（十二：2020.08.28）CVPR 2016 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643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.CNN-N-Gram for Handwriting Word Recognition 深陈述和图像集群联合无监督学习
2.A Text Detection System for Natural Scenes With Convolutional Feature Learning and Cascaded Classification 复杂的动态场景的时间相干4D重建
3.Saliency Unified: A Deep Architecture for Simultaneous Eye Fixation Prediction and Salient Object Segmentation 在时变图像集增量对象发现
4.What Players Do With the Ball: A Physically Constrained Interaction Modeling 对于点集注册引力方法
5.Two Illuminant Estimation and User Correction Preference 可变孔径的光场摄影：克服衍射极限空间 - 角分辨率权衡
6.The Global Patch Collider 自我中心未来本地化
7.Structured Regression Gradient Boosting 多尺度补丁聚集（MPA）的同时检测与分割
8.Rethinking the Inception Architecture for Computer Vision 双边投影二维概率主成分分析的混合
9.Learning to Localize Little Landmarks 强大的光场进深估计嘈杂的场面与闭塞
10.When VLAD Met Hilbert 该数据集SYNTHIA：合成影像的城市场景的语义分割的大集合
11.Rotational Crossed-Slit Light Field 歧义帮助：分类异议的众包中的注解
12.Object Contour Detection With a Fully Convolutional Encoder-Decoder Network 对称验证码
13.Pedestrian Detection Inspired by Appearance Constancy and Shape Symmetry 子空间聚类随着先验通过稀疏二次约束二次规划
14.Self-Adaptive Matrix Completion for Heart Rate Estimation From Face Videos Under Realistic Conditions 深入了解在显着性：功能对比，语义和超越
15.Learning to Assign Orientations to Feature Points 单个图像对象建模地面BRDF和R表面学习
16.Learning From the Mistakes of Others: Matching Errors in Cross-Dataset Learning 当地背景为机箱的RGB-d显着对象检测
17.Scale-Aware Alignment of Hierarchical Image Segmentation 学习跨域的地标异构领域适应性
18.iLab-20M: A Large-Scale Controlled Object Dataset to Investigate Deep Learning 恢复6D物体姿态在人群中预测下一个最佳观
19.Temporal Action Localization in Untrimmed Videos via Multi-Stage CNNs 学习知识可转让的语义分割凭借深厚的卷积神经网络
20.Hierarchical Recurrent Neural Encoder for Video Representation With Application to Captioning 基于Oracle的有效集算法可伸缩弹力网子空间聚类
21.Temporal Multimodal Learning in Audiovisual Speech Recognition 语义过滤
22.DeepHand: Robust Hand Pose Estimation by Completing a Matrix Imputed With Deep Features 基于姿势的层次化方法在复杂的行动了解使用Actionlets和运动Poselets的字典
23.SVBRDF-Invariant Shape and Reflectance Estimation From Light-Field Cameras 针匹配：可靠的块匹配在高度不确定性
24.Convolutional Two-Stream Network Fusion for Video Action Recognition HyperNet：迈向精确的地区建议生成和联合检测对象
25.Semi-Supervised Vocabulary-Informed Learning 迪莱：强大的空间布局估计杂乱室内场景
26.A Consensus-Based Framework for Distributed Bundle Adjustment 调幅摄像机 - 动态场景光分离
27.DisturbLabel: Regularizing CNN on the Loss Layer 通过3D制导周期一致性学习的密集通讯
28.You Lead, We Exceed: Labor-Free Video Concept Learning by Jointly Exploiting Web Videos and Images 可扩展的稀疏子空间聚类通过正交匹配追踪
29.Kernel Sparse Subspace Clustering on Symmetric Positive Definite Manifolds 现场标识使用稀疏精度矩阵
30.Sketch Me That Shoe 立体3D跟踪由检测
31.Split and Match: Example-Based Adaptive Patch Sampling for Unsupervised Style Transfer Sample和Filter：通过有效的过滤非参数场景解析
32.3D Part-Based Sparse Tracker With Automatic Synchronization and Registration 在线学习贝叶斯分类树
33.HD Maps: Fine-Grained Road Segmentation by Parsing Ground and Aerial Images 利用边界盒注释为多标签识别对象
34.Visual7W: Grounded Question Answering in Images 建议流程
35.A Field Model for Repairing 3D Shapes 对于深度基于个人识别复发注意模型
36.Mining Discriminative Triplets of Patches for Fine-Grained Classification 除了F-编队：在自由站立交谈组确定社会参与从静态图像
37.Recovering the Missing Link: Predicting Class-Attribute Associations for Unsupervised Zero-Shot Learning 多线索零射门学习具有较强的监督
38.Highlight Detection With Pairwise Deep Ranking for First-Person Video Summarization 嘈杂的标签回收的阴影检测在陌生的域名
39.Eye Tracking for Everyone 大型室内空间的三维语义分析
40.When Naive Bayes Nearest Neighbors Meet Convolutional Neural Networks 跟踪商数会见稀疏：一种用于学习的低维图像表示
41.High-Quality Depth From Uncalibrated Small Motion Clip 卷帘门绝对姿态问题与已知的垂直方向
42.Learning Reconstruction-Based Remote Gaze Estimation 双源法三维姿态估计从单个图像
43.Reinforcement Learning for Visual Object Detection DeepFashion：强大的供电服装识别与检索利用丰富的注解
44.Recombinator Networks: Learning Coarse-To-Fine Feature Aggregation 高效粗到细PatchMatch大排量光流
45.Person Re-Identification by Multi-Channel Parts-Based CNN With Improved Triplet Loss Function 计算成像的VLBI图像重建
46.Geometry-Informed Material Recognition DeepFool：一个简单而准确的方法来欺骗深层神经网络
47.A Multi-Stream Bi-Directional Recurrent Neural Network for Fine-Grained Action Detection TGIF：一个新的数据集和动画GIF说明基准
48.Structure-From-Motion Revisited 自动化颈动脉内膜中层厚度视频信息解读卷积神经网络
49.Multiple Model Fitting as a Set Coverage Problem 单幅图像的摄像机标定随着透镜阵列增强现实
50.Harnessing Object and Scene Semantics for Large-Scale Video Understanding 适合像手套：快速和可靠的手形个性化

论文	概要
51.Efficient Coarse-To-Fine PatchMatch for Large Displacement Optical Flow 拔插头？预测如果计算机或人类应该图像分割
52.Computational Imaging for VLBI Image Reconstruction 多机校准从可见光和镜像核点
53.DeepFool: A Simple and Accurate Method to Fool Deep Neural Networks MCMC形状采样的图像分割非参数形状先验
54.TGIF: A New Dataset and Benchmark on Animated GIF Description 图片式转换使用卷积神经网络
55.Automating Carotid Intima-Media Thickness Video Interpretation With Convolutional Neural Networks 通过深协会典范驱动自上而下的显着性检测
56.Single Image Camera Calibration With Lenticular Arrays for Augmented Reality 量词辨析：费舍尔载体和深层神经网络
57.Fits Like a Glove: Rapid and Reliable Hand Shape Personalization 显着性指导意思 - 弱监督图像解析
58.Pull the Plug? Predicting If Computers or Humans Should Segment Images 深反射地图
59.Multicamera Calibration From Visible and Mirrored Epipoles 学习时间规律的视频序列
60.MCMC Shape Sampling for Image Segmentation With Nonparametric Shape Priors 喷布：动态选型的深层次网络
61.Image Style Transfer Using Convolutional Neural Networks 弱监督对象定位有了进步领域适应性
62.Exemplar-Driven Top-Down Saliency Detection via Deep Association 动态图像网络行动识别
63.Analyzing Classifiers: Fisher Vectors and Deep Neural Networks 精明的文本检测器：快速鲁棒场景文本定位算法
64.Saliency Guided Dictionary Learning for Weakly-Supervised Image Parsing 据悉准传递相似性检索从面孔的大集合
65.Deep Reflectance Maps 约束深陷转会地物学习及其应用
66.Learning Temporal Regularity in Video Sequences 强大的场景文本识别随着自动纠正
67.Blockout: Dynamic Model Selection for Hierarchical Deep Networks 通过概率分布预测端 - 端显着性绘图
68.Weakly Supervised Object Localization With Progressive Domain Adaptation 自然语言检索对象
69.Dynamic Image Networks for Action Recognition 非凸能源的下标的精确放松
70.Canny Text Detector: Fast and Robust Scene Text Localization Algorithm 稀疏编码和字典学习用线性动态系统
71.Learnt Quasi-Transitive Similarity for Retrieval From Large Collections of Faces 相似性学习具有空间约束的人重新鉴定
72.Constrained Deep Transfer Feature Learning and Its Applications 联合建模嵌入和翻译大桥视频和语言
73.Robust Scene Text Recognition With Automatic Rectification 自动三维人脸重构 - 从多张图片采用优质措施
74.End-To-End Saliency Mapping via Probability Distribution Prediction 科马尔：好等特点，以匹配对象边界
75.Natural Language Object Retrieval DeepStereo：学习预测的新认识世界的意象
76.Sublabel-Accurate Relaxation of Nonconvex Energies 什么稀疏光场编码揭示了场景结构
77.Sparse Coding and Dictionary Learning With Linear Dynamical Systems 亲和CNN：学习像素为中心的两两关系的Figure_Ground嵌入
78.Similarity Learning With Spatial Constraints for Person Re-Identification 深监督散列的快速图像检索
79.Jointly Modeling Embedding and Translation to Bridge Video and Language 汇总图像和文本量化相关组件
80.Automated 3D Face Reconstruction From Multiple Images Using Quality Measures 快速时间活动性提案的毛边影片人类行为的有效检测
81.CoMaL: Good Features to Match on Object Boundaries 检测和圆形基准点在极具挑战性的条件准确定位
82.DeepStereo: Learning to Predict New Views From the World’s Imagery TI-池：转型不变池地物学习的卷积神经网络
83.What Sparse Light Field Coding Reveals About Scene Structure 结构化特征的学习姿态估计
84.Affinity CNN: Learning Pixel-Centric Pairwise Relations for Figure_Ground Embedding 参数对象运动由模糊
85.Deep Supervised Hashing for Fast Image Retrieval 密集的通讯和Cosegmentation联合回收两幅图像
86.Aggregating Image and Text Quantized Correlated Components 全局最优刚性强度基于注册：快速傅立叶域方法
87.Fast Temporal Activity Proposals for Efficient Detection of Human Actions in Untrimmed Videos 范式建筑广义人类形象感知模型通过数据融合
88.Detection and Accurate Localization of Circular Fiducials Under Highly Challenging Conditions 三维人体的直接预测姿态从运动补偿序列
89.TI-Pooling: Transformation-Invariant Pooling for Feature Learning in Convolutional Neural Networks 深典型时间规整
90.Structured Feature Learning for Pose Estimation 功能面面观：GroupWise的密集使用通讯功能图
91.Parametric Object Motion From Blur 立体匹配随着彩色和黑白相机在低光照条件下
92.Joint Recovery of Dense Correspondence and Cosegmentation in Two Images 实时单幅图像和视频超分辨率采用高效的子像素卷积神经网络
93.Globally Optimal Rigid Intensity Based Registration: A Fast Fourier Domain Approach 利用谱空间相关性的编码的高光谱图像复原
94.A Paradigm for Building Generalized Models of Human Image Perception Through Data Fusion 实时深度精制的镜面物体
95.Direct Prediction of 3D Body Poses From Motion Compensated Sequences 多视角深度网络的跨浏览分类
96.Deep Canonical Time Warping 潜曲面嵌入了零镜头分类
97.Functional Faces: Groupwise Dense Correspondence Using Functional Maps 认识情绪从抽象绘画使用非线性矩阵完成
98.Stereo Matching With Color and Monochrome Cameras in Low-Light Conditions 经常注意网络的显着性检测
99.Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network 据悉二进制光谱形状描述的三维形状对应
100.Exploiting Spectral-Spatial Correlation for Coded Hyperspectral Image Restoration 相机校准从行人的周期运动

论文	概要
101.Learning to Select Pre-Trained Deep Representations With Bayesian Evidence Framework 学习重量不确定性随机梯度MCMC的形状分类
102.Learning Deep Feature Representations With Domain Guided Dropout for Person Re-Identification 弱回溯ScSPM图像分类监督自上而下的显着性
103.Efficient Point Process Inference for Large-Scale Object Detection 街景的语义标注实例通过三维到二维标签转移
104.Training Region-Based Object Detectors With Online Hard Example Mining 单图像盲去模糊算法的比较研究
105.Accurate Image Super-Resolution Using Very Deep Convolutional Networks 多式联运自发情感语料库人的行为分析
106.A Holistic Approach to Cross-Channel Image Noise Modeling and Its Application to Image Denoising 规律驱动的门面匹配空中和街景视图之间
107.Recurrently Target-Attending Tracking 学习共同生成对象的建议了深刻的结构化网络
108.A Weighted Variational Model for Simultaneous Reflectance and Illumination Estimation 室内场景的在线重构 - 从RGB-d流
109.SPDA-CNN: Unifying Semantic Part Detection and Abstraction for Fine-Grained Recognition 递归复发篮网注意力建模OCR在狂野
110.Region Ranking SVM for Image Classification 判别属性和可视化表示的无监督学习
111.Temporal Action Localization With Pyramid of Score Distribution Features 认识到汽车Fluents从视频
112.Convolutional Pose Machines 改进的海明距离搜索使用可变长度子串
113.Joint Multiview Segmentation and Localization of RGB-D Images Using Depth-Induced Silhouette Consistency 自主驾驶单眼立体物检测
114.Tensor Robust Principal Component Analysis: Exact Recovery of Corrupted Low-Rank Tensors via Convex Optimization 同时聚类和选型张量相契
115.Structural-RNN: Deep Learning on Spatio-Temporal Graphs 在此之前，可压缩性结构与运动
116.Staple: Complementary Learners for Real-Time Tracking 基于背景重构为三维视频查看合成一个孔洞填充方法
117.Deep Residual Learning for Image Recognition 学习深特色功能判别本地化
118.Pairwise Matching Through Max-Weight Bipartite Belief Propagation NetVLAD：CNN架构弱监督地方识别
119.Information-Driven Adaptive Structured-Light Scanners 语义对象分析随着地方 - 全球长短期记忆
120.Learning Local Image Descriptors With Deep Siamese and Triplet Convolutional Networks by Minimising Global Loss Functions 事件特异性图像重要
121.Efficient Deep Learning for Stereo Matching 矿业3D钥匙姿势基序行动识别
122.Primary Object Segmentation in Videos via Alternate Convex Optimization of Foreground and Background Distributions 上下文编码器：地物学习用图像修复
123.A Probabilistic Framework for Color-Based Point Set Registration 无人机传感器融合在潜动态条件随机场的冠状面估计
124.Deep Structured Scene Parsing by Learning With Image Descriptions 高效的大规模相似性搜索基于矩阵分解
125.Mirror Surface Reconstruction Under an Uncalibrated Camera 闭塞，自由面阵营：深回归网络结合德舞弊自动编码
126.Deep Gaussian Conditional Random Field Network: A Model-Based Deep Network for Discriminative Denoising 切片卷积神经网络的人群视频了解
127.Consensus of Non-Rigid Reconstructions 除了本地搜索：跟踪对象到处都具有实例，具体建议<