2015 IEEE International Conference on Computer Vision (ICCV)最新文献_第5页

Visual Madlibs: Fill in the Blank Description Generation and Question Answering Visual Madlibs:填空描述生成和问题回答

2015 IEEE International Conference on Computer Vision (ICCV) Pub Date : 2015-12-07 DOI: 10.1109/ICCV.2015.283

Licheng Yu, Eunbyung Park, A. Berg, Tamara L. Berg

引用次数: 135

Attributed Grammars for Joint Estimation of Human Attributes, Part and Pose 人体属性、部位和姿势联合估计的属性语法

2015 IEEE International Conference on Computer Vision (ICCV) Pub Date : 2015-12-07 DOI: 10.1109/ICCV.2015.273

Seyoung Park, Song-Chun Zhu

引用次数: 23

Sparse Dynamic 3D Reconstruction from Unsynchronized Videos 从非同步视频稀疏动态3D重建

2015 IEEE International Conference on Computer Vision (ICCV) Pub Date : 2015-12-07 DOI: 10.1109/ICCV.2015.504

Enliang Zheng, Dinghuang Ji, Enrique Dunn, Jan-Michael Frahm

引用次数: 23

Photogeometric Scene Flow for High-Detail Dynamic 3D Reconstruction 高细节动态三维重建的光几何场景流

2015 IEEE International Conference on Computer Vision (ICCV) Pub Date : 2015-12-07 DOI: 10.1109/ICCV.2015.103

P. Gotardo, T. Simon, Yaser Sheikh, I. Matthews

{"title":"Photogeometric Scene Flow for High-Detail Dynamic 3D Reconstruction","authors":"P. Gotardo, T. Simon, Yaser Sheikh, I. Matthews","doi":"10.1109/ICCV.2015.103","DOIUrl":"https://doi.org/10.1109/ICCV.2015.103","url":null,"abstract":"Photometric stereo (PS) is an established technique for high-detail reconstruction of 3D geometry and appearance. To correct for surface integration errors, PS is often combined with multiview stereo (MVS). With dynamic objects, PS reconstruction also faces the problem of computing optical flow (OF) for image alignment under rapid changes in illumination. Current PS methods typically compute optical flow and MVS as independent stages, each one with its own limitations and errors introduced by early regularization. In contrast, scene flow methods estimate geometry and motion, but lack the fine detail from PS. This paper proposes photogeometric scene flow (PGSF) for high-quality dynamic 3D reconstruction. PGSF performs PS, OF, and MVS simultaneously. It is based on two key observations: (i) while image alignment improves PS, PS allows for surfaces to be relit to improve alignment, (ii) PS provides surface gradients that render the smoothness term in MVS unnecessary, leading to truly data-driven, continuous depth estimates. This synergy is demonstrated in the quality of the resulting RGB appearance, 3D geometry, and 3D motion.","PeriodicalId":6633,"journal":{"name":"2015 IEEE International Conference on Computer Vision (ICCV)","volume":"16 1","pages":"846-854"},"PeriodicalIF":0.0,"publicationDate":"2015-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83153687","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 44

Depth Recovery from Light Field Using Focal Stack Symmetry 利用焦叠对称的光场深度恢复

2015 IEEE International Conference on Computer Vision (ICCV) Pub Date : 2015-12-07 DOI: 10.1109/ICCV.2015.394

Haiting Lin, Can Chen, S. B. Kang, Jingyi Yu

引用次数: 134

A Novel Sparsity Measure for Tensor Recovery 一种新的张量恢复稀疏度测度

2015 IEEE International Conference on Computer Vision (ICCV) Pub Date : 2015-12-07 DOI: 10.1109/ICCV.2015.39

Qian Zhao, Deyu Meng, Xu Kong, Qi Xie, Wenfei Cao, Yao Wang, Zongben Xu

引用次数: 47

Actionness-Assisted Recognition of Actions 动作-辅助动作识别

2015 IEEE International Conference on Computer Vision (ICCV) Pub Date : 2015-12-07 DOI: 10.1109/ICCV.2015.371

Ye Luo, L. Cheong, An Tran

引用次数: 10

Action Localization in Videos through Context Walk 通过上下文行走在视频中的动作定位

2015 IEEE International Conference on Computer Vision (ICCV) Pub Date : 2015-12-07 DOI: 10.1109/ICCV.2015.375

K. Soomro, Haroon Idrees, M. Shah

{"title":"Action Localization in Videos through Context Walk","authors":"K. Soomro, Haroon Idrees, M. Shah","doi":"10.1109/ICCV.2015.375","DOIUrl":"https://doi.org/10.1109/ICCV.2015.375","url":null,"abstract":"This paper presents an efficient approach for localizing actions by learning contextual relations, in the form of relative locations between different video regions. We begin by over-segmenting the videos into supervoxels, which have the ability to preserve action boundaries and also reduce the complexity of the problem. Context relations are learned during training which capture displacements from all the supervoxels in a video to those belonging to foreground actions. Then, given a testing video, we select a supervoxel randomly and use the context information acquired during training to estimate the probability of each supervoxel belonging to the foreground action. The walk proceeds to a new supervoxel and the process is repeated for a few steps. This \"context walk\" generates a conditional distribution of an action over all the supervoxels. A Conditional Random Field is then used to find action proposals in the video, whose confidences are obtained using SVMs. We validated the proposed approach on several datasets and show that context in the form of relative displacements between supervoxels can be extremely useful for action localization. This also results in significantly fewer evaluations of the classifier, in sharp contrast to the alternate sliding window approaches.","PeriodicalId":6633,"journal":{"name":"2015 IEEE International Conference on Computer Vision (ICCV)","volume":"91 1","pages":"3280-3288"},"PeriodicalIF":0.0,"publicationDate":"2015-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90185039","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 74

An NMF Perspective on Binary Hashing 二进制哈希的NMF视角

2015 IEEE International Conference on Computer Vision (ICCV) Pub Date : 2015-12-07 DOI: 10.1109/ICCV.2015.476

L. Mukherjee, Sathya Ravi, V. Ithapu, Tyler Holmes, Vikas Singh

{"title":"An NMF Perspective on Binary Hashing","authors":"L. Mukherjee, Sathya Ravi, V. Ithapu, Tyler Holmes, Vikas Singh","doi":"10.1109/ICCV.2015.476","DOIUrl":"https://doi.org/10.1109/ICCV.2015.476","url":null,"abstract":"The pervasiveness of massive data repositories has led to much interest in efficient methods for indexing, search, and retrieval. For image data, a rapidly developing body of work for these applications shows impressive performance with methods that broadly fall under the umbrella term of Binary Hashing. Given a distance matrix, a binary hashing algorithm solves for a binary code for the given set of examples, whose Hamming distance nicely approximates the original distances. The formulation is non-convex -- so existing solutions adopt spectral relaxations or perform coordinate descent (or quantization) on a surrogate objective that is numerically more tractable. In this paper, we first derive an Augmented Lagrangian approach to optimize the standard binary Hashing objective (i.e.,maintain fidelity with a given distance matrix). With appropriate step sizes, we find that this scheme already yields results that match or substantially outperform state of the art methods on most benchmarks used in the literature. Then, to allow the model to scale to large datasets, we obtain an interesting reformulation of the binary hashing objective as a non negative matrix factorization. Later, this leads to a simple multiplicative updates algorithm -- whose parallelization properties are exploited to obtain a fast GPU based implementation. We give a probabilistic analysis of our initialization scheme and present a range of experiments to show that the method is simple to implement and competes favorably with available methods (both for optimization and generalization).","PeriodicalId":6633,"journal":{"name":"2015 IEEE International Conference on Computer Vision (ICCV)","volume":"67 1","pages":"4184-4192"},"PeriodicalIF":0.0,"publicationDate":"2015-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90195759","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 15

BodyPrint: Pose Invariant 3D Shape Matching of Human Bodies BodyPrint:人体姿势不变的3D形状匹配

2015 IEEE International Conference on Computer Vision (ICCV) Pub Date : 2015-12-07 DOI: 10.1109/ICCV.2015.186

Jiangping Wang, Kai Ma, V. Singh, Thomas S. Huang, Terrence Chen

引用次数: 2