（十一：2020.08.28）CVPR 2017 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。因为脚本还没完善而且谷歌把我的ip给封了暂时无法翻译，所以中英文不对称，之后有时间做修改。
• Respect！

---

论文目录

论文	概要
1.Geometric Deep Learning on Graphs and Manifolds Using Mixture Model CNNs 损失最大，池语义图像分割
2.Making Deep Neural Networks Robust to Label Noise: A Loss Correction Approach 多视角立体物检测网络的自动驾驶
3.ActionVLAD: Learning Spatio-Temporal Aggregation for Action Classification 在建模的第一人称动作识别子事件动态
4.Benchmarking Denoising Algorithms With Real Photographs 辐射校正从图像面孔
5.Stereo-Based 3D Reconstruction of Dynamic Fluid Surfaces by Global Optimization 并峙成像系统的线性外部校准从单三维点
6.Reflection Removal Using Low-Rank Matrix Completion 在线不对称相似性学习的跨模态的检索
7.A Dual Ascent Framework for Lagrangean Decomposition of Combinatorial Problems 参加组：A弱监督的深度学习框架借鉴Web数据
8.Deep Reinforcement Learning-Based Image Captioning With Embedding Reward 动态面部分析：从贝叶斯过滤，以回归神经网络
9.OctNet: Learning Deep 3D Representations at High Resolutions 广义语义保留哈希对于N标签跨模态的检索
10.Not All Pixels Are Equal: Difficulty-Aware Semantic Segmentation via Deep Layer Cascade 辐射校准互联网照片集
11.Unified Embedding and Metric Learning for Zero-Exemplar Event Detection 零射门识别使用双视觉，语义映射路径
12.Multiple Instance Detection Network With Online Instance Classifier Refinement 快速移动的物体的世界
13.Personalizing Gesture Recognition Using Hierarchical Bayesian Neural Networks 多目标跟踪与四套卷积神经网络
14.The Amazing Mysteries of the Gutter: Drawing Inferences Between Panels in Comic Book Narratives 深层结构化学习的面部动作单位强度估计
15.Wetness and Color From a Single Multispectral Image 同时超分辨率和使用弱监督联合卷积稀疏编码三维医学图像的跨模态合成
16.Discovering Causal Signals in Images 一到多网络的赏心悦目的压缩失真减少
17.Generative Hierarchical Learning of Sparse FRAME Models 判别相关滤波法与渠道和空间可靠性
18.Alternating Direction Graph Matching 自适应类保用于图像分类的表示
19.A-Fast-RCNN: Hard Positive Generation via Adversary for Object Detection 学习判别和转换协变局部特征检测器
20.Low-Rank-Sparse Subspace Representation for Robust Regression 线性逆回归应用的深度混合，以头姿态估计
21.Shape Completion Using 3D-Encoder-Predictor CNNs and Shape Synthesis 动态边缘空调的过滤器在卷积神经网络的图表
22.Neural Face Editing With Intrinsic Image Disentangling 可扩展的人重新鉴定的监督平滑流形
23.Unsupervised Video Summarization With Adversarial LSTM Networks FC4：全卷积颜色恒常随着置信度加权池
24.A Study of Lagrangean Decompositions and Dual Ascent Solvers for Graph Matching 多层次注意网络的可视化问题回答
25.Are You Smarter Than a Sixth Grader? Textbook Question Answering for Multimodal Machine Comprehension 迷雾三点算法相对位姿
26.Unrolling the Shutter: CNN to Correct Motion Distortions 通过关联性学习 - 一种多功能的神经网络半监督训练方法
27.Seeing Invisible Poses: Estimating 3D Body Pose From Egocentric Video FFTLasso：大型套索傅立叶域
28.A Matrix Splitting Method for Composite Function Minimization 详细，准确，人形估计从衣服的3D扫描序列
29.Deep Video Deblurring for Hand-Held Cameras 生长大脑：微调的增长模式容量
30.Bidirectional Multirate Reconstruction for Temporal Modeling in Videos 有什么可以帮行人检测？
31.Flexible Spatio-Temporal Networks for Video Prediction SST：单流态采取行动的建议
32.Predicting Salient Face in Multiple-Face Videos 实时神经式转换为影片
33.Learning From Noisy Large-Scale Datasets With Minimal Supervision 生成的描述具有接地和共同参考人
34.Are Large-Scale 3D Models Really Necessary for Accurate Visual Localization? 添加剂组分分析
35.Simultaneous Geometric and Radiometric Calibration of a Projector-Camera Pair 三维点云登记本地化使用深层神经网络自动编码器
36.BranchOut: Regularization for Online Ensemble Tracking With Convolutional Neural Networks 通过结合视觉和语言细粒度图像分类
37.SyncSpecCNN: Synchronized Spectral CNN for 3D Shape Segmentation AnchorNet：中弱监督网络学习的语义匹配几何敏感的特性
38.Weakly Supervised Semantic Segmentation Using Web-Crawled Videos 基于视觉表征重温度量学习的SPD矩阵
39.Non-Contact Full Field Vibration Measurement Based on Phase-Shifting 联合判别贝叶斯字典和分类学习
40.RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation 全自动内在摄像机标定采用定向光编码的实用方法
41.AMC: Attention guided Multi-modal Correlation Learning for Image Search 大多在刚性场景光流
42.A Multi-View Stereo Benchmark With High-Resolution Images and Multi-Camera Videos 深多式联运表示学习从时空数据
43.S3Pool: Pooling With Stochastic Spatial Sampling CLKN：级联卢卡斯金出武雄网络的图像对齐
44.CNN-Based Patch Matching for Optical Flow With Thresholded Hinge Embedding Loss 预算感知深层语义视频分割
45.Adaptive and Move Making Auxiliary Cuts for Binary Pairwise Energies 从零射门学习传统的监督分类：看不见的可视化数据合成
46.YouTube-BoundingBoxes: A Large High-Precision Human-Annotated Data Set for Object Detection in Video 空间语义图像由视觉特征综合搜索
47.Point to Set Similarity Based Deep Feature Learning for Person Re-Identification 在制作VQA物质在V：升降图像理解的视觉问题回答中的作用
48.Realtime Multi-Person 2D Pose Estimation Using Part Affinity Fields 视频加速放大
49.Age Progression_Regression by Conditional Adversarial Autoencoder 面的快速三维重建配眼镜
50.Soft-Margin Mixture of Regressions 学习视频对象分割从静态图像

论文	概要
51.Reliable Crowdsourcing and Deep Locality-Preserving Learning for Expression Recognition in the Wild 可靠的众包和深局部性保留学习的表情识别在野生
52.Semantic Image Inpainting With Deep Generative Models 语义图像修复凭借深厚的生成模型
53.ArtTrack: Articulated Multi-Person Tracking in the Wild ArtTrack：铰接式多人跟踪中野
54.Deep Quantization: Encoding Convolutional Activations With Deep Generative Model 深量化：卷积编码采用的激活深层生成模型
55.Binarized Mode Seeking for Scalable Visual Pattern Discovery 二值化模式寻求可扩展可视化模式发现
56.Simple Does It: Weakly Supervised Instance and Semantic Segmentation 简单做的：弱监督实例和语义分割
57.Variational Bayesian Multiple Instance Learning With Gaussian Processes 变贝叶斯多示例学习用高斯过程
58.Learning Barycentric Representations of 3D Shapes for Sketch-Based 3D Shape Retrieval 3D形状，以素描为基础的3D形状检索学习重心交涉
59.Deep Roots: Improving CNN Efficiency With Hierarchical Filter Groups 深根：提高CNN效率分级结构滤波器组
60.Crossing Nets: Combining GANs and VAEs With a Shared Latent Space for Hand Pose Estimation 隧道网：结合甘斯和VAES与共享的潜在空间的手的形状估计
61.Harmonic Networks: Deep Translation and Rotation Equivariance 谐波网络：深平移和旋转同变性
62.Spatio-Temporal Self-Organizing Map Deep Network for Dynamic Object Detection From Videos 时空自组织映射网络深层的动态目标检测从影片
63.Jointly Learning Energy Expenditures and Activities Using Egocentric Multimodal Signals 共同学习能源支出和活动使用自我中心的多模态信号
64.Efficient Diffusion on Region Manifolds: Recovering Small Objects With Compact CNN Representations 在地区歧管高效扩散：恢复小物件紧凑CNN交涉
65.Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network 照片般逼真的单幅图像的超分辨率使用剖成对抗性网络
66.ShapeOdds: Variational Bayesian Learning of Generative Shape Models 学习式外形模型的变分贝叶斯：ShapeOdds
67.Amodal Detection of 3D Objects: Inferring 3D Bounding Boxes From 2D Ones in RGB-Depth Images 3D的Amodal检测对象：在RGB-深度图像推断3D包围盒从2D问鼎
68.Joint Sequence Learning and Cross-Modality Convolution for 3D Biomedical Segmentation 联合序列学习和跨模态卷积3D生物医学分割
69.Spatially-Varying Blur Detection Based on Multiscale Fused and Sorted Transform Coefficients of Gradient Magnitudes 空间变化的模糊检测基于多尺度融合和排序变换梯度强度系数
70.Training Object Class Detectors With Click Supervision 培训对象类探测器随着点击监督
71.Fully-Adaptive Feature Sharing in Multi-Task Networks With Applications in Person Attribute Classification 在多任务网络全自适应特征共享随着人员属性分类中的应用
72.Active Convolution: Learning the Shape of Convolution for Image Classification 主动卷积：学习卷积对图像分类形状
73.BIND: Binary Integrated Net Descriptors for Texture-Less Object Recognition BIND：二进制综合净叙为无纹理物体识别
74.Efficient Global Point Cloud Alignment Using Bayesian Nonparametric Mixtures 高效的全球点云对齐使用贝叶斯非参数混合物
75.Real-Time 3D Model Tracking in Color and Depth on a Single CPU Core 实时3D模型跟踪的颜色和深度上的单核CPU
76.Image-To-Image Translation With Conditional Adversarial Networks 图片到影像翻译有条件的对抗性网络
77.IRINA: Iris Recognition (Even) in Inaccurately Segmented Data IRINA：虹膜识别（即使）在不准确分割数据
78.A Graph Regularized Deep Neural Network for Unsupervised Image Representation Learning 图表正则深层神经网络的无监督图像表示学习
79.Nonnegative Matrix Underapproximation for Robust Multiple Model Fitting 非负矩阵Underapproximation的鲁棒多模型拟合
80.Learning Deep CNN Denoiser Prior for Image Restoration 图像复原学习深CNN去噪前
81.A Unified Approach of Multi-Scale Deep and Hand-Crafted Features for Defocus Estimation 多尺度深和手工制作的统一的方法特点的散焦估计
82.Detecting Oriented Text in Natural Images by Linking Segments 通过链接段检测自然图像中的文本面向
83.Spatio-Temporal Naive-Bayes Nearest-Neighbor (ST-NBNN) for Skeleton-Based Action Recognition 时空朴素贝叶斯近邻（ST-NBNN）为骨架为基础的行动识别
84.Noisy Softmax: Improving the Generalization Ability of DCNN via Postponing the Early Softmax Saturation 嘈杂SOFTMAX：通过推迟早期使用SoftMax饱和度提高DCNN的泛化能力
85.A Non-Convex Variational Approach to Photometric Stereo Under Inaccurate Lighting 一个非凸变分法，以光度立体不精确照明
86.Weakly Supervised Dense Video Captioning 弱监督密集视频字幕
87.Learning From Simulated and Unsupervised Images Through Adversarial Training 学习从模拟和无监督的图像通过对抗性训练
88.Gated Feedback Refinement Network for Dense Image Labeling 封闭式反馈细化网络的密集影像标签
89.Kernel Pooling for Convolutional Neural Networks 内核池卷积神经网络
90.Context-Aware Correlation Filter Tracking 上下文感知相关滤波跟踪
91.Detect, Replace, Refine: Deep Structured Prediction for Pixel Wise Labeling 检测，替换，优化：对于像素级标签深结构预测
92.SphereFace: Deep Hypersphere Embedding for Face Recognition SphereFace：深超球嵌入人脸识别
93.ER3: A Unified Framework for Event Retrieval, Recognition and Recounting ER3：一个统一的框架为事件检索，识别，并介绍
94.Direct Photometric Alignment by Mesh Deformation 直接对准光度通过网格变形
95.Self-Critical Sequence Training for Image Captioning 自我批判序列训练的图像字幕
96.Temporal Convolutional Networks for Action Segmentation and Detection 时间卷积网络的行动分割和检测
97.Oriented Response Networks 面向反应网络
98.Reflectance Adaptive Filtering Improves Intrinsic Image Estimation 反射自适应滤波提高了内在的图像估计
99.Multi-Scale Continuous CRFs as Sequential Deep Networks for Monocular Depth Estimation 多尺度连续控释肥作为连续深网络的单眼深度估计
100.Removing Rain From Single Images via a Deep Detail Network 通过深入详细的网络中删除雨水单张图像

论文	概要
101.Learning to Predict Stereo Reliability Enforcing Local Consistency of Confidence Maps 语义正则复发的图像标注
102.Learning Deep Binary Descriptor With Multi-Quantization 边缘检测更丰富的卷积功能
103.Person Search With Natural Language Description 强大的联合和个别差异的解释
104.Parametric T-Spline Face Morphable Model for Detailed Fitting in Shape Subspace 动态FAUST：在运动登记人体
105.Discriminative Optimization: Theory and Applications to Point Cloud Registration 全球环境感知注意LSTM网络的3D动作识别
106.A Message Passing Algorithm for the Minimum Cost Multicut Problem 学习自适应接受域的深层意象解析网络
107.A Dataset and Exploration of Models for Understanding Video Data Through Fill-In-The-Blank Question-Answering 模仿非常有效的网络物体检测
108.Compact Matrix Factorization With Dependent Subspaces 深表示学习的人体运动预测和分类
109.Transformation-Grounded Image Generation Network for Novel 3D View Synthesis 定点分比网络
110.Binary Constraint Preserving Graph Matching FastMask：在一杆段多尺度物体候选
111.L2-Net: Deep Learning of Discriminative Patch Descriptor in Euclidean Space 时空注意力门控模型的鲁棒序划分
112.End-To-End 3D Face Reconstruction With Deep Neural Networks 深度学习人视觉灵敏度的图像质量评估框架
113.PolyNet: A Pursuit of Structural Diversity in Very Deep Networks InstanceCut：从边缘到实例用的MultiCut
114.Zero-Shot Action Recognition With Error-Correcting Output Codes 多路多级内核建模神经影像学分类
115.Comparative Evaluation of Hand-Crafted and Learned Local Features 在神经风格传输控制感性因素
116.Unsupervised Semantic Scene Labeling for Streaming Data 3D包围盒估计使用Deep学习几何
117.Unsupervised Monocular Depth Estimation With Left-Right Consistency 非对称特征的地图，应用基于草图检索
118.An Efficient Algebraic Solution to the Perspective-Three-Point Problem 由粗到细分中的具有形状定制连续尺度空间
119.Memory-Augmented Attribute Manipulation Networks for Interactive Fashion Search 一种有效的背景期限为三维重建和跟踪光滑曲面模型
120.CERN: Confidence-Energy Recurrent Network for Group Activity Recognition 单次视频对象分割
121.Geodesic Distance Descriptors Adversarially调谐场景生成
122.Deep Hashing Network for Unsupervised Domain Adaptation 局部性敏感的反褶积网络，门控融合RGB-d室内语义分割
123.Incremental Kernel Null Space Discriminant Analysis for Novelty Detection 动态合成模式的时空剖成ConvNet
124.Seeing Into Darkness: Scotopic Visual Recognition 从红酒到红番茄：组成具有上下文
125.Slow Flow: Exploiting High-Speed Cameras for Accurate and Diverse Optical Flow Reference Data 深多尺度卷积神经网络的动态场景去模糊算法
126.Look Closer to See Better: Recurrent Attention Convolutional Neural Network for Fine-Grained Image Recognition 数据集为基准基于图像的定位
127.VidLoc: A Deep Spatio-Temporal Model for 6-DoF Video-Clip Relocalization SGM-篮网：半全局匹配带神经网络
128.S2F: Slow-To-Fast Interpolator Flow 层次多模态度量学习的多模态分类
129.Flight Dynamics-Based Recovery of a UAV Trajectory Using Ground Cameras 对象知晓密集语义对应
130.Fine-To-Coarse Global Registration of RGB-D Scans 使用排名-CNN的年龄估计
131.Local Binary Convolutional Neural Networks 深度离焦在狂野
132.Aggregated Residual Transformations for Deep Neural Networks 过渡森林：学习判别时间变迁行动识别定位
133.DeepPermNet: Visual Permutation Learning 深沉的变奏 - 结构化强化学习的视觉关系和属性检测
134.Anti-Glare: Tightly Constrained Optimization for Eyeglass Reflection Removal SPFTN：自定进度微调网络用于分割在弱标记的视频对象
135.A Domain Based Approach to Social Relation Recognition TGIF-QA：走向时空推理在Visual答疑
136.Simultaneous Stereo Video Deblurring and Scene Flow Estimation Speed_Accuracy取舍现代卷积对象探测器
137.Noise Robust Depth From Focus Using a Ring Difference Filter 学习为Geolocalization对齐语义分割和2.5D地图
138.Deep Future Gaze: Gaze Anticipation on Egocentric Videos Using Adversarial Networks 牛顿型方法推断高阶马尔可夫随机场
139.Reconstructing Transient Images From Single-Photon Sensors 终端到终端的概念词检测视频字幕显示，检索和问题回答
140.ChestX-ray8: Hospital-Scale Chest X-Ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseases 一个强化学习的方法来查看规划问题
141.Collaborative Deep Reinforcement Learning for Joint Object Search 阴影标注在狂野
142.Multigrid Neural Architectures 同时功能聚合和散列进行大规模图片搜索
143.Pose-Aware Person Recognition **基于模型的迭代复原为二进制文档图像压缩处理的意思 - **
144.Video Propagation Networks 新秩约束的多视角基本矩阵，及对摄像头位置恢复中的应用
145.Forecasting Interactive Dynamics of Pedestrians With Fictitious Play 词随着语言的结构的弱监督视觉接地
146.3D Human Pose Estimation From a Single Image via Distance Matrix Regression 联合登记和代表学习的无约束人脸识别
147.Hidden Layers in Perceptual Learning STD2P：RGBD语义分割使用的时空数据驱动池
148.Detecting Masked Faces in the Wild With LLE-CNNs 筛选流程提出了切实可行的：大规模并行和无锁
149.Domain Adaptation by Mixture of Alignments of Second- or Higher-Order Scatter Tensors 自我监督视频表示学习用奇一出网络
150.Material Classification Using Frequency- and Depth-Dependent Time-Of-Flight Distortion 了解交通密度大规模网络摄像头数据

论文	概要
151.On the Global Geometry of Sphere-Constrained Sparse Blind Deconvolution 在球约束稀疏盲解全球几何
152.Hallucinating Very Low-Resolution Unaligned and Noisy Face Images by Transformative Discriminative Autoencoders