2013 IEEE International Conference on Computer Vision最新文献_第7页

From Semi-supervised to Transfer Counting of Crowds 从半监督到人群转移计数

2013 IEEE International Conference on Computer Vision Pub Date : 2013-12-01 DOI: 10.1109/ICCV.2013.270

Chen Change Loy, S. Gong, T. Xiang

引用次数: 142

Restoring an Image Taken through a Window Covered with Dirt or Rain 恢复通过被灰尘或雨水覆盖的窗户拍摄的图像

2013 IEEE International Conference on Computer Vision Pub Date : 2013-12-01 DOI: 10.1109/ICCV.2013.84

D. Eigen, Dilip Krishnan, R. Fergus

引用次数: 405

Detecting Irregular Curvilinear Structures in Gray Scale and Color Imagery Using Multi-directional Oriented Flux 利用多向定向磁通检测灰度和彩色图像中的不规则曲线结构

2013 IEEE International Conference on Computer Vision Pub Date : 2013-12-01 DOI: 10.1109/ICCV.2013.196

Engin Türetken, C. Becker, Przemyslaw Glowacki, Fethallah Benmansour, P. Fua

引用次数: 43

Manifold Based Face Synthesis from Sparse Samples 基于稀疏样本的流形人脸合成

2013 IEEE International Conference on Computer Vision Pub Date : 2013-12-01 DOI: 10.1109/ICCV.2013.275

Hongteng Xu, H. Zha

引用次数: 9

Slice Sampling Particle Belief Propagation 切片采样粒子信念传播

2013 IEEE International Conference on Computer Vision Pub Date : 2013-12-01 DOI: 10.1109/ICCV.2013.144

Oliver Müller, M. Yang, B. Rosenhahn

引用次数: 7

Multi-view Normal Field Integration for 3D Reconstruction of Mirroring Objects 镜像对象三维重建的多视图法向场集成

2013 IEEE International Conference on Computer Vision Pub Date : 2013-12-01 DOI: 10.1109/ICCV.2013.311

Michael Weinmann, Aljosa Osep, R. Ruiters, R. Klein

{"title":"Multi-view Normal Field Integration for 3D Reconstruction of Mirroring Objects","authors":"Michael Weinmann, Aljosa Osep, R. Ruiters, R. Klein","doi":"10.1109/ICCV.2013.311","DOIUrl":"https://doi.org/10.1109/ICCV.2013.311","url":null,"abstract":"In this paper, we present a novel, robust multi-view normal field integration technique for reconstructing the full 3D shape of mirroring objects. We employ a turntable-based setup with several cameras and displays. These are used to display illumination patterns which are reflected by the object surface. The pattern information observed in the cameras enables the calculation of individual volumetric normal fields for each combination of camera, display and turntable angle. As the pattern information might be blurred depending on the surface curvature or due to non-perfect mirroring surface characteristics, we locally adapt the decoding to the finest still resolvable pattern resolution. In complex real-world scenarios, the normal fields contain regions without observations due to occlusions and outliers due to interreflections and noise. Therefore, a robust reconstruction using only normal information is challenging. Via a non-parametric clustering of normal hypotheses derived for each point in the scene, we obtain both the most likely local surface normal and a local surface consistency estimate. This information is utilized in an iterative min-cut based variational approach to reconstruct the surface geometry.","PeriodicalId":6351,"journal":{"name":"2013 IEEE International Conference on Computer Vision","volume":"9 1","pages":"2504-2511"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89518611","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

Unifying Nuclear Norm and Bilinear Factorization Approaches for Low-Rank Matrix Decomposition 低秩矩阵分解的统一核范数与双线性分解方法

2013 IEEE International Conference on Computer Vision Pub Date : 2013-12-01 DOI: 10.1109/ICCV.2013.309

R. Cabral, F. D. L. Torre, J. Costeira, Alexandre Bernardino

{"title":"Unifying Nuclear Norm and Bilinear Factorization Approaches for Low-Rank Matrix Decomposition","authors":"R. Cabral, F. D. L. Torre, J. Costeira, Alexandre Bernardino","doi":"10.1109/ICCV.2013.309","DOIUrl":"https://doi.org/10.1109/ICCV.2013.309","url":null,"abstract":"Low rank models have been widely used for the representation of shape, appearance or motion in computer vision problems. Traditional approaches to fit low rank models make use of an explicit bilinear factorization. These approaches benefit from fast numerical methods for optimization and easy kernelization. However, they suffer from serious local minima problems depending on the loss function and the amount/type of missing data. Recently, these low-rank models have alternatively been formulated as convex problems using the nuclear norm regularizer, unlike factorization methods, their numerical solvers are slow and it is unclear how to kernelize them or to impose a rank a priori. This paper proposes a unified approach to bilinear factorization and nuclear norm regularization, that inherits the benefits of both. We analyze the conditions under which these approaches are equivalent. Moreover, based on this analysis, we propose a new optimization algorithm and a \"rank continuation'' strategy that outperform state-of-the-art approaches for Robust PCA, Structure from Motion and Photometric Stereo with outliers and missing data.","PeriodicalId":6351,"journal":{"name":"2013 IEEE International Conference on Computer Vision","volume":"9 1","pages":"2488-2495"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89812993","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: 181

Saliency Detection via Absorbing Markov Chain 吸收马尔可夫链的显著性检测

2013 IEEE International Conference on Computer Vision Pub Date : 2013-12-01 DOI: 10.1109/ICCV.2013.209

Bowen Jiang, L. Zhang, Huchuan Lu, Chuan Yang, Ming-Hsuan Yang

引用次数: 585

Learning Slow Features for Behaviour Analysis 学习行为分析的慢特性

2013 IEEE International Conference on Computer Vision Pub Date : 2013-12-01 DOI: 10.1109/ICCV.2013.353

Lazaros Zafeiriou, M. Nicolaou, S. Zafeiriou, Symeon Nikitidis, M. Pantic

{"title":"Learning Slow Features for Behaviour Analysis","authors":"Lazaros Zafeiriou, M. Nicolaou, S. Zafeiriou, Symeon Nikitidis, M. Pantic","doi":"10.1109/ICCV.2013.353","DOIUrl":"https://doi.org/10.1109/ICCV.2013.353","url":null,"abstract":"A recently introduced latent feature learning technique for time varying dynamic phenomena analysis is the so called Slow Feature Analysis (SFA). SFA is a deterministic component analysis technique for multi-dimensional sequences that by minimizing the variance of the first order time derivative approximation of the input signal finds uncorrelated projections that extract slowly-varying features ordered by their temporal consistency and constancy. In this paper, we propose a number of extensions in both the deterministic and the probabilistic SFA optimization frameworks. In particular, we derive a novel deterministic SFA algorithm that is able to identify linear projections that extract the common slowest varying features of two or more sequences. In addition, we propose an Expectation Maximization (EM) algorithm to perform inference in a probabilistic formulation of SFA and similarly extend it in order to handle two and more time varying data sequences. Moreover, we demonstrate that the probabilistic SFA (EMSFA) algorithm that discovers the common slowest varying latent space of multiple sequences can be combined with dynamic time warping techniques for robust sequence time alignment. The proposed SFA algorithms were applied for facial behavior analysis demonstrating their usefulness and appropriateness for this task.","PeriodicalId":6351,"journal":{"name":"2013 IEEE International Conference on Computer Vision","volume":"21 1","pages":"2840-2847"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86581464","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: 23

A Convex Optimization Framework for Active Learning 主动学习的凸优化框架

2013 IEEE International Conference on Computer Vision Pub Date : 2013-12-01 DOI: 10.1109/ICCV.2013.33

Ehsan Elhamifar, G. Sapiro, A. Yang, S. Shankar Sasrty

{"title":"A Convex Optimization Framework for Active Learning","authors":"Ehsan Elhamifar, G. Sapiro, A. Yang, S. Shankar Sasrty","doi":"10.1109/ICCV.2013.33","DOIUrl":"https://doi.org/10.1109/ICCV.2013.33","url":null,"abstract":"In many image/video/web classification problems, we have access to a large number of unlabeled samples. However, it is typically expensive and time consuming to obtain labels for the samples. Active learning is the problem of progressively selecting and annotating the most informative unlabeled samples, in order to obtain a high classification performance. Most existing active learning algorithms select only one sample at a time prior to retraining the classifier. Hence, they are computationally expensive and cannot take advantage of parallel labeling systems such as Mechanical Turk. On the other hand, algorithms that allow the selection of multiple samples prior to retraining the classifier, may select samples that have significant information overlap or they involve solving a non-convex optimization. More importantly, the majority of active learning algorithms are developed for a certain classifier type such as SVM. In this paper, we develop an efficient active learning framework based on convex programming, which can select multiple samples at a time for annotation. Unlike the state of the art, our algorithm can be used in conjunction with any type of classifiers, including those of the family of the recently proposed Sparse Representation-based Classification (SRC). We use the two principles of classifier uncertainty and sample diversity in order to guide the optimization program towards selecting the most informative unlabeled samples, which have the least information overlap. Our method can incorporate the data distribution in the selection process by using the appropriate dissimilarity between pairs of samples. We show the effectiveness of our framework in person detection, scene categorization and face recognition on real-world datasets.","PeriodicalId":6351,"journal":{"name":"2013 IEEE International Conference on Computer Vision","volume":"3 1","pages":"209-216"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87810141","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: 116