for Action Recognition
Speech2Action-动作识别的跨模式监督
1225.SpeedNet - Learning the Speediness in Videos
SpeedNet-学习视频的快速性
1226.Spherical Space Domain Adaptation With Robust Pseudo-Label Loss
具有鲁棒伪标签损失的球形空间域自适应
1227.SpineNet - Learning Scale-Permuted Backbone for Recognition and Localization
SpineNet-用于识别和本地化的学习规模排列骨干
1228.SP-NAS - Serial-to-Parallel Backbone Search for Object Detection
SP-NAS-串行到并行主干搜索以进行对象检测
1229.SpSequenceNet - Semantic Segmentation Network on 4D Point Clouds
SpSequenceNet-4D点云上的语义分割网络
1230.SQE - a Self Quality Evaluation Metric for Parameters Optimization in Multi-Object Tracking
SQE-用于多目标跟踪的参数优化的一种自我质量评估指标
1231.Squeeze-and-Attention Networks for Semantic Segmentation
挤压和注意网络的语义分割
1232.SQuINTing at VQA Models - Introspecting VQA Models With Sub-Questions
在VQA模型上进行SQuINTing-通过子问题自省VQA模型
1233.SSRNet - Scalable 3D Surface Reconstruction Network
SSRNet-可扩展的3D表面重建网络
1234.StarGAN v2 - Diverse Image Synthesis for Multiple Domains
StarGAN v2-多个域的多样化图像合成
1235.State-Aware Tracker for Real-Time Video Object Segmentation
用于实时视频对象分割的状态感知跟踪器
1236.State-Relabeling Adversarial Active Learning
状态重新标记对抗主动学习
1237.STAViS - Spatio-Temporal AudioVisual Saliency Network
STAViS-时空视听显着网络
1238.Steering Self-Supervised Feature Learning Beyond Local Pixel Statistics
指导超越局部像素统计的自我监督特征学习
1239.STEFANN - Scene Text Editor Using Font Adaptive Neural Network
STEFANN-使用字体自适应神经网络的场景文本编辑器
1240.StegaStamp - Invisible Hyperlinks in Physical Photographs
StegaStamp-物理照片中的隐形超链接
1241.StereoGAN - Bridging Synthetic-to-Real Domain Gap by Joint Optimization of Domain Translation and Stereo Matching
StereoGAN-通过领域翻译和立体声匹配的联合优化,在合成领域与真实领域之间建立桥梁
1242.Stereoscopic Flash and No-Flash Photography for Shape and Albedo Recovery
立体闪光和无闪光摄影,可恢复形状和反照率
1243.STINet - Spatio-Temporal-Interactive Network for Pedestrian Detection and Trajectory Prediction
STINet-行人检测和轨迹预测的时空互动网络
1244.Stochastic Classifiers for Unsupervised Domain Adaptation
用于无监督域自适应的随机分类器
1245.Stochastic Sparse Subspace Clustering
随机稀疏子空间聚类
1246.Straight to the Point - Fast-Forwarding Videos via Reinforcement Learning Using Textual Data
直截了当-通过使用文本数据的强化学习来快速转发视频
1247.Strip Pooling - Rethinking Spatial Pooling for Scene Parsing
带状池-重新考虑空间池以进行场景解析
1248.StructEdit - Learning Structural Shape Variations
StructEdit-学习结构形状变化
1249.Structure Aware Single-Stage 3D Object Detection From Point Cloud
从点云进行结构感知的单阶段3D对象检测
1250.Structure Boundary Preserving Segmentation for Medical Image With Ambiguous Boundary
具有模糊边界的医学图像的结构边界保留分割
论文概要
1251.Structured Compression by Weight Encryption for Unstructured Pruning and Quantization
通过权重加密进行结构化压缩以进行非结构化修剪和量化
1252.Structured Multi-Hashing for Model Compression
用于模型压缩的结构化多哈希
1253.Structure-Guided Ranking Loss for Single Image Depth Prediction
基于结构的单图像深度预测排名损失
1254.Structure Preserving Generative Cross-Domain Learning
保留结构的生成跨域学习
1255.Structure-Preserving Super Resolution With Gradient Guidance
梯度引导的保结构超分辨率
1256.Style Normalization and Restitution for Generalizable Person Re-Identification
样式归一化和可归纳人员重新识别的归还
1257.StyleRig - Rigging StyleGAN for 3D Control Over Portrait Images
StyleRig-用于对肖像图像进行3D控制的StyleGAN索具
1258.Stylization-Based Architecture for Fast Deep Exemplar Colorization
基于样式化的体系结构,可实现快速的深样本着色
1259.Sub-Frame Appearance and 6D Pose Estimation of Fast Moving Objects
快速移动物体的子帧外观和6D姿态估计
1260.Super-BPD - Super Boundary-to-Pixel Direction for Fast Image Segmentation
Super-BPD-超级边界到像素方向,用于快速图像分割
1261.SuperGlue - Learning Feature Matching With Graph Neural Networks
SuperGlue-学习特征与图神经网络的匹配
1262.Superpixel Segmentation With Fully Convolutional Networks
完全卷积网络的超像素分割
1263.Supervised Raw Video Denoising With a Benchmark Dataset on Dynamic Scenes
在动态场景上使用基准数据集对原始视频进行去噪
1264.Suppressing Uncertainties for Large-Scale Facial Expression Recognition
抑制大规模面部表情识别的不确定性
1265.SurfelGAN - Synthesizing Realistic Sensor Data for Autonomous Driving
SurfelGAN-合成现实的传感器数据以进行自动驾驶
1266.SwapText - Image Based Texts Transfer in Scenes
SwapText-场景中基于图像的文本传输
1267.Symmetry and Group in Attribute-Object Compositions
属性对象组合中的对称性和组
1268.Syn2Real Transfer Learning for Image Deraining Using Gaussian Processes
Syn2Real转移学习,使用高斯过程进行图像去水化
1269.Synchronizing Probability Measures on Rotations via Optimal Transport
通过最优传输的旋转同步概率测度
1270.SynSin - End-to-End View Synthesis From a Single Image
SynSin-从单个图像进行端到端视图合成
1271.Syntax-Aware Action Targeting for Video Captioning
视频字幕的语法感知动作目标
1272.Synthetic Learning - Learn From Distributed Asynchronized Discriminator GAN Without Sharing Medical Image Data
综合学习-从分布式异步鉴别器GAN中学习而无需共享医学图像数据
1273.TailorNet - Predicting Clothing in 3D as a Function of Human Pose, Shape and Garment Style
TailorNet-根据人体姿势,形状和服装样式预测3D服装
1274.Taking a Deeper Look at Co-Salient Object Detection
深入了解共凸目标检测
1275.Tangent Images for Mitigating Spherical Distortion
减轻球面失真的正切图像
1276.Task Agnostic Robust Learning on Corrupt Outputs by Correlation-Guided Mixture Density Networks
相关指导的混合密度网络对腐败产出的任务不可知鲁棒学习
1277.TA-Student VQA - Multi-Agents Training by Self-Questioning
TA-学生VQA-通过自我提问进行多代理商培训
1278.TBT - Targeted Neural Network Attack With Bit Trojan
TBT-使用Bit Trojan的定向神经网络攻击
1279.TCTS - A Task-Consistent Two-Stage Framework for Person Search
TCTS-用于人员搜索的任务一致的两阶段框架
1280.TDAN - Temporally-Deformable Alignment Network for Video Super-Resolution
TDAN-用于视频超分辨率的临时变形对准网络
1281.TEA - Temporal Excitation and Aggregation for Action Recognition
TEA-时间激励和动作识别集合
1282.Telling Left From Right - Learning Spatial Correspondence of Sight and Sound
从右说左-学习视觉和声音的空间对应。
1283.Temporal-Context Enhanced Detection of Heavily Occluded Pedestrians
时空上下文增强的对重度行人的检测
1284.Temporally Distributed Networks for Fast Video Semantic Segmentation
临时分布式网络,用于快速视频语义分割
1285.Temporal Pyramid Network for Action Recognition
时间金字塔网络的行动识别
1286.TESA - Tensor Element Self-Attention via Matricization
TESA-通过矩阵进行张量元素自我关注
1287.TetraTSDF - 3D Human Reconstruction From a Single Image With a Tetrahedral Outer Shell
TetraTSDF-具有四面体外壳的单个图像的3D人体重建
1288.Texture and Shape Biased Two-Stream Networks for Clothing Classification and Attribute Recognition
纹理和形状有偏的两流网络用于服装分类和属性识别
1289.TextureFusion - High-Quality Texture Acquisition for Real-Time RGB-D Scanning
TextureFusion-实时RGB-D扫描的高质量纹理采集
1290.The Devil Is in the Details - Delving Into Unbiased Data Processing for Human Pose Estimation
细节决定成败-探究用于人体姿势估计的无偏数据处理
1291.The Edge of Depth - Explicit Constraints Between Segmentation and Depth
深度的边缘-分割和深度之间的显式约束
1292.The GAN That Warped - Semantic Attribute Editing With Unpaired Data
变形的GAN-使用不成对的数据进行语义属性编辑
1293.The Garden of Forking Paths - Towards Multi-Future Trajectory Prediction
分叉路径的花园-走向多轨迹预测
1294.The Knowledge Within - Methods for Data-Free Model Compression
内部知识-无数据模型压缩的方法
1295.There and Back Again - Revisiting Backpropagation Saliency Methods
那里又回来-重新研究反向传播显着性方法
1296.The Secret Revealer - Generative Model-Inversion Attacks Against Deep Neural Networks
揭秘者-针对深层神经网络的生成模型反转攻击
1297.Three-Dimensional Reconstruction of Human Interactions
人际互动的三维重构
1298.Through Fog High-Resolution Imaging Using Millimeter Wave Radar
毫米波雷达对雾进行高分辨率成像
1299.Through the Looking Glass - Neural 3D Reconstruction of Transparent Shapes
通过窥镜-透明形状的神经3D重建
1300.Time Flies - Animating a Still Image With Time-Lapse Video As Reference
时光飞逝-以延时视频为参考对静态图像进行动画处理
论文概要
1301.TITAN - Future Forecast Using Action Priors
TITAN-使用行动先验的未来预测
1302.TomoFluid - Reconstructing Dynamic Fluid From Sparse View Videos
TomoFluid-从稀疏视图重建动态流体
1303.Total3DUnderstanding - Joint Layout, Object Pose and Mesh Reconstruction for Indoor Scenes From a Single Image
Total3DUnderstanding-从单个图像对室内场景进行联合布局,对象姿势和网格重建
1304.Total Deep Variation for Linear Inverse Problems
线性反问题的总深变化
1305.Toward a Universal Model for Shape From Texture
从纹理走向通用模型
1306.Towards Accurate Scene Text Recognition With Semantic Reasoning Networks
利用语义推理网络实现准确的场景文本识别
1307.Towards Achieving Adversarial Robustness by Enforcing Feature Consistency Across Bit Planes
通过在位平面上增强特征一致性来实现对抗鲁棒性
1308.Towards Backward-Compatible Representation Learning
向后兼容的表示学习
1309.Towards Better Generalization - Joint Depth-Pose Learning Without PoseNet
迈向更好的通用化-不使用PoseNet进行深度联合学习
1310.Towards Causal VQA - Revealing and Reducing Spurious Correlations by Invariant and Covariant Semantic Editing
走向因果VQA-通过不变和协变语义编辑来显示和减少虚假相关
1311.Towards Discriminability and Diversity - Batch Nuclear-Norm Maximization Under Label Insufficient Situations
迈向可分辨性和多样性-标签不足情况下的批核范数最大化
1312.Towards Efficient Model Compression via Learned Global Ranking
通过学习的全球排名来实现有效的模型压缩
1313.Towards Fairness in Visual Recognition - Effective Strategies for Bias Mitigation
迈向视觉识别的公平-缓解偏见的有效策略
1314.Towards Global Explanations of Convolutional Neural Networks With Concept Attribution
具有概念归因的卷积神经网络的全局解释
1315.Towards High-Fidelity 3D Face Reconstruction From In-the-Wild Images Using Graph Convolutional Networks
使用图卷积网络从野外图像实现高保真3D人脸重建
1316.Towards Inheritable Models for Open-Set Domain Adaptation
面向开放式域自适应的可继承模型
1317.Towards Large Yet Imperceptible Adversarial Image Perturbations With Perceptual Color Distance
朝着具有感知色差的大而不可察觉的对抗图像扰动
1318.Towards Learning a Generic Agent for Vision-and-Language Navigation via Pre-Training
通过预训练学习视觉和语言导航的通用代理
1319.Towards Learning Structure via Consensus for Face Segmentation and Parsing
通过人脸分割和解析达成共识的学习结构
1320.Towards Photo-Realistic Virtual Try-On by Adaptively Generating-Preserving Image Content
通过自适应生成保留图像内容实现逼真的虚拟试戴
1321.Towards Robust Image Classification Using Sequential Attention Models
使用顺序注意模型实现稳健的图像分类
1322.Towards Transferable Targeted Attack
迈向可转移的目标攻击
1323.Towards Unified INT8 Training for Convolutional Neural Network
迈向卷积神经网络统一INT8培训
1324.Towards Universal Representation Learning for Deep Face Recognition
面向深层识别的通用表示学习
1325.Towards Unsupervised Learning of Generative Models for 3D Controllable Image Synthesis
面向3D可控图像合成生成模型的无监督学习
1326.Towards Verifying Robustness of Neural Networks Against A Family of Semantic Perturbations
朝着验证神经网络对语义扰动族的鲁棒性迈进
1327.Towards Visually Explaining Variational Autoencoders
朝着视觉上解释可变自动编码器的方向
1328.TPNet - Trajectory Proposal Network for Motion Prediction
TPNet-用于运动预测的弹道建议网
1329.Tracking by Instance Detection - A Meta-Learning Approach
通过实例检测进行跟踪-元学习方法
1330.Training a Steerable CNN for Guidewire Detection
训练可转向的CNN以进行导丝检测
1331.Train in Germany, Test in the USA - Making 3D Object Detectors Generalize
在德国训练,在美国进行测试-使3D对象检测器通用
1332.Training Noise-Robust Deep Neural Networks via Meta-Learning
通过元学习训练噪声鲁棒的深度神经网络
1333.Training Quantized Neural Networks With a Full-Precision Auxiliary Module
使用高精度辅助模块训练量化神经网络
1334.Transferable, Controllable, and Inconspicuous Adversarial Attacks on Person Re-identification With Deep Mis-Ranking
具有严重错误排列的人员重新识别的可传递,可控制和不起眼的对抗攻击
1335.Transfer Learning From Synthetic to Real-Noise Denoising With Adaptive Instance Normalization
通过自适应实例归一化将学习从合成降噪转换为实噪声
1336.Transferring and Regularizing Prediction for Semantic Segmentation
语义分割的传输和正则化预测
1337.Transferring Cross-Domain Knowledge for Video Sign Language Recognition
传输跨域知识以进行视频手语识别
1338.Transferring Dense Pose to Proximal Animal Classes
将密集姿势转移到近端动物类别
1339.Transform and Tell - Entity-Aware News Image Captioning
转换并讲述-实体感知新闻图片字幕
1340.Transformation GAN for Unsupervised Image Synthesis and Representation Learning
用于无监督图像合成和表示学习的Transformation GAN
1341.TransMatch - A Transfer-Learning Scheme for Semi-Supervised Few-Shot Learning
TransMatch-半监督少量学习的转学计划
1342.TransMoMo - Invariance-Driven Unsupervised Video Motion Retargeting
TransMoMo-不变性驱动的无监督视频运动重定向
1343.TRPLP - Trifocal Relative Pose From Lines at Points
TRPLP-点处线的三焦点相对姿势
1344.TubeTK - Adopting Tubes to Track Multi-Object in a One-Step Training Model
TubeTK-在一步式训练模型中采用试管跟踪多目标
1345.Two Causal Principles for Improving Visual Dialog
改善视觉对话的两个因果原理
1346.Two-Shot Spatially-Varying BRDF and Shape Estimation
两点空间变化的BRDF和形状估计
1347.Two-Stage Peer-Regularized Feature Recombination for Arbitrary Image Style Transfer
两阶段对等正则化特征重组,用于任意图像样式转换
1350.UC-Net - Uncertainty Inspired RGB-D Saliency Detection via Conditional Variational Autoencoders
UC-Net-通过条件变分自动编码器进行不确定性启发的RGB-D显着性检测
论文概要
1351.UCTGAN - Diverse Image Inpainting Based on Unsupervised Cross-Space Translation
UCTGAN-基于无监督跨空间转换的多样化图像修复
1352.UNAS - Differentiable Architecture Search Meets Reinforcement Learning
UNAS-差异化架构搜索遇到强化学习
1353.Unbiased Scene Graph Generation From Biased Training
偏向训练的无偏场景图生成
1354.Uncertainty-Aware CNNs for Depth Completion - Uncertainty from Beginning to End
不确定性的CNN深度补全-从始至终的不确定性
1355.Uncertainty-Aware Mesh Decoder for High Fidelity 3D Face Reconstruction
具有不确定性的网格解码器,可实现高保真3D人脸重建
1356.Uncertainty-Aware Score Distribution Learning for Action Quality Assessment
不确定性分数分布学习,用于行动质量评估
1357.Uncertainty Based Camera Model Selection
基于不确定性的相机模型选择
1358.Understanding Adversarial Examples From the Mutual Influence of Images and Perturbations
从图像和摄动的相互影响中了解对抗性例子
1359.Understanding Human Hands in Contact at Internet Scale
了解互联网规模的人际交往
1360.Understanding Road Layout From Videos as a Whole
从整个视频了解道路布局
1361.Unified Dynamic Convolutional Network for Super-Resolution With Variational Degradations
变分退化的超高分辨率统一动态卷积网络
1362.Unifying Training and Inference for Panoptic Segmentation
全景分割的统一训练和推理
1363.Uninformed Students - Student-Teacher Anomaly Detection With Discriminative Latent Embeddings
不知情的学生-具有判别性潜在嵌入的学生-老师异常检测
1364.UniPose - Unified Human Pose Estimation in Single Images and Videos
UniPose-单个图像和视频中的统一人体姿势估计
1365.Unity Style Transfer for Person Re-Identification
统一样式转移以重新识别人
1366.Universal Litmus Patterns - Revealing Backdoor Attacks in CNNs
通用石蕊模式-揭示CNN中的后门攻击
1367.Universal Physical Camouflage Attacks on Object Detectors
物体探测器的通用物理伪装攻击
1368.Universal Source-Free Domain Adaptation
通用无源域名自适应
1369.Universal Weighting Metric Learning for Cross-Modal Matching
跨模态匹配的通用加权度量学习
1370.Unpaired Image Super-Resolution Using Pseudo-Supervision
使用伪监督的未配对图像超分辨率
1371.Unpaired Portrait Drawing Generation via Asymmetric Cycle Mapping
通过非对称循环映射生成未配对的肖像画
1372.UnrealText - Synthesizing Realistic Scene Text Images From the Unreal World
UnrealText-合成来自虚幻世界的真实场景文本图像
1373.Unsupervised Adaptation Learning for Hyperspectral Imagery Super-Resolution
高光谱影像超分辨率的无监督自适应学习
1374.Unsupervised Deep Shape Descriptor With Point Distribution Learning
具有点分布学习的无监督深度形状描述符
1375.Unsupervised Domain Adaptation via Structurally Regularized Deep Clustering
通过结构化正则化深度聚类的无监督域自适应
1376.Unsupervised Domain Adaptation With Hierarchical Gradient Synchronization
具有分级梯度同步的无监督域自适应
1377.Unsupervised Instance Segmentation in Microscopy Images via Panoptic Domain Adaptation and Task Re-Weighting
通过全景域自适应和任务重新加权在显微镜图像中进行无监督实例分割
1378.Unsupervised Intra-Domain Adaptation for Semantic Segmentation Through Self-Supervision
通过自我监督的语义监督的无监督域内自适应
1379.Unsupervised Learning for Intrinsic Image Decomposition From a Single Image
从单个图像进行固有图像分解的无监督学习
1380.Unsupervised Learning From Video With Deep Neural Embeddings
从具有深层神经嵌入的视频中进行无监督学习
1381.Unsupervised Learning of Intrinsic Structural Representation Points
内在结构表示点的无监督学习
1382.Unsupervised Learning of Probably Symmetric Deformable 3D Objects From Images in the Wild
从野外图像中可能对称对称可变形3D对象的无监督学习
1383.Unsupervised Magnification of Posture Deviations Across Subjects
跨主体的姿势偏差的无监督放大
1384.Unsupervised Model Personalization While Preserving Privacy and Scalability - An Open Problem
在保留隐私和可伸缩性的同时,实现无监督模型个性化-一个未解决的问题
1385.Unsupervised Multi-Modal Image Registration via Geometry Preserving Image-to-Image Translation
通过几何保留图像到图像转换的无监督多模态图像配准
1386.Unsupervised Person Re-Identification via Multi-Label Classification
通过多标签分类对无人监督的人员进行重新识别
1387.Unsupervised Person Re-Identification via Softened Similarity Learning
通过软化相似学习进行无人监督的重新识别
1388.Unsupervised Reinforcement Learning of Transferable Meta-Skills for Embodied Navigation
用于实现导航的可转移元技能的无监督强化学习
1389.Unsupervised Representation Learning for Gaze Estimation
无监督表示学习的注视估计
1390.Upgrading Optical Flow to 3D Scene Flow Through Optical Expansion
通过光扩展将光流升级为3D场景流
1391.Use the Force, Luke! Learning to Predict Physical Forces by Simulating Effects
用力吧,卢克!学习通过模拟效果预测身体力量
1392.Variational Context-Deformable ConvNets for Indoor Scene Parsing
用于室内场景解析的变体上下文可变形卷积网络
1393.Variational-EM-Based Deep Learning for Noise-Blind Image Deblurring
基于变分EM的深度学习用于降噪图像去模糊
1394.Varicolored Image De-Hazing
杂色图像去雾
1395.Vec2Face - Unveil Human Faces From Their Blackbox Features in Face Recognition
Vec2Face-从人脸识别的黑盒功能中揭露人脸
1396.VecRoad - Point-Based Iterative Graph Exploration for Road Graphs Extraction
VecRoad-基于点的迭代图探索,用于道路图提取
1397.VectorNet - Encoding HD Maps and Agent Dynamics From Vectorized Representation
VectorNet-通过矢量化表示对高清地图和代理动态进行编码
1398.ViBE - Dressing for Diverse Body Shapes
ViBE-多种体形的敷料
1399.VIBE - Video Inference for Human Body Pose and Shape Estimation
VIBE-人体姿势和形状估计的视频推断
1400.Video Instance Segmentation Tracking With a Modified VAE Architecture
修改后的VAE架构的视频实例细分跟踪
论文概要
1401.Video Modeling With Correlation Networks
相关网络的视频建模
1402.Video Object Grounding Using Semantic Roles in Language Description
在语言描述中使用语义角色的视频对象接地
1403.Video Panoptic Segmentation
视频全景分割
1404.Video Playback Rate Perception for Self-Supervised Spatio-Temporal Representation Learning
自我监督的时空表示学习的视频播放率感知
1405.Video Super-Resolution With Temporal Group Attention
时域关注的视频超分辨率
1406.Video to Events - Recycling Video Datasets for Event Cameras
视频到事件-回收事件摄像机的视频数据集
1407.ViewAL - Active Learning With Viewpoint Entropy for Semantic Segmentation
ViewAL-带有观点熵的主动学习,用于语义分割
1408.View-GCN - View-Based Graph Convolutional Network for 3D Shape Analysis
View-GCN-用于3D形状分析的基于视图的图卷积网络
1409.Violin - A Large-Scale Dataset for Video-and-Language Inference
小提琴-用于视频和语言推理的大规模数据集
1410.Vision-Dialog Navigation by Exploring Cross-Modal Memory
探索跨模态记忆的视觉对话导航
1411.Vision-Language Navigation With Self-Supervised Auxiliary Reasoning Tasks
具有自我监督辅助推理任务的视觉语言导航
1412.Visual Chirality
视觉手性
1413.Visual Commonsense R-CNN
视觉常识R-CNN
1414.Visual Grounding in Video for Unsupervised Word Translation
视频中的可视化基础,可进行无监督的单词翻译
1415.Visually Imbalanced Stereo Matching
视觉失衡的立体声匹配
1416.Visual Reaction - Learning to Play Catch With Your Drone
视觉反应-学习与无人机比赛
1417.Visual-Semantic Matching by Exploring High-Order Attention and Distraction
通过探索高阶注意力和注意力来进行视觉语义匹配
1418.Visual-Textual Capsule Routing for Text-Based Video Segmentation
基于文本的视频分割的视觉-文本胶囊路由
1419.VOLDOR - Visual Odometry From Log-Logistic Dense Optical Flow Residuals
VOLDOR-对数逻辑密集光流残差的视觉里程表
1420.VPLNet - Deep Single View Normal Estimation With Vanishing Points and Lines
VPLNet-具有消失点和线的深单视图法线估计
1421.VQA With No Questions-Answers Training
毫无疑问的VQA-答案培训
1422.VSGNet - Spatial Attention Network for Detecting Human Object Interactions Using Graph Convolutions
VSGNet-使用图卷积检测人与物体相互作用的空间注意网络
1423.Warping Residual Based Image Stitching for Large Parallax
基于残差翘曲的大视差图像拼接
1424.Warp to the Future - Joint Forecasting of Features and Feature Motion
面向未来-特征和特征运动的联合预测
1425.Watch Your Up-Convolution - CNN Based Generative Deep Neural Networks Are Failing to Reproduce Spectral Distributions
观看向上卷积-基于CNN的可生成深度神经网络无法重现光谱分布
1426.Wavelet Integrated CNNs for Noise-Robust Image Classification
小波集成CNN用于鲁棒图像分类
1427.WaveletStereo - Learning Wavelet Coefficients of Disparity Map in Stereo Matching
WaveletStereo-立体匹配中视差图的小波系数学习
1428.Wavelet Synthesis Net for Disparity Estimation to Synthesize DSLR Calibre Bokeh Effect on Smartphones
小波综合网用于视差估计以合成智能手机的单反口径散景效果
1429.WCP - Worst-Case Perturbations for Semi-Supervised Deep Learning
WCP-半监督深度学习的最坏情况扰动
1430.Weakly-Supervised 3D Human Pose Learning via Multi-View Images in the Wild
在野外通过多视图图像进行弱监督的3D人体姿势学习
1431.Weakly-Supervised Action Localization by Generative Attention Modeling
通过生成注意力模型对弱监督动作进行本地化
1432.Weakly Supervised Discriminative Feature Learning With State Information for Person Identification
具有状态信息的弱监督区分特征学习,用于人员识别
1433.Weakly-Supervised Domain Adaptation via GAN and Mesh Model for Estimating 3D Hand Poses Interacting Objects
通过GAN和网格模型进行弱监督的域自适应以估计3D手姿势的交互对象
1434.Weakly Supervised Fine-Grained Image Classification via Guassian Mixture Model Oriented Discriminative Learning
基于高斯混合模型的判别学习的弱监督细粒度图像分类
1435.Weakly-Supervised Mesh-Convolutional Hand Reconstruction in the Wild
野外弱监督的网格卷积手重构
1436.Weakly-Supervised Salient Object Detection via Scribble Annotations
通过涂抹注释进行弱监督的显着对象检测
1437.Weakly Supervised Semantic Point Cloud Segmentation - Towards 10x Fewer Labels
受监督程度不强的语义点云细分-标签数量减少了10倍
1438.Weakly-Supervised Semantic Segmentation via Sub-Category Exploration
通过子类别探索的弱监督语义分割
1439.Weakly Supervised Visual Semantic Parsing
弱监督的视觉语义解析
1440.Webly Supervised Knowledge Embedding Model for Visual Reasoning
可视化推理的网络监督知识嵌入模型
1441.What Can Be Transferred - Unsupervised Domain Adaptation for Endoscopic Lesions Segmentation
什么可以转移-内镜病变分割的无监督域适应
1442.What Deep CNNs Benefit From Global Covariance Pooling - An Optimization Perspective
最深的CNN可以从全局协方差合并中受益-优化观点
1443.What Does Plate Glass Reveal About Camera Calibration -
平板玻璃对相机校准有何启示-
1444.What It Thinks Is Important Is Important - Robustness Transfers Through Input Gradients
它认为重要的是重要的-鲁棒性通过输入梯度传递
1445.What Machines See Is Not What They Get - Fooling Scene Text Recognition Models With Adversarial Text Images
机器看到的不是获得的东西-带有对抗性文本图像的傻瓜场景文本识别模型
1446.What Makes Training Multi-Modal Classification Networks Hard -
是什么使训练多模式分类网络变得困难-
1447.What’s Hidden in a Randomly Weighted Neural Network -
随机加权神经网络中隐藏的内容-
1448.What You See is What You Get - Exploiting Visibility for 3D Object Detection
所见即所得-利用3D对象检测的可见性
1449.When2com - Multi-Agent Perception via Communication Graph Grouping
When2com-通过通讯图分组进行多智能体感知
1450.When NAS Meets Robustness - In Search of Robust Architectures Against Adversarial Attacks
当NAS遇到鲁棒性时-寻找针对对抗攻击的鲁棒性架构
论文概要
1451.When to Use Convolutional Neural Networks for Inverse Problems
何时将卷积神经网络用于反问题
1452.Where Am I Looking At - Joint Location and Orientation Estimation by Cross-View Matching
我在哪里看-通过交叉视图匹配进行联合位置和方向估计
1453.Where Does It End - - Reasoning About Hidden Surfaces by Object Intersection Constraints
它在哪里结束-通过对象相交约束对隐藏曲面进行推理
1454.Where Does It Exist - Spatio-Temporal Video Grounding for Multi-Form Sentences
它存在于何处-时态视频的多形式句子接地
1455.Where, What, Whether - Multi-Modal Learning Meets Pedestrian Detection
哪里,什么,是否-多模式学习与行人检测相遇
1456.Which Is Plagiarism - Fashion Image Retrieval Based on Regional Representation for Design Protection
是Pla窃-基于区域表示的时装图像检索保护设计
1457.Why Having 10,000 Parameters in Your Camera Model Is Better Than Twelve
为什么在相机模型中具有10,000个参数要好于十二个
1458.Wish You Were Here - Context-Aware Human Generation
希望您在这里-感知上下文的人类一代
1459.X3D - Expanding Architectures for Efficient Video Recognition
X3D-高效的视频识别扩展架构
1460.X-Linear Attention Networks for Image Captioning
用于图像字幕的X线性注意力网络
1461.xMUDA - Cross-Modal Unsupervised Domain Adaptation for 3D Semantic Segmentation
xMUDA-用于3D语义分割的跨模态无监督域自适应
1462.You2Me - Inferring Body Pose in Egocentric Video via First and Second Person Interactions
You2Me-通过第一人称和第二人称互动推断自我中心视频中的身体姿势
1463.Your Local GAN - Designing Two Dimensional Local Attention Mechanisms for Generative Models
您的局部GAN-为生成模型设计二维局部注意机制
1464.Zero-Assignment Constraint for Graph Matching With Outliers
图与离群值匹配的零赋值约束
1465.ZeroQ - A Novel Zero Shot Quantization Framework
ZeroQ-一种新颖的零射击量化框架
1466.Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement
用于弱光图像增强的零参考深曲线估计
1467.Zooming Slow-Mo - Fast and Accurate One-Stage Space-Time Video Super-Resolution
慢动作缩放-快速准确的一阶段时空视频超分辨率
1468.ZSTAD - Zero-Shot Temporal Activity Detection
ZSTAD-零拍时间活动检测
  • 3
    点赞
  • 0
    评论
  • 4
    收藏
  • 一键三连
    一键三连
  • 扫一扫,分享海报

©️2021 CSDN 皮肤主题: 精致技术 设计师:CSDN官方博客 返回首页
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、C币套餐、付费专栏及课程。

余额充值