Itai Ben-Shalom, Noga Levy, Lior Wolf, N. Dershowitz, Adiel Ben-Shalom, Roni Shweka, Y. Choueka, Tamir Hazan, Yaniv Bar
We present a tool for re-ranking the results of a specific query by considering the (n+1) × (n+1) matrix of pairwise similarities among the elements of the set of n retrieved results and the query itself. The re-ranking thus makes use of the similarities between the various results and does not employ additional sources of information. The tool is based on graphical Bayesian models, which reinforce retrieved items strongly linked to other retrievals, and on repeated clustering to measure the stability of the obtained associations. The utility of the tool is demonstrated within the context of visual search of documents from the Cairo Genizah and for retrieval of paintings by the same artist and in the same style.
{"title":"Congruency-Based Reranking","authors":"Itai Ben-Shalom, Noga Levy, Lior Wolf, N. Dershowitz, Adiel Ben-Shalom, Roni Shweka, Y. Choueka, Tamir Hazan, Yaniv Bar","doi":"10.1109/CVPR.2014.270","DOIUrl":"https://doi.org/10.1109/CVPR.2014.270","url":null,"abstract":"We present a tool for re-ranking the results of a specific query by considering the (n+1) × (n+1) matrix of pairwise similarities among the elements of the set of n retrieved results and the query itself. The re-ranking thus makes use of the similarities between the various results and does not employ additional sources of information. The tool is based on graphical Bayesian models, which reinforce retrieved items strongly linked to other retrievals, and on repeated clustering to measure the stability of the obtained associations. The utility of the tool is demonstrated within the context of visual search of documents from the Cairo Genizah and for retrieval of paintings by the same artist and in the same style.","PeriodicalId":319578,"journal":{"name":"2014 IEEE Conference on Computer Vision and Pattern Recognition","volume":"80 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115012185","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}
We present a new globally optimal algorithm for self-calibrating a moving camera with constant parameters. Our method aims at estimating the Dual Absolute Quadric (DAQ) under the rank-3 and, optionally, camera centers chirality constraints. We employ the Branch-and-Prune paradigm and explore the space of only 5 parameters. Pruning in our method relies on solving Linear Matrix Inequality (LMI) feasibility and Generalized Eigenvalue (GEV) problems that solely depend upon the entries of the DAQ. These LMI and GEV problems are used to rule out branches in the search tree in which a quadric not satisfying the rank and chirality conditions on camera centers is guaranteed not to exist. The chirality LMI conditions are obtained by relying on the mild assumption that the camera undergoes a rotation of no more than 90 between consecutive views. Furthermore, our method does not rely on calculating bounds on any particular cost function and hence can virtually optimize any objective while achieving global optimality in a very competitive running-time.
{"title":"Efficient Pruning LMI Conditions for Branch-and-Prune Rank and Chirality-Constrained Estimation of the Dual Absolute Quadric","authors":"A. Habed, D. Paudel, C. Demonceaux, D. Fofi","doi":"10.1109/CVPR.2014.70","DOIUrl":"https://doi.org/10.1109/CVPR.2014.70","url":null,"abstract":"We present a new globally optimal algorithm for self-calibrating a moving camera with constant parameters. Our method aims at estimating the Dual Absolute Quadric (DAQ) under the rank-3 and, optionally, camera centers chirality constraints. We employ the Branch-and-Prune paradigm and explore the space of only 5 parameters. Pruning in our method relies on solving Linear Matrix Inequality (LMI) feasibility and Generalized Eigenvalue (GEV) problems that solely depend upon the entries of the DAQ. These LMI and GEV problems are used to rule out branches in the search tree in which a quadric not satisfying the rank and chirality conditions on camera centers is guaranteed not to exist. The chirality LMI conditions are obtained by relying on the mild assumption that the camera undergoes a rotation of no more than 90 between consecutive views. Furthermore, our method does not rely on calculating bounds on any particular cost function and hence can virtually optimize any objective while achieving global optimality in a very competitive running-time.","PeriodicalId":319578,"journal":{"name":"2014 IEEE Conference on Computer Vision and Pattern Recognition","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115141034","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}
It is often desirable to evaluate images quality with a perceptually relevant measure that does not require a reference image. Recent approaches to this problem use human provided quality scores with machine learning to learn a measure. The biggest hurdles to these efforts are: 1) the difficulty of generalizing across diverse types of distortions and 2) collecting the enormity of human scored training data that is needed to learn the measure. We present a new blind image quality measure that addresses these difficulties by learning a robust, nonlinear kernel regression function using a rectifier neural network. The method is pre-trained with unlabeled data and fine-tuned with labeled data. It generalizes across a large set of images and distortion types without the need for a large amount of labeled data. We evaluate our approach on two benchmark datasets and show that it not only outperforms the current state of the art in blind image quality estimation, but also outperforms the state of the art in non-blind measures. Furthermore, we show that our semi-supervised approach is robust to using varying amounts of labeled data.
{"title":"Blind Image Quality Assessment Using Semi-supervised Rectifier Networks","authors":"Huixuan Tang, Neel Joshi, Ashish Kapoor","doi":"10.1109/CVPR.2014.368","DOIUrl":"https://doi.org/10.1109/CVPR.2014.368","url":null,"abstract":"It is often desirable to evaluate images quality with a perceptually relevant measure that does not require a reference image. Recent approaches to this problem use human provided quality scores with machine learning to learn a measure. The biggest hurdles to these efforts are: 1) the difficulty of generalizing across diverse types of distortions and 2) collecting the enormity of human scored training data that is needed to learn the measure. We present a new blind image quality measure that addresses these difficulties by learning a robust, nonlinear kernel regression function using a rectifier neural network. The method is pre-trained with unlabeled data and fine-tuned with labeled data. It generalizes across a large set of images and distortion types without the need for a large amount of labeled data. We evaluate our approach on two benchmark datasets and show that it not only outperforms the current state of the art in blind image quality estimation, but also outperforms the state of the art in non-blind measures. Furthermore, we show that our semi-supervised approach is robust to using varying amounts of labeled data.","PeriodicalId":319578,"journal":{"name":"2014 IEEE Conference on Computer Vision and Pattern Recognition","volume":"92 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115153842","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}
Outliers are pervasive in many computer vision and pattern recognition problems. Automatically eliminating outliers scattering among practical data collections becomes increasingly important, especially for Internet inspired vision applications. In this paper, we propose a novel one-class learning approach which is robust to contamination of input training data and able to discover the outliers that corrupt one class of data source. Our approach works under a fully unsupervised manner, differing from traditional one-class learning supervised by known positive labels. By design, our approach optimizes a kernel-based max-margin objective which jointly learns a large margin one-class classifier and a soft label assignment for inliers and outliers. An alternating optimization algorithm is then designed to iteratively refine the classifier and the labeling, achieving a provably convergent solution in only a few iterations. Extensive experiments conducted on four image datasets in the presence of artificial and real-world outliers demonstrate that the proposed approach is considerably superior to the state-of-the-arts in obliterating outliers from contaminated one class of images, exhibiting strong robustness at a high outlier proportion up to 60%.
{"title":"Unsupervised One-Class Learning for Automatic Outlier Removal","authors":"W. Liu, G. Hua, John R. Smith","doi":"10.1109/CVPR.2014.483","DOIUrl":"https://doi.org/10.1109/CVPR.2014.483","url":null,"abstract":"Outliers are pervasive in many computer vision and pattern recognition problems. Automatically eliminating outliers scattering among practical data collections becomes increasingly important, especially for Internet inspired vision applications. In this paper, we propose a novel one-class learning approach which is robust to contamination of input training data and able to discover the outliers that corrupt one class of data source. Our approach works under a fully unsupervised manner, differing from traditional one-class learning supervised by known positive labels. By design, our approach optimizes a kernel-based max-margin objective which jointly learns a large margin one-class classifier and a soft label assignment for inliers and outliers. An alternating optimization algorithm is then designed to iteratively refine the classifier and the labeling, achieving a provably convergent solution in only a few iterations. Extensive experiments conducted on four image datasets in the presence of artificial and real-world outliers demonstrate that the proposed approach is considerably superior to the state-of-the-arts in obliterating outliers from contaminated one class of images, exhibiting strong robustness at a high outlier proportion up to 60%.","PeriodicalId":319578,"journal":{"name":"2014 IEEE Conference on Computer Vision and Pattern Recognition","volume":"272 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115597501","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}
Hao Zhang, Wenjun Zhou, Christopher M. Reardon, L. Parker
We present a novel feature description algorithm to describe 3D local spatio-temporal features for human action recognition. Our descriptor avoids the singularity and limited discrimination power issues of traditional 3D descriptors by quantizing and describing visual features in the simplex topological vector space. Specifically, given a feature's support region containing a set of 3D visual cues, we decompose the cues' orientation into three angles, transform the decomposed angles into the simplex space, and describe them in such a space. Then, quadrant decomposition is performed to improve discrimination, and a final feature vector is composed from the resulting histograms. We develop intuitive visualization tools for analyzing feature characteristics in the simplex topological vector space. Experimental results demonstrate that our novel simplex-based orientation decomposition (SOD) descriptor substantially outperforms traditional 3D descriptors for the KTH, UCF Sport, and Hollywood-2 benchmark action datasets. In addition, the results show that our SOD descriptor is a superior individual descriptor for action recognition.
{"title":"Simplex-Based 3D Spatio-temporal Feature Description for Action Recognition","authors":"Hao Zhang, Wenjun Zhou, Christopher M. Reardon, L. Parker","doi":"10.1109/CVPR.2014.265","DOIUrl":"https://doi.org/10.1109/CVPR.2014.265","url":null,"abstract":"We present a novel feature description algorithm to describe 3D local spatio-temporal features for human action recognition. Our descriptor avoids the singularity and limited discrimination power issues of traditional 3D descriptors by quantizing and describing visual features in the simplex topological vector space. Specifically, given a feature's support region containing a set of 3D visual cues, we decompose the cues' orientation into three angles, transform the decomposed angles into the simplex space, and describe them in such a space. Then, quadrant decomposition is performed to improve discrimination, and a final feature vector is composed from the resulting histograms. We develop intuitive visualization tools for analyzing feature characteristics in the simplex topological vector space. Experimental results demonstrate that our novel simplex-based orientation decomposition (SOD) descriptor substantially outperforms traditional 3D descriptors for the KTH, UCF Sport, and Hollywood-2 benchmark action datasets. In addition, the results show that our SOD descriptor is a superior individual descriptor for action recognition.","PeriodicalId":319578,"journal":{"name":"2014 IEEE Conference on Computer Vision and Pattern Recognition","volume":"96 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115658567","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}
Przemyslaw Glowacki, M. Pinheiro, Engin Türetken, R. Sznitman, Daniel Lebrecht, J. Kybic, A. Holtmaat, P. Fua
We propose an approach to reconstructing tree structures that evolve over time in 2D images and 3D image stacks such as neuronal axons or plant branches. Instead of reconstructing structures in each image independently, we do so for all images simultaneously to take advantage of temporal-consistency constraints. We show that this problem can be formulated as a Quadratic Mixed Integer Program and solved efficiently. The outcome of our approach is a framework that provides substantial improvements in reconstructions over traditional single time-instance formulations. Furthermore, an added benefit of our approach is the ability to automatically detect places where significant changes have occurred over time, which is challenging when considering large amounts of data.
{"title":"Reconstructing Evolving Tree Structures in Time Lapse Sequences","authors":"Przemyslaw Glowacki, M. Pinheiro, Engin Türetken, R. Sznitman, Daniel Lebrecht, J. Kybic, A. Holtmaat, P. Fua","doi":"10.1109/CVPR.2014.388","DOIUrl":"https://doi.org/10.1109/CVPR.2014.388","url":null,"abstract":"We propose an approach to reconstructing tree structures that evolve over time in 2D images and 3D image stacks such as neuronal axons or plant branches. Instead of reconstructing structures in each image independently, we do so for all images simultaneously to take advantage of temporal-consistency constraints. We show that this problem can be formulated as a Quadratic Mixed Integer Program and solved efficiently. The outcome of our approach is a framework that provides substantial improvements in reconstructions over traditional single time-instance formulations. Furthermore, an added benefit of our approach is the ability to automatically detect places where significant changes have occurred over time, which is challenging when considering large amounts of data.","PeriodicalId":319578,"journal":{"name":"2014 IEEE Conference on Computer Vision and Pattern Recognition","volume":"399 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124440563","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}
In this paper, we would like to evaluate online learning algorithms for large-scale visual recognition using state-of-the-art features which are preselected and held fixed. Today, combinations of high-dimensional features and linear classifiers are widely used for large-scale visual recognition. Numerous so-called mid-level features have been developed and mutually compared on an experimental basis. Although various learning methods for linear classification have also been proposed in the machine learning and natural language processing literature, they have rarely been evaluated for visual recognition. Therefore, we give guidelines via investigations of state-of-the-art online learning methods of linear classifiers. Many methods have been evaluated using toy data and natural language processing problems such as document classification. Consequently, we gave those methods a unified interpretation from the viewpoint of visual recognition. Results of controlled comparisons indicate three guidelines that might change the pipeline for visual recognition.
{"title":"Three Guidelines of Online Learning for Large-Scale Visual Recognition","authors":"Y. Ushiku, Masatoshi Hidaka, T. Harada","doi":"10.1109/CVPR.2014.457","DOIUrl":"https://doi.org/10.1109/CVPR.2014.457","url":null,"abstract":"In this paper, we would like to evaluate online learning algorithms for large-scale visual recognition using state-of-the-art features which are preselected and held fixed. Today, combinations of high-dimensional features and linear classifiers are widely used for large-scale visual recognition. Numerous so-called mid-level features have been developed and mutually compared on an experimental basis. Although various learning methods for linear classification have also been proposed in the machine learning and natural language processing literature, they have rarely been evaluated for visual recognition. Therefore, we give guidelines via investigations of state-of-the-art online learning methods of linear classifiers. Many methods have been evaluated using toy data and natural language processing problems such as document classification. Consequently, we gave those methods a unified interpretation from the viewpoint of visual recognition. Results of controlled comparisons indicate three guidelines that might change the pipeline for visual recognition.","PeriodicalId":319578,"journal":{"name":"2014 IEEE Conference on Computer Vision and Pattern Recognition","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125238758","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}
We propose a joint foreground-background mixture model (FBM) that simultaneously performs background estimation and motion segmentation in complex dynamic scenes. Our FBM consist of a set of location-specific dynamic texture (DT) components, for modeling local background motion, and set of global DT components, for modeling consistent foreground motion. We derive an EM algorithm for estimating the parameters of the FBM. We also apply spatial constraints to the FBM using an Markov random field grid, and derive a corresponding variational approximation for inference. Unlike existing approaches to background subtraction, our FBM does not require a manually selected threshold or a separate training video. Unlike existing motion segmentation techniques, our FBM can segment foreground motions over complex background with mixed motions, and detect stopped objects. Since most dynamic scene datasets only contain videos with a single foreground object over a simple background, we develop a new challenging dataset with multiple foreground objects over complex dynamic backgrounds. In experiments, we show that jointly modeling the background and foreground segments with FBM yields significant improvements in accuracy on both background estimation and motion segmentation, compared to state-of-the-art methods.
{"title":"Joint Motion Segmentation and Background Estimation in Dynamic Scenes","authors":"Adeel Mumtaz, Weichen Zhang, Antoni B. Chan","doi":"10.1109/CVPR.2014.54","DOIUrl":"https://doi.org/10.1109/CVPR.2014.54","url":null,"abstract":"We propose a joint foreground-background mixture model (FBM) that simultaneously performs background estimation and motion segmentation in complex dynamic scenes. Our FBM consist of a set of location-specific dynamic texture (DT) components, for modeling local background motion, and set of global DT components, for modeling consistent foreground motion. We derive an EM algorithm for estimating the parameters of the FBM. We also apply spatial constraints to the FBM using an Markov random field grid, and derive a corresponding variational approximation for inference. Unlike existing approaches to background subtraction, our FBM does not require a manually selected threshold or a separate training video. Unlike existing motion segmentation techniques, our FBM can segment foreground motions over complex background with mixed motions, and detect stopped objects. Since most dynamic scene datasets only contain videos with a single foreground object over a simple background, we develop a new challenging dataset with multiple foreground objects over complex dynamic backgrounds. In experiments, we show that jointly modeling the background and foreground segments with FBM yields significant improvements in accuracy on both background estimation and motion segmentation, compared to state-of-the-art methods.","PeriodicalId":319578,"journal":{"name":"2014 IEEE Conference on Computer Vision and Pattern Recognition","volume":"231 7","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120890056","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}
Mingsheng Long, Jianmin Wang, Guiguang Ding, Jiaguang Sun, Philip S. Yu
Visual domain adaptation, which learns an accurate classifier for a new domain using labeled images from an old domain, has shown promising value in computer vision yet still been a challenging problem. Most prior works have explored two learning strategies independently for domain adaptation: feature matching and instance reweighting. In this paper, we show that both strategies are important and inevitable when the domain difference is substantially large. We therefore put forward a novel Transfer Joint Matching (TJM) approach to model them in a unified optimization problem. Specifically, TJM aims to reduce the domain difference by jointly matching the features and reweighting the instances across domains in a principled dimensionality reduction procedure, and construct new feature representation that is invariant to both the distribution difference and the irrelevant instances. Comprehensive experimental results verify that TJM can significantly outperform competitive methods for cross-domain image recognition problems.
{"title":"Transfer Joint Matching for Unsupervised Domain Adaptation","authors":"Mingsheng Long, Jianmin Wang, Guiguang Ding, Jiaguang Sun, Philip S. Yu","doi":"10.1109/CVPR.2014.183","DOIUrl":"https://doi.org/10.1109/CVPR.2014.183","url":null,"abstract":"Visual domain adaptation, which learns an accurate classifier for a new domain using labeled images from an old domain, has shown promising value in computer vision yet still been a challenging problem. Most prior works have explored two learning strategies independently for domain adaptation: feature matching and instance reweighting. In this paper, we show that both strategies are important and inevitable when the domain difference is substantially large. We therefore put forward a novel Transfer Joint Matching (TJM) approach to model them in a unified optimization problem. Specifically, TJM aims to reduce the domain difference by jointly matching the features and reweighting the instances across domains in a principled dimensionality reduction procedure, and construct new feature representation that is invariant to both the distribution difference and the irrelevant instances. Comprehensive experimental results verify that TJM can significantly outperform competitive methods for cross-domain image recognition problems.","PeriodicalId":319578,"journal":{"name":"2014 IEEE Conference on Computer Vision and Pattern Recognition","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124819129","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}
We advocate the inference of qualitative information about 3D human pose, called posebits, from images. Posebits represent Boolean geometric relationships between body parts (e.g., left-leg in front of right-leg or hands close to each other). The advantages of posebits as a mid-level representation are 1) for many tasks of interest, such qualitative pose information may be sufficient (e.g., semantic image retrieval), 2) it is relatively easy to annotate large image corpora with posebits, as it simply requires answers to yes/no questions, and 3) they help resolve challenging pose ambiguities and therefore facilitate the difficult talk of image-based 3D pose estimation. We introduce posebits, a posebit database, a method for selecting useful posebits for pose estimation and a structural SVM model for posebit inference. Experiments show the use of posebits for semantic image retrieval and for improving 3D pose estimation.
{"title":"Posebits for Monocular Human Pose Estimation","authors":"Gerard Pons-Moll, David J. Fleet, B. Rosenhahn","doi":"10.1109/CVPR.2014.300","DOIUrl":"https://doi.org/10.1109/CVPR.2014.300","url":null,"abstract":"We advocate the inference of qualitative information about 3D human pose, called posebits, from images. Posebits represent Boolean geometric relationships between body parts (e.g., left-leg in front of right-leg or hands close to each other). The advantages of posebits as a mid-level representation are 1) for many tasks of interest, such qualitative pose information may be sufficient (e.g., semantic image retrieval), 2) it is relatively easy to annotate large image corpora with posebits, as it simply requires answers to yes/no questions, and 3) they help resolve challenging pose ambiguities and therefore facilitate the difficult talk of image-based 3D pose estimation. We introduce posebits, a posebit database, a method for selecting useful posebits for pose estimation and a structural SVM model for posebit inference. Experiments show the use of posebits for semantic image retrieval and for improving 3D pose estimation.","PeriodicalId":319578,"journal":{"name":"2014 IEEE Conference on Computer Vision and Pattern Recognition","volume":"19 5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125013843","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：