（十四：2020.08.28）CVPR 2014 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500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.Efficient Squared Curvature 分段平面和紧凑的布局规划重建从图片
2.Smooth Representation Clustering 10规范基于字典的学习与全局收敛近端方法
3.Towards Multi-view and Partially-Occluded Face Alignment 一个学习型到秩逼近的图像色彩增强
4.Co-localization in Real-World Images 相似性比较交互式细粒度分类
5.Joint Depth Estimation and Camera Shake Removal from Single Blurry Image 空时可组合的人类活动的判别分层建模
6.Subspace Tracking under Dynamic Dimensionality for Online Background Subtraction 基于模型的实时关节的对象姿势探测和跟踪与变刚度约束
7.The Language of Actions: Recovering the Syntax and Semantics of Goal-Directed Human Activities 快速，准确的图像匹配与级联散列的三维重建
8.Facial Expression Recognition via a Boosted Deep Belief Network 无监督的一类学习的自动去除异常值
9.Iterative Multilevel MRF Leveraging Context and Voxel Information for Brain Tumour Segmentation in MRI 光度捆绑调整高密度多视图三维建模
10.Discriminative Ferns Ensemble for Hand Pose Recognition Tracklet协会在线的目标，具体的度量学习
11.Inferring Unseen Views of People 解析与节段性文法操作的影片
12.Geometric Generative Gaze Estimation (G3E) for Remote RGB-D Cameras DeepPose：人类通过深层神经网络姿态估计
13.Unsupervised Multi-Class Joint Image Segmentation 大排量光流快速边缘保持PatchMatch
14.Symmetry-Aware Nonrigid Matching of Incomplete 3D Surfaces 自适应颜色属性的实时视觉跟踪
15.Hierarchical Feature Hashing for Fast Dimensionality Reduction 主动外观模型的实例加权迁移学习
16.A Multigraph Representation for Improved Unsupervised_Semi-supervised Learning of Human Actions 单查看3D场景解析由属性文法
17.Reconstructing Evolving Tree Structures in Time Lapse Sequences 实证最小贝叶斯风险预测：如何提取从只有三个参数的更多视觉模型多打少性能％
18.Bayes Merging of Multiple Vocabularies for Scalable Image Retrieval 使用弱优化平均精密教师数据
19.Topic Modeling of Multimodal Data: An Autoregressive Approach 快速，准确：ADMM为基础的判别形分割与糊涂的零件模型
20.Learning to Detect Ground Control Points for Improving the Accuracy of Stereo Matching 基于质量的多式联运分类采用树形结构稀疏
21.On Projective Reconstruction In Arbitrary Dimensions 二阶体型优化的视觉几何反问题
22.Multipoint Filtering with Local Polynomial Approximation and Range Guidance 使用相对平滑单张图像分层
23.Active Sampling for Subjective Image Quality Assessment 高效的特征提取，编码和分类行动识别
24.Geometric Urban Geo-Localization 脸配准在3000 FPS通过回归局部二元特点
25.Decomposable Nonlocal Tensor Dictionary Learning for Multispectral Image Denoising 的原因，运动轨迹的影响分析建模操作
26.Is Rotation a Nuisance in Shape Recognition? 除了比较像对：对相关属性进行逐集合主动学习
27.Separation of Line Drawings Based on Split Faces for 3D Object Reconstruction 视频分类使用语义概念共现
28.3D Reconstruction from Accidental Motion 对于视频对象分割基于区域的粒子滤波
29.An Online Learned Elementary Grouping Model for Multi-target Tracking 布雷格曼背离了无穷维协方差矩阵
30.Novel Methods for Multilinear Data Completion and De-noising Based on Tensor-SVD 使用形变场模型下，监管不力本地化面和脸部点
31.Deformable Object Matching via Deformation Decomposition based 2D Label MRF CID：联合图像去噪在空域和频域使用网页图片
32.Region-based Discriminative Feature Pooling for Scene Text Recognition 复杂的行为识别在体育和监控视频使用格兰杰约束DBN（GCDBN）
33.Hash-SVM: Scalable Kernel Machines for Large-Scale Visual Classification 随机拉普拉斯功能对于半群内核的直方图地图
34.Deep Fisher Kernels - End to End Learning of the Fisher Kernel GMM Parameters 快速监督散列与决策树的高维数据
35.Shape-Preserving Half-Projective Warps for Image Stitching 学习的最佳种子基于扩散的显着对象检测
36.Object Classification with Adaptable Regions 本地重新调整的高分辨率三维重建
37.Ask the Image: Supervised Pooling to Preserve Feature Locality 统计分析框架搜索空间减少：根据序列最优立体声采样
38.Parsing Occluded People 学习的重要空间汇集地区的场景分类
39.Fast MRF Optimization with Application to Depth Reconstruction 随机马克斯保证金组合物视觉识别
40.Semi-Supervised Coupled Dictionary Learning for Person Re-identification 收缩的字段的有效图像复原
41.Pulling Things out of Perspective 使用稀疏低维流形和坚定信念网络非刚性分割
42.Visual Persuasion: Inferring Communicative Intents of Images 在线目标跟踪，学习和分析含有和-或图形
43.Joint Motion Segmentation and Background Estimation in Dynamic Scenes 深度和骨骼相关的动作识别，而联机残疾人专用RGB-d相机
44.One Millisecond Face Alignment with an Ensemble of Regression Trees 利用分层参数网络的骨架关节基础的行动分割与识别
45.MAP Visibility Estimation for Large-Scale Dynamic 3D Reconstruction 场景无关的集团剖析人群中
46.Curvilinear Structure Tracking by Low Rank Tensor Approximation with Model Propagation 方位金字塔匹配识别的室内场景
47.Improving Semantic Concept Detection through the Dictionary of Visually-distinct Elements 多源深学习的人体姿势估计
48.Multi-Shot Imaging: Joint Alignment, Deblurring and Resolution-Enhancement 多尺度中心线检测通过学习尺度空间距离变换
49.A Hierarchical Probabilistic Model for Facial Feature Detection 发现：发现的重要段视频的分类活动，并介绍
50.Super Normal Vector for Activity Recognition Using Depth Sequences 三维形状和结构光传输间接外观

论文	概要
51.Piecewise Planar and Compact Floorplan Reconstruction from Images 多折MIL培训弱监督的目标定位
52.l0 Norm Based Dictionary Learning by Proximal Methods with Global Convergence 征图像的测光
53.A Learning-to-Rank Approach for Image Color Enhancement 堆叠逐行自动编码器（SPAE）的人脸识别跨体式
54.Similarity Comparisons for Interactive Fine-Grained Categorization 更好的跟踪功能通过子空间约束
55.Discriminative Hierarchical Modeling of Spatio-Temporally Composable Human Activities 基于标本安CRF的多实例对象分割
56.Real-time Model-based Articulated Object Pose Detection and Tracking with Variable Rigidity Constraints 分析合成：3D物体识别的对象重建
57.Fast and Accurate Image Matching with Cascade Hashing for 3D Reconstruction Fantope正规化的度量学习
58.Unsupervised One-Class Learning for Automatic Outlier Removal 卷积神经网络的无参考图像质量评价
59.Photometric Bundle Adjustment for Dense Multi-View 3D Modeling 密集语义图像分割对象和属性
60.Tracklet Association with Online Target-Specific Metric Learning BING：二值化的赋范渐变为对象性估计在300fps
61.Parsing Videos of Actions with Segmental Grammars 用于接种的图像分割拉普拉斯坐标
62.DeepPose: Human Pose Estimation via Deep Neural Networks 特征的独立行动去渍没有人的本土化，分割或逐帧跟踪
63.Fast Edge-Preserving PatchMatch for Large Displacement Optical Flow DAISY过滤流量：广义离散方法，以密集的对应
64.Adaptive Color Attributes for Real-Time Visual Tracking 预测用户烦恼使用Visual属性
65.Instance-weighted Transfer Learning of Active Appearance Models 从一袋视觉字图像重建
66.Single-View 3D Scene Parsing by Attributed Grammar Actionness莱迪思条件序号随机域排名
67.Empirical Minimum Bayes Risk Prediction: How to Extract an Extra Few % Performance from Vision Models with Just Three More Parameters 人类行为识别跨数据集的前景加权直方图分解
68.Optimizing Average Precision using Weakly Supervised Data 基于图像的合成和再合成3D模型的指导下观
69.Fast and Exact: ADMM-Based Discriminative Shape Segmentation with Loopy Part Models 下恢复一般未知光照使用遮阳和粗多视点立体表面细节
70.Quality-based Multimodal Classification using Tree-Structured Sparsity 广义非凸非光滑低阶最小化
71.Second-Order Shape Optimization for Geometric Inverse Problems in Vision 信心额定多重背景增压物体检测
72.Single Image Layer Separation using Relative Smoothness 学习可扩展的判别字典与样品关联
73.Efficient Feature Extraction, Encoding and Classification for Action Recognition 谁你看我像？通过门控自动编码确定亲子相似性
74.Face Alignment at 3000 FPS via Regressing Local Binary Features 对于Pose-和表达，强大的人脸特征点定位本地外观的非参数建模语境
75.A Cause and Effect Analysis of Motion Trajectories for Modeling Actions 费舍尔和VLAD与FLAIR
76.Beyond Comparing Image Pairs: Setwise Active Learning for Relative Attributes 在结构化稀疏重建预处理的加速迭代重加权最小二乘
77.Video Classification using Semantic Concept Co-occurrences 从概率模型最优决策：在交叉点过联盟案例
78.Region-based Particle Filter for Video Object Segmentation 数据驱动的花瓣造型与植物学先验
79.Bregman Divergences for Infinite Dimensional Covariance Matrices 深度学习的人脸表示从预测万类
80.Using a Deformation Field Model for Localizing Faces and Facial Points under Weak Supervision 强大的子空间分割与块对角前
81.CID: Combined Image Denoising in Spatial and Frequency Domains Using Web Images 眼看着时间的箭
82.Complex Activity Recognition using Granger Constrained DBN (GCDBN) in Sports and Surveillance Video 跨视图操作模型，学习和识别
83.Random Laplace Feature Maps for Semigroup Kernels on Histograms DeepReID：深层过滤配对神经网络的人重新鉴定
84.Fast Supervised Hashing with Decision Trees for High-Dimensional Data 使用约束二元回归一般各向同性表面光度立体
85.Learning Optimal Seeds for Diffusion-based Salient Object Detection 双线性回归遥感分类中的人脸聚类识别
86.Local Readjustment for High-Resolution 3D Reconstruction 在详细了解对象细粒度属性
87.Stereo under Sequential Optimal Sampling: A Statistical Analysis Framework for Search Space Reduction 最小的解广义姿态和尺度问题
88.Learning Important Spatial Pooling Regions for Scene Classification 曼哈顿框架设计的融合：超越曼哈顿世界
89.Randomized Max-Margin Compositions for Visual Recognition 混合人类身体部分序列姿态估计
90.Shrinkage Fields for Effective Image Restoration 多粒度分析细粒度动作检测
91.Non-rigid Segmentation using Sparse Low Dimensional Manifolds and Deep Belief Networks 协方差描述符的3D形状匹配和检索
92.Online Object Tracking, Learning and Parsing with And-Or Graphs 语境的物体检测和语义分割在狂野中的作用
93.Depth and Skeleton Associated Action Recognition without Online Accessible RGB-D Cameras 基于PatchMatch联合视图选择和深度图估计
94.Leveraging Hierarchical Parametric Networks for Skeletal Joints Based Action Segmentation and Recognition 强大的3D跟踪与描述符字段
95.Scene-Independent Group Profiling in Crowd 预测视觉系统的故障
96.Orientational Pyramid Matching for Recognizing Indoor Scenes 将移动电话变为3D扫描仪
97.Multi-source Deep Learning for Human Pose Estimation 稀疏字典学习的高分辨率图像的编辑传播
98.Multiscale Centerline Detection by Learning a Scale-Space Distance Transform 人脸对准高斯牛顿变形零件模型中最野性
99.DISCOVER: Discovering Important Segments for Classification of Video Events and Recounting 多元一般线性模型（MGLM）黎曼流形上与应用统计分析弥散加权像
100.3D Shape and Indirect Appearance by Structured Light Transport DeepFace：缩小差距，以人级别的性能在人脸验证

论文	概要
101.Human Action Recognition Based on Context-Dependent Graph Kernels 三角嵌入和民主汇聚图片搜索
102.Anytime Recognition of Objects and Scenes 稳定和翔实的光谱特征的图匹配
103.Action Localization with Tubelets from Motion 判别特征的点对点匹配的基于图像的定位