2011 International Conference on Computer Vision最新文献_第10页

Recursive MDL via graph cuts: Application to segmentation 通过图切割递归MDL:在分割中的应用

2011 International Conference on Computer Vision Pub Date : 2011-11-06 DOI: 10.1109/ICCV.2011.6126330

Lena Gorelick, Andrew Delong, O. Veksler, Yuri Boykov

引用次数: 10

Unsupervised learning of a scene-specific coarse gaze estimator 场景特定的粗凝视估计器的无监督学习

2011 International Conference on Computer Vision Pub Date : 2011-11-06 DOI: 10.1109/ICCV.2011.6126516

Ben Benfold, I. Reid

引用次数: 69

Discriminative figure-centric models for joint action localization and recognition 联合动作定位与识别的判别图形中心模型

2011 International Conference on Computer Vision Pub Date : 2011-11-06 DOI: 10.1109/ICCV.2011.6126472

Tian Lan, Yang Wang, Greg Mori

引用次数: 246

A joint learning framework for attribute models and object descriptions 一个用于属性模型和对象描述的联合学习框架

2011 International Conference on Computer Vision Pub Date : 2011-11-06 DOI: 10.1109/ICCV.2011.6126373

D. Mahajan, Sundararajan Sellamanickam, Vinod Nair

引用次数: 92

Active clustering of document fragments using information derived from both images and catalogs 使用来自图像和目录的信息对文档片段进行主动聚类

2011 International Conference on Computer Vision Pub Date : 2011-11-06 DOI: 10.1109/ICCV.2011.6126428

Lior Wolf, Lior Litwak, N. Dershowitz, Roni Shweka, Y. Choueka

引用次数: 11

Learning equivariant structured output SVM regressors 学习等变结构化输出SVM回归量

2011 International Conference on Computer Vision Pub Date : 2011-11-06 DOI: 10.1109/ICCV.2011.6126339

A. Vedaldi, Matthew B. Blaschko, Andrew Zisserman

{"title":"Learning equivariant structured output SVM regressors","authors":"A. Vedaldi, Matthew B. Blaschko, Andrew Zisserman","doi":"10.1109/ICCV.2011.6126339","DOIUrl":"https://doi.org/10.1109/ICCV.2011.6126339","url":null,"abstract":"Equivariance and invariance are often desired properties of a computer vision system. However, currently available strategies generally rely on virtual sampling, leaving open the question of how many samples are necessary, on the use of invariant feature representations, which can mistakenly discard information relevant to the vision task, or on the use of latent variable models, which result in non-convex training and expensive inference at test time. We propose here a generalization of structured output SVM regressors that can incorporate equivariance and invariance into a convex training procedure, enabling the incorporation of large families of transformations, while maintaining optimality and tractability. Importantly, test time inference does not require the estimation of latent variables, resulting in highly efficient objective functions. This results in a natural formulation for treating equivariance and invariance that is easily implemented as an adaptation of off-the-shelf optimization software, obviating the need for ad hoc sampling strategies. Theoretical results relating to vicinal risk, and experiments on challenging aerial car and pedestrian detection tasks show the effectiveness of the proposed solution.","PeriodicalId":6391,"journal":{"name":"2011 International Conference on Computer Vision","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2011-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85012249","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: 33

Multi-class semi-supervised SVMs with Positiveness Exclusive Regularization 具有正排他正则化的多类半监督支持向量机

2011 International Conference on Computer Vision Pub Date : 2011-11-06 DOI: 10.1109/ICCV.2011.6126399

Xiaobai Liu, Xiao-Tong Yuan, Shuicheng Yan, Hai Jin

{"title":"Multi-class semi-supervised SVMs with Positiveness Exclusive Regularization","authors":"Xiaobai Liu, Xiao-Tong Yuan, Shuicheng Yan, Hai Jin","doi":"10.1109/ICCV.2011.6126399","DOIUrl":"https://doi.org/10.1109/ICCV.2011.6126399","url":null,"abstract":"In this work, we address the problem of multi-class classification problem in semi-supervised setting. A regularized multi-task learning approach is presented to train multiple binary-class Semi-Supervised Support Vector Machines (S3VMs) using the one-vs-rest strategy within a joint framework. A novel type of regularization, namely Positiveness Exclusive Regularization (PER), is introduced to induce the following prior: if an unlabeled sample receives significant positive response from one of the classifiers, it is less likely for this sample to receive positive responses from the other classifiers. That is, we expect an exclusive relationship among different S3VMs for evaluating the same unlabeled sample. We propose to use an ℓ1,2-norm regularizer as an implementation of PER. The objective of our approach is to minimize an empirical risk regularized by a PER term and a manifold regularization term. An efficient Nesterov-type smoothing approximation based method is developed for optimization. Evaluations with comparisons are conducted on several benchmarks for visual classification to demonstrate the advantages of the proposed method.","PeriodicalId":6391,"journal":{"name":"2011 International Conference on Computer Vision","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2011-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87352335","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: 6

Linear stereo matching 线性立体匹配

2011 International Conference on Computer Vision Pub Date : 2011-11-06 DOI: 10.1109/ICCV.2011.6126434

Leonardo De-Maeztu, S. Mattoccia, A. Villanueva, R. Cabeza

引用次数: 102

Robust topological features for deformation invariant image matching 形变不变图像匹配的鲁棒拓扑特征

2011 International Conference on Computer Vision Pub Date : 2011-11-06 DOI: 10.1109/ICCV.2011.6126538

E. Lobaton, Ramanarayan Vasudevan, R. Alterovitz, R. Bajcsy

引用次数: 9

Kinecting the dots: Particle based scene flow from depth sensors 连接点:基于深度传感器的粒子场景流

2011 International Conference on Computer Vision Pub Date : 2011-11-06 DOI: 10.1109/ICCV.2011.6126509

Simon Hadfield, R. Bowden

引用次数: 97