CVPR 2011 Pub Date : 2011-06-20 DOI: 10.1109/CVPR.2011.5995432

Yunchao Gong, S. Lazebnik

引用次数: 1189

A brute-force algorithm for reconstructing a scene from two projections 一种从两个投影重建场景的蛮力算法

CVPR 2011 Pub Date : 2011-06-20 DOI: 10.1109/CVPR.2011.5995669

O. Enqvist, Fangyuan Jiang, Fredrik Kahl

{"title":"A brute-force algorithm for reconstructing a scene from two projections","authors":"O. Enqvist, Fangyuan Jiang, Fredrik Kahl","doi":"10.1109/CVPR.2011.5995669","DOIUrl":"https://doi.org/10.1109/CVPR.2011.5995669","url":null,"abstract":"Is the real problem in finding the relative orientation of two viewpoints the correspondence problem? We argue that this is only one difficulty. Even with known correspondences, popular methods like the eight point algorithm and minimal solvers may break down due to planar scenes or small relative motions. In this paper, we derive a simple, brute-force algorithm which is both robust to outliers and has no such algorithmic degeneracies. Several cost functions are explored including maximizing the consensus set and robust norms like truncated least-squares. Our method is based on parameter search in a four-dimensional space using a new epipolar parametrization. In principle, we do an exhaustive search of parameter space, but the computations are very simple and easily parallelizable, resulting in an efficient method. Further speed-ups can be obtained by restricting the domain of possible motions to, for example, planar motions or small rotations. Experimental results are given for a variety of scenarios including scenes with a large portion of outliers. Further, we apply our algorithm to 3D motion segmentation where we outperform state-of-the-art on the well-known Hopkins-155 benchmark database.","PeriodicalId":445398,"journal":{"name":"CVPR 2011","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115474490","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: 16

Towards cross-category knowledge propagation for learning visual concepts 面向视觉概念学习的跨范畴知识传播

CVPR 2011 Pub Date : 2011-06-20 DOI: 10.1109/CVPR.2011.5995312

Guo-Jun Qi, C. Aggarwal, Y. Rui, Q. Tian, Shiyu Chang, Thomas S. Huang

{"title":"Towards cross-category knowledge propagation for learning visual concepts","authors":"Guo-Jun Qi, C. Aggarwal, Y. Rui, Q. Tian, Shiyu Chang, Thomas S. Huang","doi":"10.1109/CVPR.2011.5995312","DOIUrl":"https://doi.org/10.1109/CVPR.2011.5995312","url":null,"abstract":"In recent years, knowledge transfer algorithms have become one of most the active research areas in learning visual concepts. Most of the existing learning algorithms focuses on leveraging the knowledge transfer process which is specific to a given category. However, in many cases, such a process may not be very effective when a particular target category has very few samples. In such cases, it is interesting to examine, whether it is feasible to use cross-category knowledge for improving the learning process by exploring the knowledge in correlated categories. Such a task can be quite challenging due to variations in semantic similarities and differences between categories, which could either help or hinder the cross-category learning process. In order to address this challenge, we develop a cross-category label propagation algorithm, which can directly propagate the inter-category knowledge at instance level between the source and the target categories. Furthermore, this algorithm can automatically detect conditions under which the transfer process can be detrimental to the learning process. This provides us a way to know when the transfer of cross-category knowledge is both useful and desirable. We present experimental results on real image and video data sets in order to demonstrate the effectiveness of our approach.","PeriodicalId":445398,"journal":{"name":"CVPR 2011","volume":"30 5","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120994205","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: 81

Functional categorization of objects using real-time markerless motion capture 使用实时无标记动作捕捉的物体功能分类

CVPR 2011 Pub Date : 2011-06-20 DOI: 10.1109/CVPR.2011.5995582

Juergen Gall, A. Fossati, L. Gool

引用次数: 70

Local isomorphism to solve the pre-image problem in kernel methods 局部同构解决核方法中的预像问题

CVPR 2011 Pub Date : 2011-06-20 DOI: 10.1109/CVPR.2011.5995685

Dong Huang, Yuandong Tian, F. D. L. Torre

引用次数: 11

An effective document image deblurring algorithm 一种有效的文档图像去模糊算法

CVPR 2011 Pub Date : 2011-06-20 DOI: 10.1109/CVPR.2011.5995568

Xiaogang Chen, Xiangjian He, Jie Yang, Qiang Wu

引用次数: 84

Tracking 3D human pose with large root node uncertainty 具有大根节点不确定性的三维人体姿态跟踪

CVPR 2011 Pub Date : 2011-06-20 DOI: 10.1109/CVPR.2011.5995502

B. Daubney, Xianghua Xie

{"title":"Tracking 3D human pose with large root node uncertainty","authors":"B. Daubney, Xianghua Xie","doi":"10.1109/CVPR.2011.5995502","DOIUrl":"https://doi.org/10.1109/CVPR.2011.5995502","url":null,"abstract":"Representing articulated objects as a graphical model has gained much popularity in recent years, often the root node of the graph describes the global position and orientation of the object. In this work a method is presented to robustly track 3D human pose by permitting greater uncertainty to be modeled over the root node than existing techniques allow. Significantly, this is achieved without increasing the uncertainty of remaining parts of the model. The benefit is that a greater volume of the posterior can be supported making the approach less vulnerable to tracking failure. Given a hypothesis of the root node state a novel method is presented to estimate the posterior over the remaining parts of the body conditioned on this value. All probability distributions are approximated using a single Gaussian allowing inference to be carried out in closed form. A set of deterministically selected sample points are used that allow the posterior to be updated for each part requiring just seven image likelihood evaluations making it extremely efficient. Multiple root node states are supported and propagated using standard sampling techniques. We believe this to be the first work devoted to efficient tracking of human pose whilst modeling large uncertainty in the root node and demonstrate the presented method to be more robust to tracking failures than existing approaches.","PeriodicalId":445398,"journal":{"name":"CVPR 2011","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124968844","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: 27

From partial shape matching through local deformation to robust global shape similarity for object detection 从局部变形的局部形状匹配到鲁棒的全局形状相似目标检测

CVPR 2011 Pub Date : 2011-06-20 DOI: 10.1109/CVPR.2011.5995591

Tianyang Ma, Longin Jan Latecki

引用次数: 106

Spatial-DiscLDA for visual recognition 用于视觉识别的空间disclda

CVPR 2011 Pub Date : 2011-06-20 DOI: 10.1109/CVPR.2011.5995426

Zhenxing Niu, G. Hua, Xinbo Gao, Q. Tian

{"title":"Spatial-DiscLDA for visual recognition","authors":"Zhenxing Niu, G. Hua, Xinbo Gao, Q. Tian","doi":"10.1109/CVPR.2011.5995426","DOIUrl":"https://doi.org/10.1109/CVPR.2011.5995426","url":null,"abstract":"Topic models such as pLSA, LDA and their variants have been widely adopted for visual recognition. However, most of the adopted models, if not all, are unsupervised, which neglected the valuable supervised labels during model training. In this paper, we exploit recent advancement in supervised topic modeling, more particularly, the DiscLDA model for object recognition. We extend it to a part based visual representation to automatically identify and model different object parts. We call the proposed model as Spatial-DiscLDA (S-DiscLDA). It models the appearances and locations of the object parts simultaneously, which also takes the supervised labels into consideration. It can be directly used as a classifier to recognize the object. This is performed by an approximate inference algorithm based on Gibbs sampling and bridge sampling methods. We examine the performance of our model by comparing its performance with another supervised topic model on two scene category datasets, i.e., LabelMe and UIUC-sport dataset. We also compare our approach with other approaches which model spatial structures of visual features on the popular Caltech-4 dataset. The experimental results illustrate that it provides competitive performance.","PeriodicalId":445398,"journal":{"name":"CVPR 2011","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123543456","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: 35

Rank-SIFT: Learning to rank repeatable local interest points rank - sift:学习对可重复的局部兴趣点进行排序

CVPR 2011 Pub Date : 2011-06-20 DOI: 10.1109/CVPR.2011.5995461

Bing Li, Rong Xiao, Zhiwei Li, Rui Cai, Bao-Liang Lu, Lei Zhang

引用次数: 47

CVPR 2011最新文献