（十五：2020.08.28）CVPR 2013 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200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.All About VLAD 融合离焦深度和立体有编码孔径
2.Lost! Leveraging the Crowd for Probabilistic Visual Self-Localization 量词与同时主动学习通过相对反馈属性
3.Looking Beyond the Image: Unsupervised Learning for Object Saliency and Detection 灰色的5个牙色的快速和可靠的相机姿态估计
4.Bringing Semantics into Focus Using Visual Abstraction 在自然光照和非朗伯反射分析双线性外观子空间构建模型图片辐照
5.Augmenting CRFs with Boltzmann Machine Shape Priors for Image Labeling 核心零空间方法新颖检测
6.Sparse Subspace Denoising for Image Manifolds SCALPEL：分段瀑布与本地化先验高效学习
7.Dense Variational Reconstruction of Non-rigid Surfaces from Monocular Video 通过形态学语境肿瘤组织学分类
8.A Fully-Connected Layered Model of Foreground and Background Flow 基于图形优化与Tubularity马尔科夫树的3D血管分割
9.Blur Processing Using Double Discrete Wavelet Transform 通过多源视频属性的复杂事件检测
10.Spatio-temporal Depth Cuboid Similarity Feature for Activity Recognition Using Depth Camera 通过学习属性添加的未标记样本来分类
11.Poselet Key-Framing: A Model for Human Activity Recognition 概率弹性匹配的姿态变人脸验证
12.Weakly Supervised Learning for Attribute Localization in Outdoor Scenes 双曲调和映射约束脑表面报名
13.Bilinear Programming for Human Activity Recognition with Unknown MRF Graphs 人体姿势估计中的身体部位相关联的回归量
14.Unsupervised Joint Object Discovery and Segmentation in Internet Images 第一人称动作识别：他们在做什么给我？
15.What Object Motion Reveals about Shape with Unknown BRDF and Lighting 自上而下的分割非刚性可视化对象稀疏流形的应用导数，基于搜索
16.Manhattan Scene Understanding via XSlit Imaging 非刚性表面的高精度和稳健的注册使用分层统计形状模型
17.A Theory of Refractive Photo-Light-Path Triangulation 贝叶斯语法学习的逆过程建模
18.Learning SURF Cascade for Fast and Accurate Object Detection 经由图像特异性和Tag-特定线性稀疏重建图像标记完成
19.Class Generative Models Based on Feature Regression for Pose Estimation of Object Categories 稀疏的人脸识别在国防
20.Multipath Sparse Coding Using Hierarchical Matching Pursuit 在视频半监督功能层次的目标检测学习
21.HDR Deghosting: How to Deal with Saturation? 基于算法求解超大型拼图的遗传
22.Weakly-Supervised Dual Clustering for Image Semantic Segmentation 计算为大运动插值微分同胚的路径
23.In Defense of 3D-Label Stereo 快速移动物体检测与熵驱动的评估
24.Light Field Distortion Feature for Transparent Object Recognition 视频编辑与时间，空间和外观的一致性
25.Relative Hidden Markov Models for Evaluating Motion Skill 学习目标识别零件模型的集合
26.Depth Super Resolution by Rigid Body Self-Similarity in 3D 哈利·波特的活点地图：定位和跟踪多个人的兴趣由非负离散
27.HON4D: Histogram of Oriented 4D Normals for Activity Recognition from Depth Sequences 3D视觉空间关系学：从单个图像识别人的相互作用在3D
28.Diffusion Processes for Retrieval Revisited 这是毫不客气地点：不确定属性描述人物
29.A Principled Deep Random Field Model for Image Segmentation 一个凸正规化为彩色图像恢复减少伪色
30.Efficient Computation of Shortest Path-Concavity for 3D Meshes 在依赖关系图人类计算效率的回归姿态估计
31.Prostate Segmentation in CT Images via Spatial-Constrained Transductive Lasso 约束聚类及其面临聚类在视频中的应用
32.Binary Code Ranking with Weighted Hamming Distance 高阶函的一般类辅助割伤
33.Joint Geodesic Upsampling of Depth Images 推进二进制关键点描述符
34.Towards Contactless, Low-Cost and Accurate 3D Fingerprint Identification 快速卷积稀疏编码
35.Action Recognition by Hierarchical Sequence Summarization 现代推理技术的离散能量最小化问题的比较研究
36.Event Recognition in Videos by Learning from Heterogeneous Web Sources 非参数滤波几何细节提取和材料表现
37.Robust Feature Matching with Alternate Hough and Inverted Hough Transforms 什么是一个名称？第一名称作为面部属性
38.Procrustean Normal Distribution for Non-rigid Structure from Motion 卷闸相机校准
39.Discriminative Color Descriptors 交替决策森林
40.Separating Signal from Noise Using Patch Recurrence across Scales 多代理事件检测：本地化和角色分配
41.FrameBreak: Dramatic Image Extrapolation by Guided Shift-Maps AS-投影-AS-可能的图像与移动DLT拼接
42.Discriminative Segment Annotation in Weakly Labeled Video 校准光度立体的整体反射对称分析
43.Dense Object Reconstruction with Semantic Priors 自下而上分段自上而下检测
44.Discriminative Non-blind Deblurring 人们戴着偏光眼镜的视频增强：变黑逆转减灾思考
45.Submodular Salient Region Detection 径向畸变自校准
46.3D R Transform on Spatio-temporal Interest Points for Action Recognition 检测和对齐面对由图像检索
47.Discriminative Re-ranking of Diverse Segmentations 哈希位选择：统一的解决方案在哈希选择问题
48.SWIGS: A Swift Guided Sampling Method 镜面重建从单个图像
49.Learning Discriminative Illumination and Filters for Raw Material Classification with Optimal Projections of Bidirectional Texture Functions 在高动态场景合奏视频对象剪切
50.Finding Things: Image Parsing with Regions and Per-Exemplar Detectors 可压缩运动领域

论文	概要
51.Fusing Depth from Defocus and Stereo with Coded Apertures 转移稀疏编码的鲁棒图像表示
52.Simultaneous Active Learning of Classifiers & Attributes via Relative Feedback 朝姿态强大的人脸识别
53.Five Shades of Grey for Fast and Reliable Camera Pose Estimation 从运动利用结构学习判别码本可扩展地标分类
54.Analytic Bilinear Appearance Subspace Construction for Modeling Image Irradiance under Natural Illumination and Non-Lambertian Reflectance 旋转，缩放和变形不变散射的纹理识别
55.Kernel Null Space Methods for Novelty Detection 基于图形的判别学习的位置识别
56.SCALPEL: Segmentation Cascades with Localized Priors and Efficient Learning CLAM：耦合的定位和地图与高效异常处理
57.Classification of Tumor Histology via Morphometric Context 跟踪人们和他们的对象
58.Graph-Based Optimization with Tubularity Markov Tree for 3D Vessel Segmentation 从部分对应部分发现
59.Complex Event Detection via Multi-source Video Attributes 与多阶语境共生演化检测
60.Adding Unlabeled Samples to Categories by Learned Attributes 三角表面网格的对应，减少非刚性注册
61.Probabilistic Elastic Matching for Pose Variant Face Verification 从局部逼近于全球编码：申请图像分类
62.Hyperbolic Harmonic Mapping for Constrained Brain Surface Registration 光照估计算法双层稀疏编码
63.Human Pose Estimation Using Body Parts Dependent Joint Regressors 学习多非线性子空间使用K-RBMS
64.First-Person Activity Recognition: What Are They Doing to Me? 变形图匹配
65.Top-Down Segmentation of Non-rigid Visual Objects Using Derivative-Based Search on Sparse Manifolds 核学习了千姿百态的外在分类
66.Accurate and Robust Registration of Nonrigid Surface Using Hierarchical Statistical Shape Model 典范基础的脸解析
67.Bayesian Grammar Learning for Inverse Procedural Modeling 活动轮廓与组相似度
68.Image Tag Completion via Image-Specific and Tag-Specific Linear Sparse Reconstructions 非参数框架文件放气经过去除
69.In Defense of Sparsity Based Face Recognition 噪声处理单的图像去模糊使用方向滤波器
70.Semi-supervised Learning of Feature Hierarchies for Object Detection in a Video 年龄和人群密度估计累积属性空间
71.A Genetic Algorithm-Based Solver for Very Large Jigsaw Puzzles 多目标跟踪拉格朗日松弛闽费用网络流
72.Computing Diffeomorphic Paths for Large Motion Interpolation 快速多部分基于对象的检测使用KD-蕨类植物
73.Fast Object Detection with Entropy-Driven Evaluation 学习的结构预测近似使用次梯度下降与工作集
74.Video Editing with Temporal, Spatial and Appearance Consistency 结构化面幻觉
75.Learning Collections of Part Models for Object Recognition 多属性查询：合并或不合并？
76.Harry Potter’s Marauder’s Map: Localizing and Tracking Multiple Persons-of-Interest by Nonnegative Discretization 张量为基础的高阶语义关系转移语义场景分割
77.3D Visual Proxemics: Recognizing Human Interactions in 3D from a Single Image 共同对齐和分割多个Web照片流的集体照片故事情节的推理
78.It’s Not Polite to Point: Describing People with Uncertain Attributes RGB-d图像的基于渐变形状细化
79.A Convex Regularize for Reducing Color Artifact in Color Image Recovery 噗：第一部分为基础的一对，一个特点细粒度分类，人脸验证和属性估计
80.Computationally Efficient Regression on a Dependency Graph for Human Pose Estimation 从部分可观测的视频识别人类活动
81.Constrained Clustering and Its Application to Face Clustering in Videos 探索弱镇定动作特征提取
82.Auxiliary Cuts for General Classes of Higher Order Functionals 故事驱动的总结视频自我中心
83.Boosting Binary Keypoint Descriptors 细粒度众包细粒度识别
84.Fast Convolutional Sparse Coding 流形上感应散列
85.A Comparative Study of Modern Inference Techniques for Discrete Energy Minimization Problems 从单点的多观察发现一个平面镜系统的结构
86.Non-parametric Filtering for Geometric Detail Extraction and Material Representation 事件检索与循环时间编码的视频大集合
87.What’s in a Name? First Names as Facial Attributes 通过连续的虚拟路径交叉视角行为识别
88.Rolling Shutter Camera Calibration 通过基于表示平均序列稀疏分类人脸识别的电影预告片
89.Alternating Decision Forests 图像抠图与本地及非局部平滑先验
90.Multi-agent Event Detection: Localization and Role Assignment 重建使用整数规划糊涂的曲线结构
91.As-Projective-As-Possible Image Stitching with Moving DLT 重建气体流速使用光路逼近
92.Calibrating Photometric Stereo by Holistic Reflectance Symmetry Analysis 概率标签树的高效大型图像分类
93.Bottom-Up Segmentation for Top-Down Detection 通过关联含糊标记图像学习
94.Video Enhancement of People Wearing Polarized Glasses: Darkening Reversal and Reflection Reduction 从N到N + 1：多类传输增量学习
95.Radial Distortion Self-Calibration **Block和集团正则稀疏建模意思 - **
96.Detecting and Aligning Faces by Image Retrieval 稀疏量化的补丁说明
97.Hash Bit Selection: A Unified Solution for Selection Problems in Hashing 基于模板的等距变形三维重建与基于采样焦距自校准
98.Mirror Surface Reconstruction from a Single Image 所有关于VLAD
99.Ensemble Video Object Cut in Highly Dynamic Scenes 丢失！凭借人群的概率视觉中的自身定位
100.Compressible Motion Fields 在展望图片：无监督学习的对象显着和检测

论文	概要
101.Wide-Baseline Hair Capture Using Strand-Based Refinement 把语义成焦点使用Visual抽象
102.Efficient 2D-to-3D Correspondence Filtering for Scalable 3D Object Recognition 增强控释肥与玻尔兹曼机外形先验的图像标签
103.Joint Spectral Correspondence for Disparate Image Matching 稀疏子空间去噪的图像流形
104.Context-Aware Modeling and Recognition of Activities in Video 非刚性表面的密集重建变单目视频
105.Studying Relationships between Human Gaze, Description, and Computer Vision 前台和后台流程的全连接分层模型
106.Compressed Hashing 模糊处理采用双离散小波变换
107.Subcategory-Aware Object Classification 时空深度长方体相似特征的动作识别使用深度相机
108.Semi-supervised Domain Adaptation with Instance Constraints Poselet关键成帧：一种人类活动识别模型
109.Visual Tracking via Locality Sensitive Histograms 弱监督学习中的室外场景属性本地化
110.Exploring Compositional High Order Pattern Potentials for Structured Output Learning 双线性规划的人类活动识别未知MRF图表
111.Fast Image Super-Resolution Based on In-Place Example Regression 无监督的联合对象发现并分割在互联网图片
112.An Iterated L1 Algorithm for Non-smooth Non-convex Optimization in Computer Vision 什么物体的运动揭示了未知BRDF和照明形状
113.Expanded Parts Model for Human Attribute and Action Recognition in Still Images 曼哈顿场景通过XSlit成像了解
114.Optimized Pedestrian Detection for Multiple and Occluded People 折射光电光路三角理论
115.Multi-image Blind Deblurring Using a Coupled Adaptive Sparse Prior 学习SURF级联实现快速准确的目标检测
116.Learning to Detect Partially Overlapping Instances 基于特征回归的对象类别的姿态估计类生成模型
117.Principal Observation Ray Calibration for Tiled-Lens-Array Integral Imaging Display 多径稀疏编码采用分层匹配追踪
118.Large-Scale Video Summarization Using Web-Image Priors HDR去鬼影：如何用饱和应对？
119.Optimized Product Quantization for Approximate Nearest Neighbor Search 弱监督的双重聚类的图像语义分割
120.Detecting and Naming Actors in Movies Using Generative Appearance Models 三维立体的标签在国防
121.A Linear Approach to Matching Cuboids in RGBD Images 光场畸变特性为透明物体识别
122.The SVM-Minus Similarity Score for Video Face Recognition 相对隐马尔可夫模型的评估运动技巧
123.A Minimum Error Vanishing Point Detection Approach for Uncalibrated Monocular Images of Man-Made Environments 深超解像刚体自相似3D
124.Learning Structured Low-Rank Representations for Image Classification HON4D：从深度序列面向4D法线的行为识别的直方图
125.Incorporating User Interaction and Topological Constraints within Contour Completion via Discrete Calculus 扩散过程检索再访
126.Joint 3D Scene Reconstruction and Class Segmentation 有原则的深随机场模型的图像分割
127.Monocular Template-Based 3D Reconstruction of Extensible Surfaces with Local Linear Elasticity 最短路径凹性的高效计算的3D网格
128.Single Image Calibration of Multi-axial Imaging Systems 通过空间受限的直推拉索前列腺分割的CT图像
129.Deformable Spatial Pyramid Matching for Fast Dense Correspondences 二进制代码加权海明距离排名
130.A New Model and Simple Algorithms for Multi-label Mumford-Shah Problems 深度图像的联合短程上采样
131.Query Adaptive Similarity for Large Scale Object Retrieval 朝接触，低成本和精确的3D指纹识别
132.Maximum Cohesive Grid of Superpixels for Fast Object Localization 动作识别的等级序列综述
133.Adaptive Active Learning for Image Classification 事件识别在影片通过学习从异构网络资源
134.Optical Flow Estimation Using Laplacian Mesh Energy 强大的功能匹配与备用霍夫和倒霍夫变换
135.Non-rigid Structure from Motion with Diffusion Maps Prior 削足适履正态分布从运动非刚性结构
136.Multi-view Photometric Stereo with Spatially Varying Isotropic Materials 判别颜色描述符
137.Multi-target Tracking by Rank-1 Tensor Approximation 从跨尺度的噪声使用补丁复发分离信号
138.Improving an Object Detector and Extracting Regions Using Superpixels FrameBreak：通过引导按住Shift键地图生动形象外推
139.Information Consensus for Distributed Multi-target Tracking 在弱标记视频判别段注释
140.Dictionary Learning from Ambiguously Labeled Data 与语义先验致密的天体重建
141.Incorporating Structural Alternatives and Sharing into Hierarchy for Multiclass Object Recognition and Detection 判别非盲去模糊算法
142.Fast Patch-Based Denoising Using Approximated Patch Geodesic Paths 子模的显着区域检测
143.Globally Consistent Multi-label Assignment on the Ray Space of 4D Light Fields 3D [R变换的时空兴趣点行动识别
144.SLAM++: Simultaneous Localisation and Mapping at the Level of Objects 多元分割的判别重新排名
145.Winding Number for Region-Boundary Consistent Salient Contour Extraction SWIGS：迅速指导抽样方法
146.Ensemble Learning for Confidence Measures in Stereo Vision 学习判别照明与双向纹理函数的最优预测过滤器原料分类
147.Templateless Quasi-rigid Shape Modeling with Implicit Loop-Closure 寻找物品：图像解析与地区和Per-的Exemplar探测器
148.Articulated and Restricted Motion Subspaces and Their Signatures 宽基线头发捕捉使用链为基础的细化
149.Selective Transfer Machine for Personalized Facial Action Unit Detection 高效的2D到3D对应滤波可扩展的三维物体识别
150.Exploring Implicit Image Statistics for Visual Representativeness Modeling 联合谱通讯将完全不同的图像匹配

论文	概要
151.Transfer Sparse Coding for Robust Image Representation 环境感知建模和视频活动的识别
152.Towards Pose Robust Face Recognition 人的目光，描述和计算机视觉之间的关系研究
153.Leveraging Structure from Motion to Learn Discriminative Codebooks for Scalable Landmark Classification 压缩散列
154.Rotation, Scaling and Deformation Invariant Scattering for Texture Discrimination 子目录知晓对象分类
155.Graph-Based Discriminative Learning for Location Recognition 半监督领域适应性与实例约束
156.CLAM: Coupled Localization and Mapping with Efficient Outlier Handling 通过局部敏感直方图视觉跟踪
157.Tracking People and Their Objects 探索组成高阶模式潜力结构性输出学习
158.Part Discovery from Partial Correspondence 快速图像超分辨率基础上，代替实施回归
159.Detection Evolution with Multi-order Contextual Co-occurrence 的迭代L1算法非光滑计算机视觉非凸优化
160.Correspondence-Less Non-rigid Registration of Triangular Surface Meshes 扩展配件型号为人类属性和行为识别静止图像
161.From Local Similarity to Global Coding: An Application to Image Classification 优化行人检测的多和闭塞的人
162.Illumination Estimation Based on Bilayer Sparse Coding 多图像去模糊盲用偶联的自适应稀疏之前
163.Learning Multiple Non-linear Sub-spaces Using K-RBMs 学习检测部分重叠的实例
164.Deformable Graph Matching 主要观察射线刻度的瓷砖，透镜阵列型积分成像显示
165.Kernel Learning for Extrinsic Classification of Manifold Features 大型视频概述使用Web-先验图像
166.Exemplar-Based Face Parsing 优化的产品为量化近似最近邻搜索
167.Active Contours with Group Similarity 检测和电影演员的命名使用生成外观模型
168.A Non-parametric Framework for Document Bleed-through Removal 一个线性方法来匹配立方体在RGBD图片
169.Handling Noise in Single Image Deblurring Using Directional Filters 该SVM-减相似度得分视频人脸识别
170.Cumulative Attribute Space for Age and Crowd Density Estimation 误差最小的消失点检测方法的人工环境的无标定单眼图像
171.Multi-target Tracking by Lagrangian Relaxation to Min-cost Network Flow 学习的图像分类结构的低品质交涉
172.Fast Multiple-Part Based Object Detection Using KD-Ferns 通过离散积分合并轮廓内竣工，用户交互和拓扑约束
173.Learning for Structured Prediction Using Approximate Subgradient Descent with Working Sets 联合3D现场重建类细分
174.Structured Face Hallucination 扩展表面的单眼基于模板的三维重建与局部线性弹性
175.Multi-attribute Queries: To Merge or Not to Merge? 多轴成像系统的单张图像校准
176.Tensor-Based High-Order Semantic Relation Transfer for Semantic Scene Segmentation 变形空间金字塔匹配的快速密集的对应
177.Jointly Aligning and Segmenting Multiple Web Photo Streams for the Inference of Collective Photo Storylines 一种新的模式和简单的算法的多标签芒福德 - 沙阿问题
178.Shading-Based Shape Refinement of RGB-D Images 查询自适应相似的大型对象检索
179.POOF: Part-Based One-vs.-One Features for Fine-Grained Categorization, Face Verification, and Attribute Estimation 超级像素的最大粘结电网对快速目标定位
180.Recognize Human Activities from Partially Observed Videos 自适应主动学习的图像分类
181.Exploring Weak Stabilization for Motion Feature Extraction 光流估计使用拉普拉斯能源网
182.Story-Driven Summarization for Egocentric Video 从运动非刚性结构与扩散地图前
183.Fine-Grained Crowdsourcing for Fine-Grained Recognition 多视角光度立体与空间变异性各向同性材料
184.Inductive Hashing on Manifolds 多目标跟踪由秩1张量逼近
185.Discovering the Structure of a Planar Mirror System from Multiple Observations of a Single Point 改进的物体检测并提取地区使用超级像素
186.Event Retrieval in Large Video Collections with Circulant Temporal Encoding 信息共识分布式多目标跟踪
187.Cross-View Action Recognition via a Continuous Virtual Path 字典学习从模棱两可的标签数据
188.Face Recognition in Movie Trailers via Mean Sequence Sparse Representation-Based Classification 结合结构方案，并分享到层次结构多类目标识别定位
189.Image Matting with Local and Nonlocal Smooth Priors 快速补丁为基础的去噪近似补丁短程路径
190.Reconstructing Loopy Curvilinear Structures Using Integer Programming 在4D光场的射线空间全球一致的多标签分配
191.Reconstructing Gas Flows Using Light-Path Approximation SLAM ++：同步定位和映射在对象的水平
192.Probabilistic Label Trees for Efficient Large Scale Image Classification 绕线号区，边界一致凸轮廓提取
193.Learning by Associating Ambiguously Labeled Images 集成学习在立体视觉置信度
194.From N to N+1: Multiclass Transfer Incremental Learning Templateless准刚性形状建模与隐环路闭合
195.Block and Group Regularized Sparse Modeling for Dictionary Learning 铰接式和受限制的运动子空间和他们的签名
196.Sparse Quantization for Patch Description 对于个性化的面部动作单位检测选择性转移机
197.Template-Based Isometric Deformable 3D Reconstruction with Sampling-Based Focal Length Self-Calibration 探索视觉代表性建模隐形图像统计