（十三：2020.08.28）CVPR 2015 追踪之论文纲要（译）_integrating coordinates with context for informati

作者：凡人多烦事01 | 2024-04-02 12:32:07

踩

integrating coordinates with context for information extraction in document

CVPR 2020 追踪之论文纲要（修正于2020.08.27）

讲在前面
论文目录

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602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.What do 15,000 Object Categories Tell Us About Classifying and Localizing Actions? 多假设轨迹分析稳健视觉跟踪
2.On Pairwise Costs for Network Flow Multi-Object Tracking 通过天窗估计一天的户外光度立体
3.Shape-From-Template in Flatland 通过广义融合套索前景建模背景减除
4.New Insights Into Laplacian Similarity Search 无约束的三维人脸重建
5.Sparse Depth Super Resolution 小方差非参数聚类上期超球
6.Global Refinement of Random Forest 最佳伙伴相似的鲁棒模板匹配
7.First-Person Pose Recognition Using Egocentric Workspaces 计算立体匹配成本使用卷积神经网络
8.Diversity-Induced Multi-View Subspace Clustering 纹理表征对图像和视频合成
9.Joint Action Recognition and Pose Estimation From Video 传统的显着性重装上阵：一个好的旧型号的新形态
10.Learning to Generate Chairs With Convolutional Neural Networks 面部动作单元估计强度潜树
11.A Light Transport Model for Mitigating Multipath Interference in Time-of-Flight Sensors 认识到定影深槽复杂事件从静态图像
12.Exact Bias Correction and Covariance Estimation for Stereo Vision 一种有效容积框架形状跟踪
13.Image Parsing With a Wide Range of Classes and Scene-Level Context 转移的语义表示对人再次鉴定和搜索
14.Video Co-Summarization: Video Summarization by Visual Co-Occurrence 提高对象建议采用多阈值跨界扩张
15.Sparse Convolutional Neural Networks Book2Movie：对齐视频的场景图书章节
16.Probability Occupancy Maps for Occluded Depth Images 代表对网格流形3D纹理进行检索和识别中的应用
17.Shape and Light Directions From Shading and Polarization 灵活的张量块坐标的Ascent方案超图匹配
18.Feature-Independent Context Estimation for Automatic Image Annotation 查询自适应后融合了图片搜索和人物重新鉴定
19.Motion Part Regularization: Improving Action Recognition via Trajectory Selection 从标题到视觉概念和返回
20.Total Variation Regularization of Shape Signals 无监督对象发现和本地化的野生：基于部分匹配自下而上区的建议
21.Jointly Learning Heterogeneous Features for RGB-D Activity Recognition 情绪的好坏参半：模型，预测和转移情绪分布
22.Membership Representation for Detecting Block-Diagonal Structure in Low-Rank or Sparse Subspace Clustering 室内场景结构分析单幅图像深度估计
23.Subgraph Matching Using Compactness Prior for Robust Feature Correspondence 设计深度网络的曲面法估计
24.Reweighted Laplace Prior Based Hyperspectral Compressive Sensing for Unknown Sparsity 从映像级到像素级贴标随着卷积网络
25.Reflectance Hashing for Material Recognition 分层回归神经网络为骨架的行为识别
26.Towards Open World Recognition 再谈核心化局部性敏感哈希用于改进大型图像检索
27.Gaze-Enabled Egocentric Video Summarization via Constrained Submodular Maximization 输出曲面嵌入的评价细粒度图像分类
28.Saliency Propagation From Simple to Difficult 域的大小池在局部描述：DSP-SIFT
29.Similarity Learning on an Explicit Polynomial Kernel Feature Map for Person Re-Identification 学习目标识别和三维姿态估计描述符
30.Material Classification With Thermal Imagery 事件驱动的立体匹配的实时3D全景视觉
31.DeepContour: A Deep Convolutional Feature Learned by Positive-Sharing Loss for Contour Detection 高效的标签征集未标记的图片数据集
32.A New Retraction for Accelerating the Riemannian Three-Factor Low-Rank Matrix Completion Algorithm 在二十个问题图像分割
33.Salient Object Subitizing 除了高斯金字塔：行动识别多跳过特性堆积
34.Semantic Alignment of LiDAR Data at City Scale 在弱标记的视频通过检测语义对象分割
35.Human Action Segmentation With Hierarchical Supervoxel Consistency 通过检查影响邻居了解分类错误
36.Automatic Construction Of Robust Spherical Harmonic Subspaces 熔断子类别概率纹理分类
37.Heat Diffusion Over Weighted Manifolds: A New Descriptor for Textured 3D Non-Rigid Shapes 本地高阶正则化上的数据流形
38.Exploiting Uncertainty in Regression Forests for Accurate Camera Relocalization 基于仰角恢复从各向同性材料的BRDF对称无标定光度立体
39.Propagated Image Filtering 快速，准确的图像变换，使用超分辨率森林
40.Subgraph Decomposition for Multi-Target Tracking 迭代明智的先验的盲解的判别学习
41.Attributes and Categories for Generic Instance Search From One Example 广义变形空间金字塔：几何保留密集函授估计
42.Joint Vanishing Point Extraction and Tracking 利用卫星图像大规模损伤检测
43.Displets: Resolving Stereo Ambiguities Using Object Knowledge 非线性卷积网络的高效，准确的逼近
44.Pedestrian Detection Aided by Deep Learning Semantic Tasks 实用强大的双视翻译估计
45.Going Deeper With Convolutions 搜索目标的预测从开放世界设定录制品
46.A Statistical Model of Riemannian Metric Variation for Deformable Shape Analysis PAIGE：成对的图像几何编码在结构，由运动提高效率
47.Depth From Focus With Your Mobile Phone 中超像素为基础的视频对象分割利用感知组织和位置之前
48.Video Event Recognition With Deep Hierarchical Context Model 的多面块坐标弗兰克 - 沃尔夫算法训练支持向量机的结构用昂贵的马克斯 - 甲骨文
49.Building Proteins in a Day: Efficient 3D Molecular Reconstruction 高效光源估计颜色恒常使用灰色像素
50.Learning Scene-Specific Pedestrian Detectors Without Real Data 室内场景的鲁棒重建

论文	概要
51.One-Day Outdoor Photometric Stereo via Skylight Estimation 低级别的视觉以协商一致的地区的空间层次
52.Background Subtraction via Generalized Fused Lasso Foreground Modeling 基于对称文本行检测的自然场景
53.Unconstrained 3D Face Reconstruction 人类才能飞？行动理解与演员的多个类
54.Small-Variance Nonparametric Clustering on the Hypersphere SWIFT：内围稀疏撤回在一审
55.Best-Buddies Similarity for Robust Template Matching 深深了解到脸部表征稀少，选择性和稳健
56.Computing the Stereo Matching Cost With a Convolutional Neural Network 同心圆的通用自极三角形及其在相机校准应用
57.Texture Representations for Image and Video Synthesis 监督离散散列
58.Traditional Saliency Reloaded: A Good Old Model in New Shape 分类器调节在预测时间
59.Latent Trees for Estimating Intensity of Facial Action Units 半监督学习有了明确的关系正规化
60.Recognize Complex Events From Static Images by Fusing Deep Channels EgoSampling：快进和立体声的自我中心影片
61.An Efficient Volumetric Framework for Shape Tracking ActivityNet：大规模视频基准的人类活动的理解
62.Transferring a Semantic Representation for Person Re-Identification and Search 双线性异构信息机的RGB-d行为识别
63.Improving Object Proposals With Multi-Thresholding Straddling Expansion 由粗到细的模型的三维姿态估计和子类别识别
64.Book2Movie: Aligning Video Scenes With Book Chapters 匹配-CNN会见KNN：准参数解析人
65.Representing 3D Texture on Mesh Manifolds for Retrieval and Recognition Applications segDeepM：分割环境与开发和深层神经网络语境下的目标检测
66.A Flexible Tensor Block Coordinate Ascent Scheme for Hypergraph Matching 核心融合为更好的图像去模糊
67.Query-Adaptive Late Fusion for Image Search and Person Re-Identification 提高对象通过贝叶斯优化和结构预测检测凭借深厚的卷积网络
68.From Captions to Visual Concepts and Back 向力传感从愿景：观测手对象的交互来推断操纵力
69.Unsupervised Object Discovery and Localization in the Wild: Part-Based Matching With Bottom-Up Region Proposals 学习等级的人重新鉴定与度量合奏
70.A Mixed Bag of Emotions: Model, Predict, and Transfer Emotion Distributions DASC：密集自适应自相关描述符的多模态和多谱匹配
71.Indoor Scene Structure Analysis for Single Image Depth Estimation 凸优化方法的鲁棒基本矩阵估计
72.Designing Deep Networks for Surface Normal Estimation 自适应区域池物体检测
73.From Image-Level to Pixel-Level Labeling With Convolutional Networks 对于语义分割完全卷积网络
74.Hierarchical Recurrent Neural Network for Skeleton Based Action Recognition 多类语义视频分割带宾语水平主动推理
75.Revisiting Kernelized Locality-Sensitive Hashing for Improved Large-Scale Image Retrieval 反思去除使用鬼影线索
76.Evaluation of Output Embeddings for Fine-Grained Image Classification 光场从微观基线图像对
77.Domain-Size Pooling in Local Descriptors: DSP-SIFT 超级增强，正规化的深度学习细粒度的图像分类
78.Learning Descriptors for Object Recognition and 3D Pose Estimation 可伸缩的结构与运动的密集采样影片
79.Event-Driven Stereo Matching for Real-Time 3D Panoramic Vision 扩大目标物检测的地平线：增量学习框架目标检测在视频
80.Efficient Label Collection for Unlabeled Image Datasets 联合多特征空间环境的场景识别的语义歧管
81.Image Segmentation in Twenty Questions 好等特点，用于跟踪视觉SLAM
82.Beyond Gaussian Pyramid: Multi-Skip Feature Stacking for Action Recognition 自适应AS-自然AS-可能的图像拼接
83.Semantic Object Segmentation via Detection in Weakly Labeled Video 显着性感知测地线的视频对象分割
84.Understanding Classifier Errors by Examining Influential Neighbors 自适应眼摄像机标定的头戴式设备
85.Fusing Subcategory Probabilities for Texture Classification 视觉Vibrometry：估计材料性能从小Motion在视频
86.Local High-Order Regularization on Data Manifolds 人类行为的弹性功能编码：从矢量场，以潜变量
87.Uncalibrated Photometric Stereo Based on Elevation Angle Recovery From BRDF Symmetry of Isotropic Materials 递归卷积神经网络的目标识别
88.Fast and Accurate Image Upscaling With Super-Resolution Forests 卷积功能屏蔽了联合对象和东西分割
89.Discriminative Learning of Iteration-Wise Priors for Blind Deconvolution Rent3D：平面布置图的先验单眼版图估计
90.Generalized Deformable Spatial Pyramid: Geometry-Preserving Dense Correspondence Estimation 同时非监督正交基聚类特征选择
91.Large-Scale Damage Detection Using Satellite Imagery FaceNet：统一嵌入人脸识别和聚类
92.Efficient and Accurate Approximations of Nonlinear Convolutional Networks 材料识别在野外与材料在上下文数据库
93.Practical Robust Two-View Translation Estimation 通过标签超级像素目标检测
94.Prediction of Search Targets From Fixations in Open-World Settings 整体3D场景理解从单地理标记的图片
95.PAIGE: PAirwise Image Geometry Encoding for Improved Efficiency in Structure-From-Motion FPA-CS：焦平面阵列基于压缩成像短波红外
96.Superpixel-Based Video Object Segmentation Using Perceptual Organization and Location Prior 迈向立体物检测双峰深玻尔兹曼机在RGBD影像
97.A Multi-Plane Block-Coordinate Frank-Wolfe Algorithm for Training Structural SVMs With a Costly Max-Oracle LMI基于2D-3D注册：从非标定图像欧几里德场景
98.Efficient Illuminant Estimation for Color Constancy Using Grey Pixels 社会显着性预测
99.Robust Reconstruction of Indoor Scenes 广义去模糊的视频动态场景
100.Low-Level Vision by Consensus in a Spatial Hierarchy of Regions 视频异常检测与定位方法层次特征表示和高斯过程回归

论文	概要
101.Saliency Detection via Cellular Automata 长期反复发作卷积网络从视觉上识别和描述
102.Inferring 3D Layout of Building Facades From a Single Image 一种稳定的多尺度内核的拓扑机器学习
103.Deeply Learned Attributes for Crowded Scene Understanding 隐私保护光学镜片，用于微型视觉传感器
104.Direct Structure Estimation for 3D Reconstruction 半透明的恢复内切片对象通过多频照明
105.Hardware Compliant Approximate Image Codes 人算本地化影片在嘈杂的前景和检测项
106.Efficient Globally Optimal Consensus Maximisation With Tree Search 迈向多相机人力形状检测用户特定的跟踪
107.Effective Learning-Based Illuminant Estimation Using Simple Features 汇集运动特性的第一人称视频
108.Understanding Deep Image Representations by Inverting Them DynamicFusion：在实时重构与跟踪非刚性的场景
109.Fine-Grained Visual Categorization via Multi-Stage Metric Learning 深度相机跟踪与轮廓线索
110.Detector Discovery in the Wild: Joint Multiple Instance and Representation Learning 行动人识别轨迹，汇集深卷积描述符
111.Data-Driven Depth Map Refinement via Multi-Scale Sparse Representation 异方差最大最小距离分析
112.On the Minimal Problems of Low-Rank Matrix Factorization 图像分割成凸多边形
113.Time-to-Contact From Image Intensity KL发散基于凝聚聚类的自动分级白癜风
114.Fast Randomized Singular Value Thresholding for Nuclear Norm Minimization 同时姿势和非刚性形状粒子动力学
115.Active Pictorial Structures 动态卷积层的近距天气预报
116.CIDEr: Consensus-Based Image Description Evaluation 24_7将通过识别合成查看
117.Self Scaled Regularized Robust Regression 粗到细的区域的选择与搭配
118.Parsing Occluded People by Flexible Composition

声明：本文内容由网友自发贡献，不代表【wpsshop博客】立场，版权归原作者所有，本站不承担相应法律责任。如您发现有侵权的内容，请联系我们。转载请注明出处：https://www.wpsshop.cn/w/凡人多烦事01/article/detail/352546