We introduce a convex optimization modeling framework that transforms a convex optimization problem expressed in a form natural and convenient for the user into an equivalent cone program in a way that preserves fast linear transforms in the original problem. By representing linear functions in the transformation process not as matrices, but as graphs that encode composition of abstract linear operators, we arrive at a matrix-free cone program, i.e., one whose data matrix is represented by an abstract linear operator and its adjoint. This cone program can then be solved by a matrix-free cone solver. By combining the matrix-free modeling framework and cone solver, we obtain a general method for efficiently solving convex optimization problems involving fast linear transforms.
{"title":"Convex Optimization with Abstract Linear Operators","authors":"Steven Diamond, Stephen P. Boyd","doi":"10.1109/ICCV.2015.84","DOIUrl":"https://doi.org/10.1109/ICCV.2015.84","url":null,"abstract":"We introduce a convex optimization modeling framework that transforms a convex optimization problem expressed in a form natural and convenient for the user into an equivalent cone program in a way that preserves fast linear transforms in the original problem. By representing linear functions in the transformation process not as matrices, but as graphs that encode composition of abstract linear operators, we arrive at a matrix-free cone program, i.e., one whose data matrix is represented by an abstract linear operator and its adjoint. This cone program can then be solved by a matrix-free cone solver. By combining the matrix-free modeling framework and cone solver, we obtain a general method for efficiently solving convex optimization problems involving fast linear transforms.","PeriodicalId":6633,"journal":{"name":"2015 IEEE International Conference on Computer Vision (ICCV)","volume":"53 1","pages":"675-683"},"PeriodicalIF":0.0,"publicationDate":"2015-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88770474","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}
Dongjin Song, W. Liu, R. Ji, David A. Meyer, John R. Smith
In recent years, binary coding techniques are becoming increasingly popular because of their high efficiency in handling large-scale computer vision applications. It has been demonstrated that supervised binary coding techniques that leverage supervised information can significantly enhance the coding quality, and hence greatly benefit visual search tasks. Typically, a modern binary coding method seeks to learn a group of coding functions which compress data samples into binary codes. However, few methods pursued the coding functions such that the precision at the top of a ranking list according to Hamming distances of the generated binary codes is optimized. In this paper, we propose a novel supervised binary coding approach, namely Top Rank Supervised Binary Coding (Top-RSBC), which explicitly focuses on optimizing the precision of top positions in a Hamming-distance ranking list towards preserving the supervision information. The core idea is to train the disciplined coding functions, by which the mistakes at the top of a Hamming-distance ranking list are penalized more than those at the bottom. To solve such coding functions, we relax the original discrete optimization objective with a continuous surrogate, and derive a stochastic gradient descent to optimize the surrogate objective. To further reduce the training time cost, we also design an online learning algorithm to optimize the surrogate objective more efficiently. Empirical studies based upon three benchmark image datasets demonstrate that the proposed binary coding approach achieves superior image search accuracy over the state-of-the-arts.
{"title":"Top Rank Supervised Binary Coding for Visual Search","authors":"Dongjin Song, W. Liu, R. Ji, David A. Meyer, John R. Smith","doi":"10.1109/ICCV.2015.223","DOIUrl":"https://doi.org/10.1109/ICCV.2015.223","url":null,"abstract":"In recent years, binary coding techniques are becoming increasingly popular because of their high efficiency in handling large-scale computer vision applications. It has been demonstrated that supervised binary coding techniques that leverage supervised information can significantly enhance the coding quality, and hence greatly benefit visual search tasks. Typically, a modern binary coding method seeks to learn a group of coding functions which compress data samples into binary codes. However, few methods pursued the coding functions such that the precision at the top of a ranking list according to Hamming distances of the generated binary codes is optimized. In this paper, we propose a novel supervised binary coding approach, namely Top Rank Supervised Binary Coding (Top-RSBC), which explicitly focuses on optimizing the precision of top positions in a Hamming-distance ranking list towards preserving the supervision information. The core idea is to train the disciplined coding functions, by which the mistakes at the top of a Hamming-distance ranking list are penalized more than those at the bottom. To solve such coding functions, we relax the original discrete optimization objective with a continuous surrogate, and derive a stochastic gradient descent to optimize the surrogate objective. To further reduce the training time cost, we also design an online learning algorithm to optimize the surrogate objective more efficiently. Empirical studies based upon three benchmark image datasets demonstrate that the proposed binary coding approach achieves superior image search accuracy over the state-of-the-arts.","PeriodicalId":6633,"journal":{"name":"2015 IEEE International Conference on Computer Vision (ICCV)","volume":"12 1","pages":"1922-1930"},"PeriodicalIF":0.0,"publicationDate":"2015-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90671401","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}
Unsupervised and weakly-supervised visual learning in large image collections are critical in order to avoid the time-consuming and error-prone process of manual labeling. Standard approaches rely on methods like multiple-instance learning or graphical models, which can be computationally intensive and sensitive to initialization. On the other hand, simpler component analysis or clustering methods usually cannot achieve meaningful invariances or semantic interpretability. To address the issues of previous work, we present a simple but effective method called Semantic Component Analysis (SCA), which provides a decomposition of images into semantic components. Unsupervised SCA decomposes additive image representations into spatially-meaningful visual components that naturally correspond to object categories. Using an overcomplete representation that allows for rich instance-level constraints and spatial priors, SCA gives improved results and more interpretable components in comparison to traditional matrix factorization techniques. If weakly-supervised information is available in the form of image-level tags, SCA factorizes a set of images into semantic groups of superpixels. We also provide qualitative connections to traditional methods for component analysis (e.g. Grassmann averages, PCA, and NMF). The effectiveness of our approach is validated through synthetic data and on the MSRC2 and Sift Flow datasets, demonstrating competitive results in unsupervised and weakly-supervised semantic segmentation.
{"title":"Semantic Component Analysis","authors":"Calvin Murdock, F. D. L. Torre","doi":"10.1109/ICCV.2015.174","DOIUrl":"https://doi.org/10.1109/ICCV.2015.174","url":null,"abstract":"Unsupervised and weakly-supervised visual learning in large image collections are critical in order to avoid the time-consuming and error-prone process of manual labeling. Standard approaches rely on methods like multiple-instance learning or graphical models, which can be computationally intensive and sensitive to initialization. On the other hand, simpler component analysis or clustering methods usually cannot achieve meaningful invariances or semantic interpretability. To address the issues of previous work, we present a simple but effective method called Semantic Component Analysis (SCA), which provides a decomposition of images into semantic components. Unsupervised SCA decomposes additive image representations into spatially-meaningful visual components that naturally correspond to object categories. Using an overcomplete representation that allows for rich instance-level constraints and spatial priors, SCA gives improved results and more interpretable components in comparison to traditional matrix factorization techniques. If weakly-supervised information is available in the form of image-level tags, SCA factorizes a set of images into semantic groups of superpixels. We also provide qualitative connections to traditional methods for component analysis (e.g. Grassmann averages, PCA, and NMF). The effectiveness of our approach is validated through synthetic data and on the MSRC2 and Sift Flow datasets, demonstrating competitive results in unsupervised and weakly-supervised semantic segmentation.","PeriodicalId":6633,"journal":{"name":"2015 IEEE International Conference on Computer Vision (ICCV)","volume":"1 1","pages":"1484-1492"},"PeriodicalIF":0.0,"publicationDate":"2015-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89461337","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}
Jorge García, N. Martinel, C. Micheloni, Alfredo Gardel Vicente
Person re-identification is an open and challenging problem in computer vision. Existing re-identification approaches focus on optimal methods for features matching (e.g., metric learning approaches) or study the inter-camera transformations of such features. These methods hardly ever pay attention to the problem of visual ambiguities shared between the first ranks. In this paper, we focus on such a problem and introduce an unsupervised ranking optimization approach based on discriminant context information analysis. The proposed approach refines a given initial ranking by removing the visual ambiguities common to first ranks. This is achieved by analyzing their content and context information. Extensive experiments on three publicly available benchmark datasets and different baseline methods have been conducted. Results demonstrate a remarkable improvement in the first positions of the ranking. Regardless of the selected dataset, state-of-the-art methods are strongly outperformed by our method.
{"title":"Person Re-Identification Ranking Optimisation by Discriminant Context Information Analysis","authors":"Jorge García, N. Martinel, C. Micheloni, Alfredo Gardel Vicente","doi":"10.1109/ICCV.2015.154","DOIUrl":"https://doi.org/10.1109/ICCV.2015.154","url":null,"abstract":"Person re-identification is an open and challenging problem in computer vision. Existing re-identification approaches focus on optimal methods for features matching (e.g., metric learning approaches) or study the inter-camera transformations of such features. These methods hardly ever pay attention to the problem of visual ambiguities shared between the first ranks. In this paper, we focus on such a problem and introduce an unsupervised ranking optimization approach based on discriminant context information analysis. The proposed approach refines a given initial ranking by removing the visual ambiguities common to first ranks. This is achieved by analyzing their content and context information. Extensive experiments on three publicly available benchmark datasets and different baseline methods have been conducted. Results demonstrate a remarkable improvement in the first positions of the ranking. Regardless of the selected dataset, state-of-the-art methods are strongly outperformed by our method.","PeriodicalId":6633,"journal":{"name":"2015 IEEE International Conference on Computer Vision (ICCV)","volume":"6 1","pages":"1305-1313"},"PeriodicalIF":0.0,"publicationDate":"2015-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89974735","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}
Radial distortion for ordinary (non-fisheye) camera lenses has traditionally been modeled as an infinite series function of radial location of an image pixel from the image center. While there has been enough empirical evidence to show that such a model is accurate and sufficient for radial distortion calibration, there has not been much analysis on the geometric/physical understanding of radial distortion from a camera calibration perspective. In this paper, we show using a thick-lens imaging model, that the variation of entrance pupil location as a function of incident image ray angle is directly responsible for radial distortion in captured images. Thus, unlike as proposed in the current state-of-the-art in camera calibration, radial distortion and entrance pupil movement are equivalent and need not be modeled together. By modeling only entrance pupil motion instead of radial distortion, we achieve two main benefits, first, we obtain comparable if not better pixel re-projection error than traditional methods, second, and more importantly, we directly back-project a radially distorted image pixel along the true image ray which formed it. Using a thick-lens setting, we show that such a back-projection is more accurate than the two-step method of undistorting an image pixel and then back-projecting it. We have applied this calibration method to the problem of generative depth-from-focus using focal stack to get accurate depth estimates.
{"title":"On the Equivalence of Moving Entrance Pupil and Radial Distortion for Camera Calibration","authors":"Avinash Kumar, N. Ahuja","doi":"10.1109/ICCV.2015.270","DOIUrl":"https://doi.org/10.1109/ICCV.2015.270","url":null,"abstract":"Radial distortion for ordinary (non-fisheye) camera lenses has traditionally been modeled as an infinite series function of radial location of an image pixel from the image center. While there has been enough empirical evidence to show that such a model is accurate and sufficient for radial distortion calibration, there has not been much analysis on the geometric/physical understanding of radial distortion from a camera calibration perspective. In this paper, we show using a thick-lens imaging model, that the variation of entrance pupil location as a function of incident image ray angle is directly responsible for radial distortion in captured images. Thus, unlike as proposed in the current state-of-the-art in camera calibration, radial distortion and entrance pupil movement are equivalent and need not be modeled together. By modeling only entrance pupil motion instead of radial distortion, we achieve two main benefits, first, we obtain comparable if not better pixel re-projection error than traditional methods, second, and more importantly, we directly back-project a radially distorted image pixel along the true image ray which formed it. Using a thick-lens setting, we show that such a back-projection is more accurate than the two-step method of undistorting an image pixel and then back-projecting it. We have applied this calibration method to the problem of generative depth-from-focus using focal stack to get accurate depth estimates.","PeriodicalId":6633,"journal":{"name":"2015 IEEE International Conference on Computer Vision (ICCV)","volume":"255 1","pages":"2345-2353"},"PeriodicalIF":0.0,"publicationDate":"2015-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76999998","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}
Natural image modeling plays a key role in many vision problems such as image denoising. Image priors are widely used to regularize the denoising process, which is an ill-posed inverse problem. One category of denoising methods exploit the priors (e.g., TV, sparsity) learned from external clean images to reconstruct the given noisy image, while another category of methods exploit the internal prior (e.g., self-similarity) to reconstruct the latent image. Though the internal prior based methods have achieved impressive denoising results, the improvement of visual quality will become very difficult with the increase of noise level. In this paper, we propose to exploit image external patch prior and internal self-similarity prior jointly, and develop an external patch prior guided internal clustering algorithm for image denoising. It is known that natural image patches form multiple subspaces. By utilizing Gaussian mixture models (GMMs) learning, image similar patches can be clustered and the subspaces can be learned. The learned GMMs from clean images are then used to guide the clustering of noisy-patches of the input noisy images, followed by a low-rank approximation process to estimate the latent subspace for image recovery. Numerical experiments show that the proposed method outperforms many state-of-the-art denoising algorithms such as BM3D and WNNM.
{"title":"External Patch Prior Guided Internal Clustering for Image Denoising","authors":"Fei Chen, Lei Zhang, Huimin Yu","doi":"10.1109/ICCV.2015.76","DOIUrl":"https://doi.org/10.1109/ICCV.2015.76","url":null,"abstract":"Natural image modeling plays a key role in many vision problems such as image denoising. Image priors are widely used to regularize the denoising process, which is an ill-posed inverse problem. One category of denoising methods exploit the priors (e.g., TV, sparsity) learned from external clean images to reconstruct the given noisy image, while another category of methods exploit the internal prior (e.g., self-similarity) to reconstruct the latent image. Though the internal prior based methods have achieved impressive denoising results, the improvement of visual quality will become very difficult with the increase of noise level. In this paper, we propose to exploit image external patch prior and internal self-similarity prior jointly, and develop an external patch prior guided internal clustering algorithm for image denoising. It is known that natural image patches form multiple subspaces. By utilizing Gaussian mixture models (GMMs) learning, image similar patches can be clustered and the subspaces can be learned. The learned GMMs from clean images are then used to guide the clustering of noisy-patches of the input noisy images, followed by a low-rank approximation process to estimate the latent subspace for image recovery. Numerical experiments show that the proposed method outperforms many state-of-the-art denoising algorithms such as BM3D and WNNM.","PeriodicalId":6633,"journal":{"name":"2015 IEEE International Conference on Computer Vision (ICCV)","volume":"87 1","pages":"603-611"},"PeriodicalIF":0.0,"publicationDate":"2015-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75192741","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 propose a novel method for depth image superresolution which combines recent advances in example based upsampling with variational superresolution based on a known blur kernel. Most traditional depth superresolution approaches try to use additional high resolution intensity images as guidance for superresolution. In our method we learn a dictionary of edge priors from an external database of high and low resolution examples. In a novel variational sparse coding approach this dictionary is used to infer strong edge priors. Additionally to the traditional sparse coding constraints the difference in the overlap of neighboring edge patches is minimized in our optimization. These edge priors are used in a novel variational superresolution as anisotropic guidance of the higher order regularization. Both the sparse coding and the variational superresolution of the depth are solved based on a primal-dual formulation. In an exhaustive numerical and visual evaluation we show that our method clearly outperforms existing approaches on multiple real and synthetic datasets.
{"title":"Variational Depth Superresolution Using Example-Based Edge Representations","authors":"David Ferstl, M. Rüther, H. Bischof","doi":"10.1109/ICCV.2015.66","DOIUrl":"https://doi.org/10.1109/ICCV.2015.66","url":null,"abstract":"In this paper we propose a novel method for depth image superresolution which combines recent advances in example based upsampling with variational superresolution based on a known blur kernel. Most traditional depth superresolution approaches try to use additional high resolution intensity images as guidance for superresolution. In our method we learn a dictionary of edge priors from an external database of high and low resolution examples. In a novel variational sparse coding approach this dictionary is used to infer strong edge priors. Additionally to the traditional sparse coding constraints the difference in the overlap of neighboring edge patches is minimized in our optimization. These edge priors are used in a novel variational superresolution as anisotropic guidance of the higher order regularization. Both the sparse coding and the variational superresolution of the depth are solved based on a primal-dual formulation. In an exhaustive numerical and visual evaluation we show that our method clearly outperforms existing approaches on multiple real and synthetic datasets.","PeriodicalId":6633,"journal":{"name":"2015 IEEE International Conference on Computer Vision (ICCV)","volume":"20 1","pages":"513-521"},"PeriodicalIF":0.0,"publicationDate":"2015-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73593012","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}
Xiaodan Liang, Si Liu, Yunchao Wei, Luoqi Liu, Liang Lin, Shuicheng Yan
Intuitive observations show that a baby may inherently possess the capability of recognizing a new visual concept (e.g., chair, dog) by learning from only very few positive instances taught by parent(s) or others, and this recognition capability can be gradually further improved by exploring and/or interacting with the real instances in the physical world. Inspired by these observations, we propose a computational model for weakly-supervised object detection, based on prior knowledge modelling, exemplar learning and learning with video contexts. The prior knowledge is modeled with a pre-trained Convolutional Neural Network (CNN). When very few instances of a new concept are given, an initial concept detector is built by exemplar learning over the deep features the pre-trained CNN. The well-designed tracking solution is then used to discover more diverse instances from the massive online weakly labeled videos. Once a positive instance is detected/identified with high score in each video, more instances possibly from different view-angles and/or different distances are tracked and accumulated. Then the concept detector can be fine-tuned based on these new instances. This process can be repeated again and again till we obtain a very mature concept detector. Extensive experiments on Pascal VOC-07/10/12 object detection datasets [9] well demonstrate the effectiveness of our framework. It can beat the state-of-the-art full-training based performances by learning from very few samples for each object category, along with about 20,000 weakly labeled videos.
{"title":"Towards Computational Baby Learning: A Weakly-Supervised Approach for Object Detection","authors":"Xiaodan Liang, Si Liu, Yunchao Wei, Luoqi Liu, Liang Lin, Shuicheng Yan","doi":"10.1109/ICCV.2015.120","DOIUrl":"https://doi.org/10.1109/ICCV.2015.120","url":null,"abstract":"Intuitive observations show that a baby may inherently possess the capability of recognizing a new visual concept (e.g., chair, dog) by learning from only very few positive instances taught by parent(s) or others, and this recognition capability can be gradually further improved by exploring and/or interacting with the real instances in the physical world. Inspired by these observations, we propose a computational model for weakly-supervised object detection, based on prior knowledge modelling, exemplar learning and learning with video contexts. The prior knowledge is modeled with a pre-trained Convolutional Neural Network (CNN). When very few instances of a new concept are given, an initial concept detector is built by exemplar learning over the deep features the pre-trained CNN. The well-designed tracking solution is then used to discover more diverse instances from the massive online weakly labeled videos. Once a positive instance is detected/identified with high score in each video, more instances possibly from different view-angles and/or different distances are tracked and accumulated. Then the concept detector can be fine-tuned based on these new instances. This process can be repeated again and again till we obtain a very mature concept detector. Extensive experiments on Pascal VOC-07/10/12 object detection datasets [9] well demonstrate the effectiveness of our framework. It can beat the state-of-the-art full-training based performances by learning from very few samples for each object category, along with about 20,000 weakly labeled videos.","PeriodicalId":6633,"journal":{"name":"2015 IEEE International Conference on Computer Vision (ICCV)","volume":"27 1","pages":"999-1007"},"PeriodicalIF":0.0,"publicationDate":"2015-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73937184","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}
Active learning is an effective way to relieve the tedious work of manual annotation in many applications of visual recognition. However, less research attention has been focused on multi-class active learning. In this paper, we propose a novel Gaussian process classifier model with multiple annotators for multi-class visual recognition. Expectation propagation (EP) is adopted for efficient approximate Bayesian inference of our probabilistic model for classification. Based on the EP approximation inference, a generalized Expectation Maximization (GEM) algorithm is derived to estimate both the parameters for instances and the quality of each individual annotator. Also, we incorporate the idea of reinforcement learning to actively select both the informative samples and the high-quality annotators, which better explores the trade-off between exploitation and exploration. The experiments clearly demonstrate the efficacy of the proposed model.
{"title":"Multi-class Multi-annotator Active Learning with Robust Gaussian Process for Visual Recognition","authors":"Chengjiang Long, G. Hua","doi":"10.1109/ICCV.2015.325","DOIUrl":"https://doi.org/10.1109/ICCV.2015.325","url":null,"abstract":"Active learning is an effective way to relieve the tedious work of manual annotation in many applications of visual recognition. However, less research attention has been focused on multi-class active learning. In this paper, we propose a novel Gaussian process classifier model with multiple annotators for multi-class visual recognition. Expectation propagation (EP) is adopted for efficient approximate Bayesian inference of our probabilistic model for classification. Based on the EP approximation inference, a generalized Expectation Maximization (GEM) algorithm is derived to estimate both the parameters for instances and the quality of each individual annotator. Also, we incorporate the idea of reinforcement learning to actively select both the informative samples and the high-quality annotators, which better explores the trade-off between exploitation and exploration. The experiments clearly demonstrate the efficacy of the proposed model.","PeriodicalId":6633,"journal":{"name":"2015 IEEE International Conference on Computer Vision (ICCV)","volume":"20 1","pages":"2839-2847"},"PeriodicalIF":0.0,"publicationDate":"2015-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84750130","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 method to detect disocclusion in video sequences of three-dimensional scenes and to partition the disoccluded regions into objects, defined by coherent deformation corresponding to surfaces in the scene. Our method infers deformation fields that are piecewise smooth by construction without the need for an explicit regularizer and the associated choice of weight. It then partitions the disoccluded region and groups its components with objects by leveraging on the complementarity of motion and appearance cues: Where appearance changes within an object, motion can usually be reliably inferred and used for grouping. Where appearance is close to constant, it can be used for grouping directly. We integrate both cues in an energy minimization framework, incorporate prior assumptions explicitly into the energy, and propose a numerical scheme.
{"title":"Self-Occlusions and Disocclusions in Causal Video Object Segmentation","authors":"Yanchao Yang, G. Sundaramoorthi, Stefano Soatto","doi":"10.1109/ICCV.2015.501","DOIUrl":"https://doi.org/10.1109/ICCV.2015.501","url":null,"abstract":"We propose a method to detect disocclusion in video sequences of three-dimensional scenes and to partition the disoccluded regions into objects, defined by coherent deformation corresponding to surfaces in the scene. Our method infers deformation fields that are piecewise smooth by construction without the need for an explicit regularizer and the associated choice of weight. It then partitions the disoccluded region and groups its components with objects by leveraging on the complementarity of motion and appearance cues: Where appearance changes within an object, motion can usually be reliably inferred and used for grouping. Where appearance is close to constant, it can be used for grouping directly. We integrate both cues in an energy minimization framework, incorporate prior assumptions explicitly into the energy, and propose a numerical scheme.","PeriodicalId":6633,"journal":{"name":"2015 IEEE International Conference on Computer Vision (ICCV)","volume":"74 1","pages":"4408-4416"},"PeriodicalIF":0.0,"publicationDate":"2015-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85145348","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：