（十：2020.08.28）CVPR 2018 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979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。
• 下面皆为机器翻译以方便我第一次筛选，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
1.2D_3D Pose Estimation and Action Recognition Using Multitask Deep Learning 使用多任务深度学习的2D_3D姿势估计和动作识别
2.3D Human Pose Estimation in the Wild by Adversarial Learning 通过对抗性学习在野外进行3D人体姿势估计
3.3D Human Sensing, Action and Emotion Recognition in Robot Assisted Therapy of Children With Autism 孤独症儿童机器人辅助治疗中的3D人体感应，动作和情感识别
4.3D Object Detection With Latent Support Surfaces 具有潜在支撑面的3D对象检测
5.3D Pose Estimation and 3D Model Retrieval for Objects in the Wild 野外物体的3D姿势估计和3D模型检索
6.3D-RCNN: Instance-Level 3D Object Reconstruction via Render-and-Compare 3D-RCNN：通过渲染和比较重建实例级3D对象
7.3D Registration of Curves and Surfaces Using Local Differential Information 使用局部微分信息进行曲线和曲面的3D配准
8.3D Semantic Segmentation With Submanifold Sparse Convolutional Networks 子流形稀疏卷积网络的3D语义分割
9.3D Semantic Trajectory Reconstruction From 3D Pixel Continuum 从3D像素连续体重建3D语义轨迹
10.4DFAB: A Large Scale 4D Database for Facial Expression Analysis and Biometric Applications 4DFAB：用于面部表情分析和生物识别应用程序的大规模4D数据库
11.4D Human Body Correspondences From Panoramic Depth Maps 全景深度图的4D人体对应
12.A2-RL: Aesthetics Aware Reinforcement Learning for Image Cropping A2-RL：用于图像裁剪的美学意识增强学习
13.A Bi-Directional Message Passing Model for Salient Object Detection 显着目标检测的双向消息传递模型
14.A Biresolution Spectral Framework for Product Quantization 用于产品量化的双分辨率光谱框架
15.A Causal And-Or Graph Model for Visibility Fluent Reasoning in Tracking Interacting Objects 交互对象跟踪中可视性推理的因果图模型
16.Accurate and Diverse Sampling of Sequences Based on a “Best of Many” Sample Objective 基于“多个最佳”样本目标的序列的准确多样采样
17.A Certifiably Globally Optimal Solution to the Non-Minimal Relative Pose Problem 非最小相对姿势问题的可证明的全局最优解
18.A Closer Look at Spatiotemporal Convolutions for Action Recognition 近距离观察时空卷积的动作识别
19.A Common Framework for Interactive Texture Transfer 交互式纹理传输的通用框架
20.A Constrained Deep Neural Network for Ordinal Regression 序数回归的约束深度神经网络
21.Action Sets: Weakly Supervised Action Segmentation Without Ordering Constraints 动作集：没有顺序约束的弱监督动作细分
22.Active Fixation Control to Predict Saccade Sequences 主动注视控制可预测扫视序列
23.Actor and Action Video Segmentation From a Sentence 句子中的演员和动作视频分割
24.Actor and Observer: Joint Modeling of First and Third-Person Videos 演员和观察员：第一人称和第三人称视频的联合建模
25.AdaDepth: Unsupervised Content Congruent Adaptation for Depth Estimation AdaDepth：用于深度估计的无监督内容一致适应
26.A Deeper Look at Power Normalizations 深入了解功率归一化
27.Adversarial Complementary Learning for Weakly Supervised Object Localization 弱监督对象定位的对抗互补学习
28.Adversarial Data Programming: Using GANs to Relax the Bottleneck of Curated Labeled Data 对抗性数据编程：使用GAN缓解标签化数据的瓶颈
29.Adversarial Feature Augmentation for Unsupervised Domain Adaptation 无监督域自适应的对抗特征增强
30.Adversarially Learned One-Class Classifier for Novelty Detection 对抗性学习的一类分类器，用于新颖性检测
31.Adversarially Occluded Samples for Person Re-Identification 对抗性样本用于人员重新识别
32.A Face-to-Face Neural Conversation Model 面对面的神经对话模型
33.A Fast Resection-Intersection Method for the Known Rotation Problem 已知旋转问题的快速后方交集方法
34.A Generative Adversarial Approach for Zero-Shot Learning From Noisy Texts 一种从嘈杂文本中零接触学习的生成对抗方法
35.A Hierarchical Generative Model for Eye Image Synthesis and Eye Gaze Estimation 眼睛图像合成和眼睛注视估计的分层生成模型
36.A High-Quality Denoising Dataset for Smartphone Cameras 用于智能手机相机的高质量降噪数据集
37.A Hybrid l1-l0 Layer Decomposition Model for Tone Mapping 用于色调映射的混合l1-l0层分解模型
38.Aligning Infinite-Dimensional Covariance Matrices in Reproducing Kernel Hilbert Spaces for Domain Adaptation 对齐域希尔伯特希尔伯特空间中的无限维协方差矩阵的对齐
39.Alive Caricature From 2D to 3D 从2D到3D的生动漫画
40.A Low Power, High Throughput, Fully Event-Based Stereo System 低功耗，高吞吐量，完全基于事件的立体声系统
41.Alternating-Stereo VINS: Observability Analysis and Performance Evaluation 交替立体VINS：可观察性分析和性能评估
42.A Memory Network Approach for Story-Based Temporal Summarization of 360deg Videos 基于故事的360deg视频时间摘要的记忆网络方法
43.A Minimalist Approach to Type-Agnostic Detection of Quadrics in Point Clouds 点云中二次元的类型不可知检测的极简方法
44.AMNet: Memorability Estimation With Attention AMNet：具有记忆力的评估
45.Analysis of Hand Segmentation in the Wild 野外手部分割分析
46.Analytical Modeling of Vanishing Points and Curves in Catadioptric Cameras 折反射相机中消失点和曲线的解析模型
47.Analytic Expressions for Probabilistic Moments of PL-DNN With Gaussian Input 高斯输入的PL-DNN概率矩的解析表达式
48.Analyzing Filters Toward Efficient ConvNet 分析面向高效ConvNet的过滤器
49.An Analysis of Scale Invariance in Object Detection SNIP 目标检测SNIP中尺度不变性的分析
50.Anatomical Priors in Convolutional Networks for Unsupervised Biomedical Segmentation 卷积网络中无监督生物医学分割的解剖先验

论文	概要
51.An Efficient and Provable Approach for Mixture Proportion Estimation Using Linear Independence Assumption 使用线性独立假设的混合比例估计的一种有效且可行的方法
52.An End-to-End TextSpotter With Explicit Alignment and Attention 具有明确对齐和注意力的端到端TextSpotter
53.A Network Architecture for Point Cloud Classification via Automatic Depth Images Generation 通过自动深度图像生成进行点云分类的网络架构
54.A Neural Multi-Sequence Alignment TeCHnique (NeuMATCH) 神经多序列比对技术（NeuMATCH）
55.Anticipating Traffic Accidents With Adaptive Loss and Large-Scale Incident DB 利用自适应丢失和大规模事件数据库预测交通事故
56.An Unsupervised Learning Model for Deformable Medical Image Registration 可变形医学图像配准的无监督学习模型
57.AON: Towards Arbitrarily-Oriented Text Recognition AON：面向任意方向的文本识别
58.A Papier-Mache Approach to Learning 3D Surface Generation 学习3D曲面生成的Papier-Mache方法
59.A Perceptual Measure for Deep Single Image Camera Calibration 深度单像相机校准的感官测量
60.Aperture Supervision for Monocular Depth Estimation 用于单眼深度估计的光圈监控
61.A PID Controller Approach for Stochastic Optimization of Deep Networks 用于深度网络随机优化的PID控制器方法
62.A Pose-Sensitive Embedding for Person Re-Identification With Expanded Cross Neighborhood Re-Ranking 具有扩展的跨邻域重新排列的姿势重新识别的姿势识别嵌入
63.Appearance-and-Relation Networks for Video Classification 视频分类的外观和关系网络
64.A Prior-Less Method for Multi-Face Tracking in Unconstrained Videos 无约束视频中多面跟踪的一种先验减少方法
65.Arbitrary Style Transfer With Deep Feature Reshuffle 任意样式转移，具有深层功能重组
66.A Revised Underwater Image Formation Model 修订后的水下成像模型
67.Are You Talking to Me? Reasoned Visual Dialog Generation Through Adversarial Learning 你在跟我讲话吗？通过对抗学习进行合理的视觉对话生成
68.A Robust Method for Strong Rolling Shutter Effects Correction Using Lines With Automatic Feature Selection 一种具有自动特征选择线的强力滚动快门效果校正的鲁棒方法
69.Art of Singular Vectors and Universal Adversarial Perturbations 奇异向量和普遍对抗性摄动的艺术
70.Attend and Interact: Higher-Order Object Interactions for Video Understanding 参加和交互：用于视频理解的高阶对象交互
71.Attentional ShapeContextNet for Point Cloud Recognition 注意ShapeContextNet用于点云识别
72.Attention-Aware Compositional Network for Person Re-Identification 用于人员重新识别的注意感知组成网络
73.Attention Clusters: Purely Attention Based Local Feature Integration for Video Classification 注意力集群：基于纯粹注意力的视频分类局部特征集成
74.Attentive Fashion Grammar Network for Fashion Landmark Detection and Clothing Category Classification 专注于时尚地标检测和服装类别分类的时尚语法网络
75.Attentive Generative Adversarial Network for Raindrop Removal From a Single Image 细心的生成对抗网络，用于从单个图像中去除雨滴
76.AttnGAN: Fine-Grained Text to Image Generation With Attentional Generative Adversarial Networks AttnGAN：细化文本到带有注意生成对抗网络的图像生成
77.A Twofold Siamese Network for Real-Time Object Tracking 用于实时对象跟踪的双重连体网络
78.A Two-Step Disentanglement Method 两步解缠法
79.Audio to Body Dynamics 音频到人体动力学
80.Augmented Skeleton Space Transfer for Depth-Based Hand Pose Estimation 基于深度的手部姿势估计的增强骨架空间传递
81.Augmenting Crowd-Sourced 3D Reconstructions Using Semantic Detections 使用语义检测增强人群源3D重建
82.A Unifying Contrast Maximization Framework for Event Cameras, With Applications to Motion, Depth, and Optical Flow Estimation 用于事件摄像机的统一对比度最大化框架，应用于运动，深度和光流估计
83.Automatic 3D Indoor Scene Modeling From Single Panorama 从单个全景图进行自动3D室内场景建模
84.AVA: A Video Dataset of Spatio-Temporally Localized Atomic Visual Actions AVA：时空局部原子视觉动作的视频数据集
85.A Variational U-Net for Conditional Appearance and Shape Generation 用于条件外观和形状生成的变体U-网
86.Avatar-Net: Multi-Scale Zero-Shot Style Transfer by Feature Decoration Avatar-Net：通过特征装饰进行多尺度零射击样式转移
87.A Weighted Sparse Sampling and Smoothing Frame Transition Approach for Semantic Fast-Forward First-Person Videos 语义快进第一人称视频的加权稀疏采样和平滑帧过渡方法
88.Baseline Desensitizing in Translation Averaging 平均翻译中的基线脱敏
89.Benchmarking 6DOF Outdoor Visual Localization in Changing Conditions 在不断变化的条件下对6DOF户外视觉本地化进行基准测试
90.Between-Class Learning for Image Classification 课间学习进行图像分类
91.Beyond Grobner Bases: Basis Selection for Minimal Solvers Grobner基础之外：最小求解器的基础选择
92.Beyond Holistic Object Recognition: Enriching Image Understanding With Part States 超越整体物体识别：利用零件状态丰富图像理解
93.Beyond the Pixel-Wise Loss for Topology-Aware Delineation 超越像素明智的拓扑描述
94.Beyond Trade-Off: Accelerate FCN-Based Face Detector With Higher Accuracy 权衡之外：高精度加速基于FCN的人脸检测器
95.Bidirectional Attentive Fusion With Context Gating for Dense Video Captioning 具有上下文门控功能的双向注意力融合，用于密集视频字幕
96.Bidirectional Retrieval Made Simple 双向检索变得简单
97.Bilateral Ordinal Relevance Multi-Instance Regression for Facial Action Unit Intensity Estimation 双边序贯相关性多实例回归用于面部动作单位强度估计
98.Blazingly Fast Video Object Segmentation With Pixel-Wise Metric Learning 像素明智的度量学习，实现了惊人的快速视频对象分割
99.Blind Predicting Similar Quality Map for Image Quality Assessment 盲预测相似质量图进行图像质量评估
100.BlockDrop: Dynamic Inference Paths in Residual Networks BlockDrop：残差网络中的动态推理路径

论文	概要
101.Boosting Adversarial Attacks With Momentum 用动量来增强对抗性攻击
102.Boosting Domain Adaptation by Discovering Latent Domains 通过发现潜在域来促进域适应
103.Boosting Self-Supervised Learning via Knowledge Transfer 通过知识转移促进自我监督学习
104.Bootstrapping the Performance of Webly Supervised Semantic Segmentation 引导Webly监督的语义分割的性能
105.Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering 自下而上和自上而下的注意力，用于图像字幕和视觉问题解答
106.Boundary Flow: A Siamese Network That Predicts Boundary Motion Without Training on Motion 边界流：无需运动训练就可以预测边界运动的暹罗网络
107.BPGrad: Towards Global Optimality in Deep Learning via Branch and Pruning BPGrad：通过分支和修剪在深度学习中实现全球最优
108.Burst Denoising With Kernel Prediction Networks 内核预测网络进行突发去噪
109.Camera Pose Estimation With Unknown Principal Point 主点未知的相机姿态估计
110.Camera Style Adaptation for Person Re-Identification 用于重新识别人的相机样式适应
111.Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet? 时空3D CNN是否可以追溯2D CNN和ImageNet的历史？
112.CarFusion: Combining Point Tracking and Part Detection for Dynamic 3D Reconstruction of Vehicles CarFusion：结合点跟踪和零件检测用于车辆的动态3D重构
113.CartoonGAN: Generative Adversarial Networks for Photo Cartoonization CartoonGAN：用于照片卡通化的生成对抗网络
114.Cascaded Pyramid Network for Multi-Person Pose Estimation 用于多人姿势估计的级联金字塔网络
115.Cascade R-CNN: Delving Into High Quality Object Detection 级联R-CNN：深入研究高质量目标检测
116.Categorizing Concepts With Basic Level for Vision-to-Language 将基本概念归类为视觉到语言
117.CBMV: A Coalesced Bidirectional Matching Volume for Disparity Estimation CBMV：用于视差估计的合并双向匹配量
118.Classification-Driven Dynamic Image Enhancement 分类驱动的动态图像增强
119.Classifier Learning With Prior Probabilities for Facial Action Unit Recognition 具有面部动作单元识别先验概率的分类器学习
120.ClcNet: Improving the Efficiency of Convolutional Neural Network Using Channel Local Convolutions ClcNet：使用通道局部卷积提高卷积神经网络的效率
121.CleanNet: Transfer Learning for Scalable Image Classifier Training With Label Noise CleanNet：带标签噪声的可扩展图像分类器培训的转移学习
122.CLEAR: Cumulative LEARning for One-Shot One-Class Image Recognition 清除：一键式一类图像识别的累积学习
123.Clinical Skin Lesion Diagnosis Using Representations Inspired by Dermatologist Criteria 使用皮肤科医生标准启发的表征进行临床皮肤病变诊断
124.CLIP-Q: Deep Network Compression Learning by In-Parallel Pruning-Quantization CLIP-Q：通过并行修剪量化进行深度网络压缩学习
125.ClusterNet: Detecting Small Objects in Large Scenes by Exploiting Spatio-Temporal Information ClusterNet：通过利用时空信息检测大型场景中的小物体
126.CNN Based Learning Using Reflection and Retinex Models for Intrinsic Image Decomposition 基于CNN的使用反射和Retinex模型进行内在图像分解的学习
127.CNN Driven Sparse Multi-Level B-Spline Image Registration CNN驱动的稀疏多级B样条图像配准
128.CNN in MRF: Video Object Segmentation via Inference in a CNN-Based Higher-Order Spatio-Temporal MRF MRF中的CNN：在基于CNN的高阶时空MRF中通过推理进行视频对象分割
129.COCO-Stuff: Thing and Stuff Classes in Context COCO-Stuff：上下文中的事物和事物类
130.CodeSLAM – Learning a Compact, Optimisable Representation for Dense Visual SLAM CodeSLAM-学习密集Visual SLAM的紧凑，可优化表示形式
131.Coding Kendall’s Shape Trajectories for 3D Action Recognition 编码Kendall的形状轨迹以进行3D动作识别
132.Collaborative and Adversarial Network for Unsupervised Domain Adaptation 无监督域自适应的协作和对抗网络
133.Compare and Contrast: Learning Prominent Visual Differences 比较和对比：学习明显的视觉差异
134.Compassionately Conservative Balanced Cuts for Image Segmentation 慷慨保守的平衡切割用于图像分割
135.Compressed Video Action Recognition 压缩视频动作识别
136.CondenseNet: An Efficient DenseNet Using Learned Group Convolutions CondenseNet：使用学习的组卷积的高效DenseNet
137.Conditional Generative Adversarial Network for Structured Domain Adaptation 结构化领域适应的条件生成对抗网络
138.Conditional Image-to-Image Translation 有条件的图像到图像翻译
139.Conditional Probability Models for Deep Image Compression 深度图像压缩的条件概率模型
140.Connecting Pixels to Privacy and Utility: Automatic Redaction of Private Information in Images 将像素连接到隐私和实用程序：自动删除图像中的私人信息
141.Consensus Maximization for Semantic Region Correspondences 语义区域对应的共识最大化
142.Content-Sensitive Supervoxels via Uniform Tessellations on Video Manifolds 通过视频流形上的统一镶嵌来对内容敏感的超级体素
143.Context-Aware Deep Feature Compression for High-Speed Visual Tracking 用于高速视觉跟踪的上下文感知深度特征压缩
144.Context-Aware Synthesis for Video Frame Interpolation 视频帧插值的上下文感知综合
145.Context Contrasted Feature and Gated Multi-Scale Aggregation for Scene Segmentation 用于场景分割的上下文对比特征和门控多尺度聚合
146.Context Embedding Networks 上下文嵌入网络
147.Context Encoding for Semantic Segmentation 用于语义分割的上下文编码
148.Continuous Relaxation of MAP Inference: A Nonconvex Perspective MAP推理的连续松弛：非凸视角
149.Controllable Video Generation With Sparse Trajectories 具有稀疏轨迹的可控视频生成
150.Convolutional Image Captioning 卷积图像字幕

论文	概要
151.Convolutional Neural Networks With Alternately Updated Clique 具有交替更新的派系的卷积神经网络
152.Convolutional Sequence to Sequence Model for Human Dynamics 卷积序列到人类动力学序列模型
153.Correlation Tracking via Joint Discrimination and Reliability Learning 通过联合鉴别和可靠性学习进行关联跟踪
154.CosFace: Large Margin Cosine Loss for Deep Face Recognition CosFace：用于识别深脸的大余弦余弦损失
155.Coupled End-to-End Transfer Learning With Generalized Fisher Information 端到端迁移学习与广义Fisher信息相结合
156.Crafting a Toolchain for Image Restoration by Deep Reinforcement Learning 通过深度强化学习制作用于图像还原的工具链
157.Creating Capsule Wardrobes From Fashion Images 从时尚形象创建胶囊衣柜
158.Cross-Dataset Adaptation for Visual Question Answering 跨数据集自适应以解决视觉问题
159.Cross-Domain Self-Supervised Multi-Task Feature Learning Using Synthetic Imagery 使用合成影像的跨域自我监督多任务特征学习
160.Cross-Domain Weakly-Supervised Object Detection Through Progressive Domain Adaptation 通过渐进域自适应进行跨域弱监督对象检测
161.Cross-Modal Deep Variational Hand Pose Estimation 跨模态深度变化手姿势估计
162.Cross-View Image Synthesis Using Conditional GANs 使用条件GAN的跨视图图像合成
163.Crowd Counting via Adversarial Cross-Scale Consistency Pursuit 通过对抗性跨尺度一致性追求进行人群计数
164.Crowd Counting With Deep Negative Correlation Learning 深度负相关学习的人群计数
165.CRRN: Multi-Scale Guided Concurrent Reflection Removal Network CRRN：多尺度引导并发反射去除网络
166.CSGNet: Neural Shape Parser for Constructive Solid Geometry CSGNet：用于构造实体几何的神经形状解析器
167.CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes CSRNet：扩展卷积神经网络，用于了解高度拥挤的场景
168.Cube Padding for Weakly-Supervised Saliency Prediction in 360deg Videos 360度视频中弱监督显着性预测的多维数据集填充
169.Curve Reconstruction via the Global Statistics of Natural Curves 通过自然曲线的整体统计量重建曲线
170.Customized Image Narrative Generation via Interactive Visual Question Generation and Answering 通过交互式视觉问题生成和回答定制的图像叙事生成
171.CVM-Net: Cross-View Matching Network for Image-Based Ground-to-Aerial Geo-Localization CVM-Net：用于基于图像的地对空地理定位的跨视图匹配网络
172.DA-GAN: Instance-Level Image Translation by Deep Attention Generative Adversarial Networks DA-GAN：深度注意生成对抗网络的实例级图像翻译
173.Data Distillation: Towards Omni-Supervised Learning 数据提炼：走向全监督学习
174.DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks DeblurGAN：使用条件对抗网络进行盲运动去模糊
175.DecideNet: Counting Varying Density Crowds Through Attention Guided Detection and Density Estimation DecideNet：通过注意力指导的检测和密度估计计算不同的密度人群
176.Decorrelated Batch Normalization 装饰相关的批次标准化
177.Decoupled Networks 解耦网络
178.Deep Adversarial Metric Learning 深度对抗度量学习
179.Deep Adversarial Subspace Clustering 深度对抗子空间聚类
180.Deep Back-Projection Networks for Super-Resolution 深度背投网络可实现超高分辨率
181.Deep Cauchy Hashing for Hamming Space Retrieval 深层柯西散列用于汉明空间检索
182.Deep Cocktail Network: Multi-Source Unsupervised Domain Adaptation With Category Shift 深度鸡尾酒网络：具有类别转移的多源无监督域自适应
183.Deep Cost-Sensitive and Order-Preserving Feature Learning for Cross-Population Age Estimation 用于跨人口年龄估计的深度成本敏感和顺序保留特征学习
184.Deep Cross-Media Knowledge Transfer 深度跨媒体知识转移
185.Deep Density Clustering of Unconstrained Faces 无约束面孔的深度密度聚类
186.Deep Depth Completion of a Single RGB-D Image 单个RGB-D图像的深度完成
187.Deep Diffeomorphic Transformer Networks 深微形变压器网络
188.Deep End-to-End Time-of-Flight Imaging 深度端到端飞行时间成像
189.Deep Extreme Cut: From Extreme Points to Object Segmentation 深度极限切割：从极限点到对象分割
190.Deep Face Detector Adaptation Without Negative Transfer or Catastrophic Forgetting 无需负迁移或灾难性遗忘的深脸检测器自适应
191.Deep Group-Shuffling Random Walk for Person Re-Identification 用于人员重新识别的深度群混洗随机游走
192.Deep Hashing via Discrepancy Minimization 通过差异最小化进行深度哈希
193.Deep Image Prior 深度图像先验
194.Deep Layer Aggregation 深层聚合
195.Deep Learning of Graph Matching