Pub Date : 2011-11-06DOI: 10.1109/ICCV.2011.6126220
Christine Chen, D. Vaquero, M. Turk
A class of techniques in computer vision and graphics is based on capturing multiple images of a scene under different illumination conditions. These techniques explore variations in illumination from image to image to extract interesting information about the scene. However, their applicability to dynamic environments is limited due to the need for robust motion compensation algorithms. To overcome this issue, we propose a method to separate multiple illuminants from a single image. Given an image of a scene simultaneously illuminated by multiple light sources, our method generates individual images as if they had been illuminated by each of the light sources separately. To facilitate the illumination separation process, we encode each light source with a distinct sinusoidal pattern, strategically selected given the relative position of each light with respect to the camera, such that the observed sinusoids become independent of the scene geometry. The individual illuminants are then demultiplexed by analyzing local frequencies. We show applications of our approach in image-based relighting, photometric stereo, and multiflash imaging.
{"title":"Illumination demultiplexing from a single image","authors":"Christine Chen, D. Vaquero, M. Turk","doi":"10.1109/ICCV.2011.6126220","DOIUrl":"https://doi.org/10.1109/ICCV.2011.6126220","url":null,"abstract":"A class of techniques in computer vision and graphics is based on capturing multiple images of a scene under different illumination conditions. These techniques explore variations in illumination from image to image to extract interesting information about the scene. However, their applicability to dynamic environments is limited due to the need for robust motion compensation algorithms. To overcome this issue, we propose a method to separate multiple illuminants from a single image. Given an image of a scene simultaneously illuminated by multiple light sources, our method generates individual images as if they had been illuminated by each of the light sources separately. To facilitate the illumination separation process, we encode each light source with a distinct sinusoidal pattern, strategically selected given the relative position of each light with respect to the camera, such that the observed sinusoids become independent of the scene geometry. The individual illuminants are then demultiplexed by analyzing local frequencies. We show applications of our approach in image-based relighting, photometric stereo, and multiflash imaging.","PeriodicalId":6391,"journal":{"name":"2011 International Conference on Computer Vision","volume":"2 1","pages":"17-24"},"PeriodicalIF":0.0,"publicationDate":"2011-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84217797","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}
Pub Date : 2011-11-06DOI: 10.1109/ICCV.2011.6126307
Qiang Qiu, Zhuolin Jiang, R. Chellappa
We present an approach for dictionary learning of action attributes via information maximization. We unify the class distribution and appearance information into an objective function for learning a sparse dictionary of action attributes. The objective function maximizes the mutual information between what has been learned and what remains to be learned in terms of appearance information and class distribution for each dictionary item. We propose a Gaussian Process (GP) model for sparse representation to optimize the dictionary objective function. The sparse coding property allows a kernel with a compact support in GP to realize a very efficient dictionary learning process. Hence we can describe an action video by a set of compact and discriminative action attributes. More importantly, we can recognize modeled action categories in a sparse feature space, which can be generalized to unseen and unmodeled action categories. Experimental results demonstrate the effectiveness of our approach in action recognition applications.
{"title":"Sparse dictionary-based representation and recognition of action attributes","authors":"Qiang Qiu, Zhuolin Jiang, R. Chellappa","doi":"10.1109/ICCV.2011.6126307","DOIUrl":"https://doi.org/10.1109/ICCV.2011.6126307","url":null,"abstract":"We present an approach for dictionary learning of action attributes via information maximization. We unify the class distribution and appearance information into an objective function for learning a sparse dictionary of action attributes. The objective function maximizes the mutual information between what has been learned and what remains to be learned in terms of appearance information and class distribution for each dictionary item. We propose a Gaussian Process (GP) model for sparse representation to optimize the dictionary objective function. The sparse coding property allows a kernel with a compact support in GP to realize a very efficient dictionary learning process. Hence we can describe an action video by a set of compact and discriminative action attributes. More importantly, we can recognize modeled action categories in a sparse feature space, which can be generalized to unseen and unmodeled action categories. Experimental results demonstrate the effectiveness of our approach in action recognition applications.","PeriodicalId":6391,"journal":{"name":"2011 International Conference on Computer Vision","volume":"58 1","pages":"707-714"},"PeriodicalIF":0.0,"publicationDate":"2011-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83947116","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}
Pub Date : 2011-11-06DOI: 10.1109/ICCV.2011.6126463
Zohaib Khan, A. Mian, Yiqun Hu
We propose ‘Contour Code’, a novel representation and binary hash table encoding for multispectral palmprint recognition. We first present a reliable technique for the extraction of a region of interest (ROI) from palm images acquired with non-contact sensors. The Contour Code representation is then derived from the Nonsubsampled Contourlet Transform. A uniscale pyramidal filter is convolved with the ROI followed by the application of a directional filter bank. The dominant directional subband establishes the orientation at each pixel and the index corresponding to this subband is encoded in the Contour Code representation. Unlike existing representations which extract orientation features directly from the palm images, the Contour Code uses a two stage filtering to extract robust orientation features. The Contour Code is binarized into an efficient hash table structure that only requires indexing and summation operations for simultaneous one-to-many matching with an embedded score level fusion of multiple bands. We quantitatively evaluate the accuracy of the ROI extraction by comparison with a manually produced ground truth. Multispectral palmprint verification results on the PolyU and CASIA databases show that the Contour Code achieves an EER reduction upto 50%, compared to state-of-the-art methods.
{"title":"Contour Code: Robust and efficient multispectral palmprint encoding for human recognition","authors":"Zohaib Khan, A. Mian, Yiqun Hu","doi":"10.1109/ICCV.2011.6126463","DOIUrl":"https://doi.org/10.1109/ICCV.2011.6126463","url":null,"abstract":"We propose ‘Contour Code’, a novel representation and binary hash table encoding for multispectral palmprint recognition. We first present a reliable technique for the extraction of a region of interest (ROI) from palm images acquired with non-contact sensors. The Contour Code representation is then derived from the Nonsubsampled Contourlet Transform. A uniscale pyramidal filter is convolved with the ROI followed by the application of a directional filter bank. The dominant directional subband establishes the orientation at each pixel and the index corresponding to this subband is encoded in the Contour Code representation. Unlike existing representations which extract orientation features directly from the palm images, the Contour Code uses a two stage filtering to extract robust orientation features. The Contour Code is binarized into an efficient hash table structure that only requires indexing and summation operations for simultaneous one-to-many matching with an embedded score level fusion of multiple bands. We quantitatively evaluate the accuracy of the ROI extraction by comparison with a manually produced ground truth. Multispectral palmprint verification results on the PolyU and CASIA databases show that the Contour Code achieves an EER reduction upto 50%, compared to state-of-the-art methods.","PeriodicalId":6391,"journal":{"name":"2011 International Conference on Computer Vision","volume":"42 1","pages":"1935-1942"},"PeriodicalIF":0.0,"publicationDate":"2011-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90672924","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}
Pub Date : 2011-11-06DOI: 10.1109/ICCV.2011.6126227
N. Komodakis
This paper proposes a very general max-margin learning framework for distance-based clustering. To this end, it formulates clustering as a high order energy minimization problem with latent variables, and applies a dual decomposition approach for training this model. The resulting framework allows learning a very broad class of distance functions, permits an automatic determination of the number of clusters during testing, and is also very efficient. As an additional contribution, we show how our method can be generalized to handle the training of a very broad class of important models in computer vision: arbitrary high-order latent CRFs. Experimental results verify its effectiveness.
{"title":"Learning to cluster using high order graphical models with latent variables","authors":"N. Komodakis","doi":"10.1109/ICCV.2011.6126227","DOIUrl":"https://doi.org/10.1109/ICCV.2011.6126227","url":null,"abstract":"This paper proposes a very general max-margin learning framework for distance-based clustering. To this end, it formulates clustering as a high order energy minimization problem with latent variables, and applies a dual decomposition approach for training this model. The resulting framework allows learning a very broad class of distance functions, permits an automatic determination of the number of clusters during testing, and is also very efficient. As an additional contribution, we show how our method can be generalized to handle the training of a very broad class of important models in computer vision: arbitrary high-order latent CRFs. Experimental results verify its effectiveness.","PeriodicalId":6391,"journal":{"name":"2011 International Conference on Computer Vision","volume":"31 1","pages":"73-80"},"PeriodicalIF":0.0,"publicationDate":"2011-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80649971","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}
Pub Date : 2011-11-06DOI: 10.1109/ICCV.2011.6126295
David Tsai, Yushi Jing, Yi Liu, H. Rowley, Sergey Ioffe, James M. Rehg
We address the problem of large-scale annotation of web images. Our approach is based on the concept of visual synset, which is an organization of images which are visually-similar and semantically-related. Each visual synset represents a single prototypical visual concept, and has an associated set of weighted annotations. Linear SVM's are utilized to predict the visual synset membership for unseen image examples, and a weighted voting rule is used to construct a ranked list of predicted annotations from a set of visual synsets. We demonstrate that visual synsets lead to better performance than standard methods on a new annotation database containing more than 200 million im- ages and 300 thousand annotations, which is the largest ever reported
{"title":"Large-scale image annotation using visual synset","authors":"David Tsai, Yushi Jing, Yi Liu, H. Rowley, Sergey Ioffe, James M. Rehg","doi":"10.1109/ICCV.2011.6126295","DOIUrl":"https://doi.org/10.1109/ICCV.2011.6126295","url":null,"abstract":"We address the problem of large-scale annotation of web images. Our approach is based on the concept of visual synset, which is an organization of images which are visually-similar and semantically-related. Each visual synset represents a single prototypical visual concept, and has an associated set of weighted annotations. Linear SVM's are utilized to predict the visual synset membership for unseen image examples, and a weighted voting rule is used to construct a ranked list of predicted annotations from a set of visual synsets. We demonstrate that visual synsets lead to better performance than standard methods on a new annotation database containing more than 200 million im- ages and 300 thousand annotations, which is the largest ever reported","PeriodicalId":6391,"journal":{"name":"2011 International Conference on Computer Vision","volume":"27 1","pages":"611-618"},"PeriodicalIF":0.0,"publicationDate":"2011-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78037490","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}
Pub Date : 2011-11-06DOI: 10.1109/ICCV.2011.6126411
Kent Fujiwara, K. Nishino, J. Takamatsu, Bo Zheng, K. Ikeuchi
We present a novel non-rigid surface registration method that achieves high accuracy and matches characteristic features without manual intervention. The key insight is to consider the entire shape as a collection of local structures that individually undergo rigid transformations to collectively deform the global structure. We realize this locally rigid but globally non-rigid surface registration with a newly derived dual-grid Free-form Deformation (FFD) framework. We first represent the source and target shapes with their signed distance fields (SDF). We then superimpose a sampling grid onto a conventional FFD grid that is dual to the control points. Each control point is then iteratively translated by a rigid transformation that minimizes the difference between two SDFs within the corresponding sampling region. The translated control points then interpolate the embedding space within the FFD grid and determine the overall deformation. The experimental results clearly demonstrate that our method is capable of overcoming the difficulty of preserving and matching local features.
{"title":"Locally rigid globally non-rigid surface registration","authors":"Kent Fujiwara, K. Nishino, J. Takamatsu, Bo Zheng, K. Ikeuchi","doi":"10.1109/ICCV.2011.6126411","DOIUrl":"https://doi.org/10.1109/ICCV.2011.6126411","url":null,"abstract":"We present a novel non-rigid surface registration method that achieves high accuracy and matches characteristic features without manual intervention. The key insight is to consider the entire shape as a collection of local structures that individually undergo rigid transformations to collectively deform the global structure. We realize this locally rigid but globally non-rigid surface registration with a newly derived dual-grid Free-form Deformation (FFD) framework. We first represent the source and target shapes with their signed distance fields (SDF). We then superimpose a sampling grid onto a conventional FFD grid that is dual to the control points. Each control point is then iteratively translated by a rigid transformation that minimizes the difference between two SDFs within the corresponding sampling region. The translated control points then interpolate the embedding space within the FFD grid and determine the overall deformation. The experimental results clearly demonstrate that our method is capable of overcoming the difficulty of preserving and matching local features.","PeriodicalId":6391,"journal":{"name":"2011 International Conference on Computer Vision","volume":"100 1","pages":"1527-1534"},"PeriodicalIF":0.0,"publicationDate":"2011-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84980846","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}
Pub Date : 2011-11-06DOI: 10.1109/ICCV.2011.6126546
Yuning Chai, V. Lempitsky, Andrew Zisserman
The objective of this paper is the unsupervised segmentation of image training sets into foreground and background in order to improve image classification performance. To this end we introduce a new scalable, alternation-based algorithm for co-segmentation, BiCoS, which is simpler than many of its predecessors, and yet has superior performance on standard benchmark image datasets.
{"title":"BiCoS: A Bi-level co-segmentation method for image classification","authors":"Yuning Chai, V. Lempitsky, Andrew Zisserman","doi":"10.1109/ICCV.2011.6126546","DOIUrl":"https://doi.org/10.1109/ICCV.2011.6126546","url":null,"abstract":"The objective of this paper is the unsupervised segmentation of image training sets into foreground and background in order to improve image classification performance. To this end we introduce a new scalable, alternation-based algorithm for co-segmentation, BiCoS, which is simpler than many of its predecessors, and yet has superior performance on standard benchmark image datasets.","PeriodicalId":6391,"journal":{"name":"2011 International Conference on Computer Vision","volume":"14 1","pages":"2579-2586"},"PeriodicalIF":0.0,"publicationDate":"2011-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88670474","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}
Pub Date : 2011-11-06DOI: 10.1109/ICCV.2011.6126271
Chao Chen, H. Edelsbrunner
Interpreting an image as a function on a compact subset of the Euclidean plane, we get its scale-space by diffusion, spreading the image over the entire plane. This generates a 1-parameter family of functions alternatively defined as convolutions with a progressively wider Gaussian kernel. We prove that the corresponding 1-parameter family of persistence diagrams have norms that go rapidly to zero as time goes to infinity. This result rationalizes experimental observations about scale-space. We hope this will lead to targeted improvements of related computer vision methods.
{"title":"Diffusion runs low on persistence fast","authors":"Chao Chen, H. Edelsbrunner","doi":"10.1109/ICCV.2011.6126271","DOIUrl":"https://doi.org/10.1109/ICCV.2011.6126271","url":null,"abstract":"Interpreting an image as a function on a compact subset of the Euclidean plane, we get its scale-space by diffusion, spreading the image over the entire plane. This generates a 1-parameter family of functions alternatively defined as convolutions with a progressively wider Gaussian kernel. We prove that the corresponding 1-parameter family of persistence diagrams have norms that go rapidly to zero as time goes to infinity. This result rationalizes experimental observations about scale-space. We hope this will lead to targeted improvements of related computer vision methods.","PeriodicalId":6391,"journal":{"name":"2011 International Conference on Computer Vision","volume":"106 1","pages":"423-430"},"PeriodicalIF":0.0,"publicationDate":"2011-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76107376","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}
Pub Date : 2011-11-06DOI: 10.1109/ICCV.2011.6126235
Horesh Ben Shitrit, J. Berclaz, F. Fleuret, P. Fua
In this paper, we show that tracking multiple people whose paths may intersect can be formulated as a convex global optimization problem. Our proposed framework is designed to exploit image appearance cues to prevent identity switches. Our method is effective even when such cues are only available at distant time intervals. This is unlike many current approaches that depend on appearance being exploitable from frame to frame. We validate our approach on three multi-camera sport and pedestrian datasets that contain long and complex sequences. Our algorithm perseveres identities better than state-of-the-art algorithms while keeping similar MOTA scores.
{"title":"Tracking multiple people under global appearance constraints","authors":"Horesh Ben Shitrit, J. Berclaz, F. Fleuret, P. Fua","doi":"10.1109/ICCV.2011.6126235","DOIUrl":"https://doi.org/10.1109/ICCV.2011.6126235","url":null,"abstract":"In this paper, we show that tracking multiple people whose paths may intersect can be formulated as a convex global optimization problem. Our proposed framework is designed to exploit image appearance cues to prevent identity switches. Our method is effective even when such cues are only available at distant time intervals. This is unlike many current approaches that depend on appearance being exploitable from frame to frame. We validate our approach on three multi-camera sport and pedestrian datasets that contain long and complex sequences. Our algorithm perseveres identities better than state-of-the-art algorithms while keeping similar MOTA scores.","PeriodicalId":6391,"journal":{"name":"2011 International Conference on Computer Vision","volume":"79 1","pages":"137-144"},"PeriodicalIF":0.0,"publicationDate":"2011-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75385237","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}
Pub Date : 2011-11-06DOI: 10.1109/ICCV.2011.6126497
T. Haines, T. Xiang
In the security domain a key problem is identifying rare behaviours of interest. Training examples for these behaviours may or may not exist, and if they do exist there will be few examples, quite probably one. We present a novel weakly supervised algorithm that can detect behaviours that either have never before been seen or for which there are few examples. Global context is modelled, allowing the detection of abnormal behaviours that in isolation appear normal. Pragmatic aspects are considered, such that no parameter tuning is required and real time performance is achieved.
{"title":"Delta-Dual Hierarchical Dirichlet Processes: A pragmatic abnormal behaviour detector","authors":"T. Haines, T. Xiang","doi":"10.1109/ICCV.2011.6126497","DOIUrl":"https://doi.org/10.1109/ICCV.2011.6126497","url":null,"abstract":"In the security domain a key problem is identifying rare behaviours of interest. Training examples for these behaviours may or may not exist, and if they do exist there will be few examples, quite probably one. We present a novel weakly supervised algorithm that can detect behaviours that either have never before been seen or for which there are few examples. Global context is modelled, allowing the detection of abnormal behaviours that in isolation appear normal. Pragmatic aspects are considered, such that no parameter tuning is required and real time performance is achieved.","PeriodicalId":6391,"journal":{"name":"2011 International Conference on Computer Vision","volume":"1 1","pages":"2198-2205"},"PeriodicalIF":0.0,"publicationDate":"2011-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91389644","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：