（八：2020.08.27）CVPR 2020 追踪之论文纲要（译）

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 Segmenta