Pub Date : 2011-11-06DOI: 10.1109/ICCV.2011.6126449
T. Tuytelaars, Mario Fritz, Kate Saenko, Trevor Darrell
Naive Bayes Nearest Neighbor (NBNN) has recently been proposed as a powerful, non-parametric approach for object classification, that manages to achieve remarkably good results thanks to the avoidance of a vector quantization step and the use of image-to-class comparisons, yielding good generalization. In this paper, we introduce a kernelized version of NBNN. This way, we can learn the classifier in a discriminative setting. Moreover, it then becomes straightforward to combine it with other kernels. In particular, we show that our NBNN kernel is complementary to standard bag-of-features based kernels, focussing on local generalization as opposed to global image composition. By combining them, we achieve state-of-the-art results on Caltech101 and 15 Scenes datasets. As a side contribution, we also investigate how to speed up the NBNN computations.
{"title":"The NBNN kernel","authors":"T. Tuytelaars, Mario Fritz, Kate Saenko, Trevor Darrell","doi":"10.1109/ICCV.2011.6126449","DOIUrl":"https://doi.org/10.1109/ICCV.2011.6126449","url":null,"abstract":"Naive Bayes Nearest Neighbor (NBNN) has recently been proposed as a powerful, non-parametric approach for object classification, that manages to achieve remarkably good results thanks to the avoidance of a vector quantization step and the use of image-to-class comparisons, yielding good generalization. In this paper, we introduce a kernelized version of NBNN. This way, we can learn the classifier in a discriminative setting. Moreover, it then becomes straightforward to combine it with other kernels. In particular, we show that our NBNN kernel is complementary to standard bag-of-features based kernels, focussing on local generalization as opposed to global image composition. By combining them, we achieve state-of-the-art results on Caltech101 and 15 Scenes datasets. As a side contribution, we also investigate how to speed up the NBNN computations.","PeriodicalId":6391,"journal":{"name":"2011 International Conference on Computer Vision","volume":"426 1","pages":"1824-1831"},"PeriodicalIF":0.0,"publicationDate":"2011-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77859656","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.2011.6126476
Rongjie Lai, Yonggang Shi, N. Sicotte, A. Toga
Corpus callosum (CC) is an important structure in human brain anatomy. In this work, we propose a fully automated and robust approach to extract corpus callosum from T1-weighted structural MR images. The novelty of our method is composed of two key steps. In the first step, we find an initial guess for the curve representation of CC by using the zero level set of the first nontrivial Laplace-Beltrami (LB) eigenfunction on the white matter surface. In the second step, the initial curve is deformed toward the final solution with a geodesic curvature flow on the white matter surface. For numerical solution of the geodesic curvature flow on surfaces, we represent the contour implicitly on a triangular mesh and develop efficient numerical schemes based on finite element method. Because our method depends only on the intrinsic geometry of the white matter surface, it is robust to orientation differences of the brain across population. In our experiments, we validate the proposed algorithm on 32 brains from a clinical study of multiple sclerosis disease and demonstrate that the accuracy of our results.
{"title":"Automated corpus callosum extraction via Laplace-Beltrami nodal parcellation and intrinsic geodesic curvature flows on surfaces","authors":"Rongjie Lai, Yonggang Shi, N. Sicotte, A. Toga","doi":"10.1109/ICCV.2011.6126476","DOIUrl":"https://doi.org/10.1109/ICCV.2011.6126476","url":null,"abstract":"Corpus callosum (CC) is an important structure in human brain anatomy. In this work, we propose a fully automated and robust approach to extract corpus callosum from T1-weighted structural MR images. The novelty of our method is composed of two key steps. In the first step, we find an initial guess for the curve representation of CC by using the zero level set of the first nontrivial Laplace-Beltrami (LB) eigenfunction on the white matter surface. In the second step, the initial curve is deformed toward the final solution with a geodesic curvature flow on the white matter surface. For numerical solution of the geodesic curvature flow on surfaces, we represent the contour implicitly on a triangular mesh and develop efficient numerical schemes based on finite element method. Because our method depends only on the intrinsic geometry of the white matter surface, it is robust to orientation differences of the brain across population. In our experiments, we validate the proposed algorithm on 32 brains from a clinical study of multiple sclerosis disease and demonstrate that the accuracy of our results.","PeriodicalId":6391,"journal":{"name":"2011 International Conference on Computer Vision","volume":"401 1","pages":"2034-2040"},"PeriodicalIF":0.0,"publicationDate":"2011-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76641952","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.2011.6126474
Matthew D. Zeiler, Graham W. Taylor, R. Fergus
We present a hierarchical model that learns image decompositions via alternating layers of convolutional sparse coding and max pooling. When trained on natural images, the layers of our model capture image information in a variety of forms: low-level edges, mid-level edge junctions, high-level object parts and complete objects. To build our model we rely on a novel inference scheme that ensures each layer reconstructs the input, rather than just the output of the layer directly beneath, as is common with existing hierarchical approaches. This makes it possible to learn multiple layers of representation and we show models with 4 layers, trained on images from the Caltech-101 and 256 datasets. When combined with a standard classifier, features extracted from these models outperform SIFT, as well as representations from other feature learning methods.
{"title":"Adaptive deconvolutional networks for mid and high level feature learning","authors":"Matthew D. Zeiler, Graham W. Taylor, R. Fergus","doi":"10.1109/ICCV.2011.6126474","DOIUrl":"https://doi.org/10.1109/ICCV.2011.6126474","url":null,"abstract":"We present a hierarchical model that learns image decompositions via alternating layers of convolutional sparse coding and max pooling. When trained on natural images, the layers of our model capture image information in a variety of forms: low-level edges, mid-level edge junctions, high-level object parts and complete objects. To build our model we rely on a novel inference scheme that ensures each layer reconstructs the input, rather than just the output of the layer directly beneath, as is common with existing hierarchical approaches. This makes it possible to learn multiple layers of representation and we show models with 4 layers, trained on images from the Caltech-101 and 256 datasets. When combined with a standard classifier, features extracted from these models outperform SIFT, as well as representations from other feature learning methods.","PeriodicalId":6391,"journal":{"name":"2011 International Conference on Computer Vision","volume":"3 1","pages":"2018-2025"},"PeriodicalIF":0.0,"publicationDate":"2011-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77059727","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.2011.6126338
Carsten Stoll, N. Hasler, Juergen Gall, H. Seidel, C. Theobalt
We present an approach for modeling the human body by Sums of spatial Gaussians (SoG), allowing us to perform fast and high-quality markerless motion capture from multi-view video sequences. The SoG model is equipped with a color model to represent the shape and appearance of the human and can be reconstructed from a sparse set of images. Similar to the human body, we also represent the image domain as SoG that models color consistent image blobs. Based on the SoG models of the image and the human body, we introduce a novel continuous and differentiable model-to-image similarity measure that can be used to estimate the skeletal motion of a human at 5–15 frames per second even for many camera views. In our experiments, we show that our method, which does not rely on silhouettes or training data, offers an good balance between accuracy and computational cost.
{"title":"Fast articulated motion tracking using a sums of Gaussians body model","authors":"Carsten Stoll, N. Hasler, Juergen Gall, H. Seidel, C. Theobalt","doi":"10.1109/ICCV.2011.6126338","DOIUrl":"https://doi.org/10.1109/ICCV.2011.6126338","url":null,"abstract":"We present an approach for modeling the human body by Sums of spatial Gaussians (SoG), allowing us to perform fast and high-quality markerless motion capture from multi-view video sequences. The SoG model is equipped with a color model to represent the shape and appearance of the human and can be reconstructed from a sparse set of images. Similar to the human body, we also represent the image domain as SoG that models color consistent image blobs. Based on the SoG models of the image and the human body, we introduce a novel continuous and differentiable model-to-image similarity measure that can be used to estimate the skeletal motion of a human at 5–15 frames per second even for many camera views. In our experiments, we show that our method, which does not rely on silhouettes or training data, offers an good balance between accuracy and computational cost.","PeriodicalId":6391,"journal":{"name":"2011 International Conference on Computer Vision","volume":"416 1","pages":"951-958"},"PeriodicalIF":0.0,"publicationDate":"2011-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80105962","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.2011.6126444
L. Marchesotti, F. Perronnin, Diane Larlus, G. Csurka
In this paper, we automatically assess the aesthetic properties of images. In the past, this problem has been addressed by hand-crafting features which would correlate with best photographic practices (e.g. “Does this image respect the rule of thirds?”) or with photographic techniques (e.g. “Is this image a macro?”). We depart from this line of research and propose to use generic image descriptors to assess aesthetic quality. We experimentally show that the descriptors we use, which aggregate statistics computed from low-level local features, implicitly encode the aesthetic properties explicitly used by state-of-the-art methods and outperform them by a significant margin.
{"title":"Assessing the aesthetic quality of photographs using generic image descriptors","authors":"L. Marchesotti, F. Perronnin, Diane Larlus, G. Csurka","doi":"10.1109/ICCV.2011.6126444","DOIUrl":"https://doi.org/10.1109/ICCV.2011.6126444","url":null,"abstract":"In this paper, we automatically assess the aesthetic properties of images. In the past, this problem has been addressed by hand-crafting features which would correlate with best photographic practices (e.g. “Does this image respect the rule of thirds?”) or with photographic techniques (e.g. “Is this image a macro?”). We depart from this line of research and propose to use generic image descriptors to assess aesthetic quality. We experimentally show that the descriptors we use, which aggregate statistics computed from low-level local features, implicitly encode the aesthetic properties explicitly used by state-of-the-art methods and outperform them by a significant margin.","PeriodicalId":6391,"journal":{"name":"2011 International Conference on Computer Vision","volume":"180 1","pages":"1784-1791"},"PeriodicalIF":0.0,"publicationDate":"2011-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75471472","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.2011.6126371
H. Jung, Kyoung Mu Lee, Sang Uk Lee
Under the popular Bayesian approach, a stereo problem can be formulated by defining likelihood and prior. Likelihoods are often associated with unary terms and priors are defined by pair-wise or higher order cliques in Markov random field (MRF). In this paper, we propose to use high order likelihood model in stereo. Numerous conventional patch based matching methods such as normalized cross correlation, Laplacian of Gaussian, or census filters are designed under the naive assumption that all the pixels of a patch have the same disparities. However, patch-wise cost can be formulated as higher order cliques for MRF so that the matching cost is a function of image patch's disparities. A patch obtained from the projected image by a disparity map should provide a better match without the blurring effect around disparity discontinuities. Among patch-wise high order matching costs, the census filter approach can be easily reduced to pair-wise cliques. The experimental results on census filter-based high order likelihood demonstrate the advantages of high order likelihood over independent identically distributed unary model.
{"title":"Stereo reconstruction using high order likelihood","authors":"H. Jung, Kyoung Mu Lee, Sang Uk Lee","doi":"10.1109/ICCV.2011.6126371","DOIUrl":"https://doi.org/10.1109/ICCV.2011.6126371","url":null,"abstract":"Under the popular Bayesian approach, a stereo problem can be formulated by defining likelihood and prior. Likelihoods are often associated with unary terms and priors are defined by pair-wise or higher order cliques in Markov random field (MRF). In this paper, we propose to use high order likelihood model in stereo. Numerous conventional patch based matching methods such as normalized cross correlation, Laplacian of Gaussian, or census filters are designed under the naive assumption that all the pixels of a patch have the same disparities. However, patch-wise cost can be formulated as higher order cliques for MRF so that the matching cost is a function of image patch's disparities. A patch obtained from the projected image by a disparity map should provide a better match without the blurring effect around disparity discontinuities. Among patch-wise high order matching costs, the census filter approach can be easily reduced to pair-wise cliques. The experimental results on census filter-based high order likelihood demonstrate the advantages of high order likelihood over independent identically distributed unary model.","PeriodicalId":6391,"journal":{"name":"2011 International Conference on Computer Vision","volume":"9 1","pages":"1211-1218"},"PeriodicalIF":0.0,"publicationDate":"2011-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78876754","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.2011.6126283
Devi Parikh
The performance of current state-of-the-art computer vision algorithms at image classification falls significantly short as compared to human abilities. To reduce this gap, it is important for the community to know what problems to solve, and not just how to solve them. Towards this goal, via the use of jumbled images, we strip apart two widely investigated aspects: local and global information in images, and identify the performance bottleneck. Interestingly, humans have been shown to reliably recognize jumbled images. The goal of our paper is to determine a functional model that mimics how humans recognize jumbled images i.e. exploit local information alone, and further evaluate if existing implementations of this computational model suffice to match human performance. Surprisingly, in our series of human studies and machine experiments, we find that a simple bag-of-words based majority-vote-like strategy is an accurate functional model of how humans recognize jumbled images. Moreover, a straightforward machine implementation of this model achieves accuracies similar to human subjects at classifying jumbled images. This indicates that perhaps existing machine vision techniques already leverage local information from images effectively, and future research efforts should be focused on more advanced modeling of global information.
{"title":"Recognizing jumbled images: The role of local and global information in image classification","authors":"Devi Parikh","doi":"10.1109/ICCV.2011.6126283","DOIUrl":"https://doi.org/10.1109/ICCV.2011.6126283","url":null,"abstract":"The performance of current state-of-the-art computer vision algorithms at image classification falls significantly short as compared to human abilities. To reduce this gap, it is important for the community to know what problems to solve, and not just how to solve them. Towards this goal, via the use of jumbled images, we strip apart two widely investigated aspects: local and global information in images, and identify the performance bottleneck. Interestingly, humans have been shown to reliably recognize jumbled images. The goal of our paper is to determine a functional model that mimics how humans recognize jumbled images i.e. exploit local information alone, and further evaluate if existing implementations of this computational model suffice to match human performance. Surprisingly, in our series of human studies and machine experiments, we find that a simple bag-of-words based majority-vote-like strategy is an accurate functional model of how humans recognize jumbled images. Moreover, a straightforward machine implementation of this model achieves accuracies similar to human subjects at classifying jumbled images. This indicates that perhaps existing machine vision techniques already leverage local information from images effectively, and future research efforts should be focused on more advanced modeling of global information.","PeriodicalId":6391,"journal":{"name":"2011 International Conference on Computer Vision","volume":"196 1","pages":"519-526"},"PeriodicalIF":0.0,"publicationDate":"2011-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79855633","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.2011.6126532
João F. Henriques, Rui Caseiro, Jorge P. Batista
Multiple object tracking has been formulated recently as a global optimization problem, and solved efficiently with optimal methods such as the Hungarian Algorithm. A severe limitation is the inability to model multiple objects that are merged into a single measurement, and track them as a group, while retaining optimality. This work presents a new graph structure that encodes these multiple-match events as standard one-to-one matches, allowing computation of the solution in polynomial time. Since identities are lost when objects merge, an efficient method to identify groups is also presented, as a flow circulation problem. The problem of tracking individual objects across groups is then posed as a standard optimal assignment. Experiments show increased performance on the PETS 2006 and 2009 datasets compared to state-of-the-art algorithms.
{"title":"Globally optimal solution to multi-object tracking with merged measurements","authors":"João F. Henriques, Rui Caseiro, Jorge P. Batista","doi":"10.1109/ICCV.2011.6126532","DOIUrl":"https://doi.org/10.1109/ICCV.2011.6126532","url":null,"abstract":"Multiple object tracking has been formulated recently as a global optimization problem, and solved efficiently with optimal methods such as the Hungarian Algorithm. A severe limitation is the inability to model multiple objects that are merged into a single measurement, and track them as a group, while retaining optimality. This work presents a new graph structure that encodes these multiple-match events as standard one-to-one matches, allowing computation of the solution in polynomial time. Since identities are lost when objects merge, an efficient method to identify groups is also presented, as a flow circulation problem. The problem of tracking individual objects across groups is then posed as a standard optimal assignment. Experiments show increased performance on the PETS 2006 and 2009 datasets compared to state-of-the-art algorithms.","PeriodicalId":6391,"journal":{"name":"2011 International Conference on Computer Vision","volume":"13 1","pages":"2470-2477"},"PeriodicalIF":0.0,"publicationDate":"2011-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80244644","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.2011.6126425
Nobuyuki Morioka, S. Satoh
Spatial relationships between local features are thought to play a vital role in representing object categories. However, learning a compact set of higher-order spatial features based on visual words, e.g., doublets and triplets, remains a challenging problem as possible combinations of visual words grow exponentially. While the local pairwise codebook achieves a compact codebook of pairs of spatially close local features without feature selection, its formulation is not scale invariant and is only suitable for densely sampled local features. In contrast, the proximity distribution kernel is a scale-invariant and robust representation capturing rich spatial proximity information between local features, but its representation grows quadratically in the number of visual words. Inspired by the two abovementioned techniques, this paper presents the compact correlation coding that combines the strengths of the two. Our method achieves a compact representation that is scaleinvariant and robust against object deformation. In addition, we adopt sparse coding instead of k-means clustering during the codebook construction to increase the discriminative power of our method. We systematically evaluate our method against both the local pairwise codebook and proximity distribution kernel on several challenging object categorization datasets to show performance improvements.
{"title":"Compact correlation coding for visual object categorization","authors":"Nobuyuki Morioka, S. Satoh","doi":"10.1109/ICCV.2011.6126425","DOIUrl":"https://doi.org/10.1109/ICCV.2011.6126425","url":null,"abstract":"Spatial relationships between local features are thought to play a vital role in representing object categories. However, learning a compact set of higher-order spatial features based on visual words, e.g., doublets and triplets, remains a challenging problem as possible combinations of visual words grow exponentially. While the local pairwise codebook achieves a compact codebook of pairs of spatially close local features without feature selection, its formulation is not scale invariant and is only suitable for densely sampled local features. In contrast, the proximity distribution kernel is a scale-invariant and robust representation capturing rich spatial proximity information between local features, but its representation grows quadratically in the number of visual words. Inspired by the two abovementioned techniques, this paper presents the compact correlation coding that combines the strengths of the two. Our method achieves a compact representation that is scaleinvariant and robust against object deformation. In addition, we adopt sparse coding instead of k-means clustering during the codebook construction to increase the discriminative power of our method. We systematically evaluate our method against both the local pairwise codebook and proximity distribution kernel on several challenging object categorization datasets to show performance improvements.","PeriodicalId":6391,"journal":{"name":"2011 International Conference on Computer Vision","volume":"146 1","pages":"1639-1646"},"PeriodicalIF":0.0,"publicationDate":"2011-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80541833","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.2011.6126477
A. J. Ma, P. Yuen
This paper addresses the independent assumption issue in fusion process. In the last decade, dependency modeling techniques were developed under a specific distribution of classifiers. This paper proposes a new framework to model the dependency between features without any assumption on feature/classifier distribution. In this paper, we prove that feature dependency can be modeled by a linear combination of the posterior probabilities under some mild assumptions. Based on the linear combination property, two methods, namely Linear Classifier Dependency Modeling (LCDM) and Linear Feature Dependency Modeling (LFDM), are derived and developed for dependency modeling in classifier level and feature level, respectively. The optimal models for LCDM and LFDM are learned by maximizing the margin between the genuine and imposter posterior probabilities. Both synthetic data and real datasets are used for experiments. Experimental results show that LFDM outperforms all existing combination methods.
{"title":"Linear dependency modeling for feature fusion","authors":"A. J. Ma, P. Yuen","doi":"10.1109/ICCV.2011.6126477","DOIUrl":"https://doi.org/10.1109/ICCV.2011.6126477","url":null,"abstract":"This paper addresses the independent assumption issue in fusion process. In the last decade, dependency modeling techniques were developed under a specific distribution of classifiers. This paper proposes a new framework to model the dependency between features without any assumption on feature/classifier distribution. In this paper, we prove that feature dependency can be modeled by a linear combination of the posterior probabilities under some mild assumptions. Based on the linear combination property, two methods, namely Linear Classifier Dependency Modeling (LCDM) and Linear Feature Dependency Modeling (LFDM), are derived and developed for dependency modeling in classifier level and feature level, respectively. The optimal models for LCDM and LFDM are learned by maximizing the margin between the genuine and imposter posterior probabilities. Both synthetic data and real datasets are used for experiments. Experimental results show that LFDM outperforms all existing combination methods.","PeriodicalId":6391,"journal":{"name":"2011 International Conference on Computer Vision","volume":"25 1","pages":"2041-2048"},"PeriodicalIF":0.0,"publicationDate":"2011-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82734205","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：