Martin Danelljan, Gustav Häger, F. Khan, M. Felsberg
Robust and accurate visual tracking is one of the most challenging computer vision problems. Due to the inherent lack of training data, a robust approach for constructing a target appearance model is crucial. Recently, discriminatively learned correlation filters (DCF) have been successfully applied to address this problem for tracking. These methods utilize a periodic assumption of the training samples to efficiently learn a classifier on all patches in the target neighborhood. However, the periodic assumption also introduces unwanted boundary effects, which severely degrade the quality of the tracking model. We propose Spatially Regularized Discriminative Correlation Filters (SRDCF) for tracking. A spatial regularization component is introduced in the learning to penalize correlation filter coefficients depending on their spatial location. Our SRDCF formulation allows the correlation filters to be learned on a significantly larger set of negative training samples, without corrupting the positive samples. We further propose an optimization strategy, based on the iterative Gauss-Seidel method, for efficient online learning of our SRDCF. Experiments are performed on four benchmark datasets: OTB-2013, ALOV++, OTB-2015, and VOT2014. Our approach achieves state-of-the-art results on all four datasets. On OTB-2013 and OTB-2015, we obtain an absolute gain of 8.0% and 8.2% respectively, in mean overlap precision, compared to the best existing trackers.
{"title":"Learning Spatially Regularized Correlation Filters for Visual Tracking","authors":"Martin Danelljan, Gustav Häger, F. Khan, M. Felsberg","doi":"10.1109/ICCV.2015.490","DOIUrl":"https://doi.org/10.1109/ICCV.2015.490","url":null,"abstract":"Robust and accurate visual tracking is one of the most challenging computer vision problems. Due to the inherent lack of training data, a robust approach for constructing a target appearance model is crucial. Recently, discriminatively learned correlation filters (DCF) have been successfully applied to address this problem for tracking. These methods utilize a periodic assumption of the training samples to efficiently learn a classifier on all patches in the target neighborhood. However, the periodic assumption also introduces unwanted boundary effects, which severely degrade the quality of the tracking model. We propose Spatially Regularized Discriminative Correlation Filters (SRDCF) for tracking. A spatial regularization component is introduced in the learning to penalize correlation filter coefficients depending on their spatial location. Our SRDCF formulation allows the correlation filters to be learned on a significantly larger set of negative training samples, without corrupting the positive samples. We further propose an optimization strategy, based on the iterative Gauss-Seidel method, for efficient online learning of our SRDCF. Experiments are performed on four benchmark datasets: OTB-2013, ALOV++, OTB-2015, and VOT2014. Our approach achieves state-of-the-art results on all four datasets. On OTB-2013 and OTB-2015, we obtain an absolute gain of 8.0% and 8.2% respectively, in mean overlap precision, compared to the best existing trackers.","PeriodicalId":6633,"journal":{"name":"2015 IEEE International Conference on Computer Vision (ICCV)","volume":"67 1","pages":"4310-4318"},"PeriodicalIF":0.0,"publicationDate":"2015-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91009967","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}
Jaemyun Kim, Adín Ramírez Rivera, Byungyong Ryu, O. Chae
In this paper, we propose a hybrid background model that relies on edge and non-edge features of the image to produce the model. We encode these features into a coding scheme, that we called Local Hybrid Pattern (LHP), that selectively models edges and non-edges features of each pixel. Furthermore, we model each pixel with an adaptive code dictionary to represent the background dynamism, and update it by adding stable codes and discarding unstable ones. We weight each code in the dictionary to enhance its description of the pixel it models. The foreground is detected as the incoming codes that deviate from the dictionary. We can detect (as foreground or background) and classify (as edge or inner region) each pixel simultaneously. We tested our proposed method in existing databases with promising results.
{"title":"Simultaneous Foreground Detection and Classification with Hybrid Features","authors":"Jaemyun Kim, Adín Ramírez Rivera, Byungyong Ryu, O. Chae","doi":"10.1109/ICCV.2015.378","DOIUrl":"https://doi.org/10.1109/ICCV.2015.378","url":null,"abstract":"In this paper, we propose a hybrid background model that relies on edge and non-edge features of the image to produce the model. We encode these features into a coding scheme, that we called Local Hybrid Pattern (LHP), that selectively models edges and non-edges features of each pixel. Furthermore, we model each pixel with an adaptive code dictionary to represent the background dynamism, and update it by adding stable codes and discarding unstable ones. We weight each code in the dictionary to enhance its description of the pixel it models. The foreground is detected as the incoming codes that deviate from the dictionary. We can detect (as foreground or background) and classify (as edge or inner region) each pixel simultaneously. We tested our proposed method in existing databases with promising results.","PeriodicalId":6633,"journal":{"name":"2015 IEEE International Conference on Computer Vision (ICCV)","volume":"319 1","pages":"3307-3315"},"PeriodicalIF":0.0,"publicationDate":"2015-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91473170","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}
Detection of elongated structures in 2D images and 3D image stacks is a critical prerequisite in many applications and Machine Learning-based approaches have recently been shown to deliver superior performance. However, these methods essentially classify individual locations and do not explicitly model the strong relationship that exists between neighboring ones. As a result, isolated erroneous responses, discontinuities, and topological errors are present in the resulting score maps. We solve this problem by projecting patches of the score map to their nearest neighbors in a set of ground truth training patches. Our algorithm induces global spatial consistency on the classifier score map and returns results that are provably geometrically consistent. We apply our algorithm to challenging datasets in four different domains and show that it compares favorably to state-of-the-art methods.
{"title":"Projection onto the Manifold of Elongated Structures for Accurate Extraction","authors":"A. Sironi, V. Lepetit, P. Fua","doi":"10.1109/ICCV.2015.44","DOIUrl":"https://doi.org/10.1109/ICCV.2015.44","url":null,"abstract":"Detection of elongated structures in 2D images and 3D image stacks is a critical prerequisite in many applications and Machine Learning-based approaches have recently been shown to deliver superior performance. However, these methods essentially classify individual locations and do not explicitly model the strong relationship that exists between neighboring ones. As a result, isolated erroneous responses, discontinuities, and topological errors are present in the resulting score maps. We solve this problem by projecting patches of the score map to their nearest neighbors in a set of ground truth training patches. Our algorithm induces global spatial consistency on the classifier score map and returns results that are provably geometrically consistent. We apply our algorithm to challenging datasets in four different domains and show that it compares favorably to state-of-the-art methods.","PeriodicalId":6633,"journal":{"name":"2015 IEEE International Conference on Computer Vision (ICCV)","volume":"20 1","pages":"316-324"},"PeriodicalIF":0.0,"publicationDate":"2015-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74523830","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 provide a new, real photo dataset with precise ground-truth for intrinsic image research. Prior ground-truth datasets have been restricted to rather simple illumination conditions and scene geometries, or have been enhanced using image synthesis methods. The dataset provided in this paper is based on complex multi-illuminant scenarios under multi-colored illumination conditions and challenging cast shadows. We provide full per-pixel intrinsic ground-truth data for these scenarios, i.e. reflectance, specularity, shading, and illumination for scenes as well as preliminary depth information. Furthermore, we evaluate 3 state-of-the-art intrinsic image recovery methods, using our dataset.
{"title":"A Comprehensive Multi-Illuminant Dataset for Benchmarking of the Intrinsic Image Algorithms","authors":"Shida Beigpour, A. Kolb, Sven Kunz","doi":"10.1109/ICCV.2015.28","DOIUrl":"https://doi.org/10.1109/ICCV.2015.28","url":null,"abstract":"In this paper, we provide a new, real photo dataset with precise ground-truth for intrinsic image research. Prior ground-truth datasets have been restricted to rather simple illumination conditions and scene geometries, or have been enhanced using image synthesis methods. The dataset provided in this paper is based on complex multi-illuminant scenarios under multi-colored illumination conditions and challenging cast shadows. We provide full per-pixel intrinsic ground-truth data for these scenarios, i.e. reflectance, specularity, shading, and illumination for scenes as well as preliminary depth information. Furthermore, we evaluate 3 state-of-the-art intrinsic image recovery methods, using our dataset.","PeriodicalId":6633,"journal":{"name":"2015 IEEE International Conference on Computer Vision (ICCV)","volume":"48 1","pages":"172-180"},"PeriodicalIF":0.0,"publicationDate":"2015-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79112375","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}
L0 gradient minimization can be applied to an input signal to control the number of non-zero gradients. This is useful in reducing small gradients generally associated with signal noise, while preserving important signal features. In computer vision, L0 gradient minimization has found applications in image denoising, 3D mesh denoising, and image enhancement. Minimizing the L0 norm, however, is an NP-hard problem because of its non-convex property. As a result, existing methods rely on approximation strategies to perform the minimization. In this paper, we present a new method to perform L0 gradient minimization that is fast and effective. Our method uses a descent approach based on region fusion that converges faster than other methods while providing a better approximation of the optimal L0 norm. In addition, our method can be applied to both 2D images and 3D mesh topologies. The effectiveness of our approach is demonstrated on a number of examples.
{"title":"Fast and Effective L0 Gradient Minimization by Region Fusion","authors":"Nguyen Ho Man Rang, M. S. Brown","doi":"10.1109/ICCV.2015.32","DOIUrl":"https://doi.org/10.1109/ICCV.2015.32","url":null,"abstract":"L0 gradient minimization can be applied to an input signal to control the number of non-zero gradients. This is useful in reducing small gradients generally associated with signal noise, while preserving important signal features. In computer vision, L0 gradient minimization has found applications in image denoising, 3D mesh denoising, and image enhancement. Minimizing the L0 norm, however, is an NP-hard problem because of its non-convex property. As a result, existing methods rely on approximation strategies to perform the minimization. In this paper, we present a new method to perform L0 gradient minimization that is fast and effective. Our method uses a descent approach based on region fusion that converges faster than other methods while providing a better approximation of the optimal L0 norm. In addition, our method can be applied to both 2D images and 3D mesh topologies. The effectiveness of our approach is demonstrated on a number of examples.","PeriodicalId":6633,"journal":{"name":"2015 IEEE International Conference on Computer Vision (ICCV)","volume":"111 1","pages":"208-216"},"PeriodicalIF":0.0,"publicationDate":"2015-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79182295","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 introduce a new approach for estimating a fine grained 3D shape and continuous pose of an object from a single image. Given a training set of view exemplars, we learn and select appearance-based discriminative parts which are mapped onto the 3D model through a facility location optimization. The training set of 3D models is summarized into a set of basis shapes from which we can generalize by linear combination. Given a test image, we detect hypotheses for each part. The main challenge is to select from these hypotheses and compute the 3D pose and shape coefficients at the same time. To achieve this, we optimize a function that considers simultaneously the appearance matching of the parts as well as the geometric reprojection error. We apply the alternating direction method of multipliers (ADMM) to minimize the resulting convex function. Our main and novel contribution is the simultaneous solution for part localization and detailed 3D geometry estimation by maximizing both appearance and geometric compatibility with convex relaxation.
{"title":"Single Image Pop-Up from Discriminatively Learned Parts","authors":"Menglong Zhu, Xiaowei Zhou, Kostas Daniilidis","doi":"10.1109/ICCV.2015.112","DOIUrl":"https://doi.org/10.1109/ICCV.2015.112","url":null,"abstract":"We introduce a new approach for estimating a fine grained 3D shape and continuous pose of an object from a single image. Given a training set of view exemplars, we learn and select appearance-based discriminative parts which are mapped onto the 3D model through a facility location optimization. The training set of 3D models is summarized into a set of basis shapes from which we can generalize by linear combination. Given a test image, we detect hypotheses for each part. The main challenge is to select from these hypotheses and compute the 3D pose and shape coefficients at the same time. To achieve this, we optimize a function that considers simultaneously the appearance matching of the parts as well as the geometric reprojection error. We apply the alternating direction method of multipliers (ADMM) to minimize the resulting convex function. Our main and novel contribution is the simultaneous solution for part localization and detailed 3D geometry estimation by maximizing both appearance and geometric compatibility with convex relaxation.","PeriodicalId":6633,"journal":{"name":"2015 IEEE International Conference on Computer Vision (ICCV)","volume":"33 1","pages":"927-935"},"PeriodicalIF":0.0,"publicationDate":"2015-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72712417","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}
Valsamis Ntouskos, Marta Sanzari, B. Cafaro, F. Nardi, Fabrizio Natola, F. Pirri, M. A. Garcia
We introduce a novel framework for modeling articulated objects based on the aspects of their components. By decomposing the object into components, we divide the problem in smaller modeling tasks. After obtaining 3D models for each component aspect by employing a shape deformation paradigm, we merge them together, forming the object components. The final model is obtained by assembling the components using an optimization scheme which fits the respective 3D models to the corresponding apparent contours in a reference pose. The results suggest that our approach can produce realistic 3D models of articulated objects in reasonable time.
{"title":"Component-Wise Modeling of Articulated Objects","authors":"Valsamis Ntouskos, Marta Sanzari, B. Cafaro, F. Nardi, Fabrizio Natola, F. Pirri, M. A. Garcia","doi":"10.1109/ICCV.2015.268","DOIUrl":"https://doi.org/10.1109/ICCV.2015.268","url":null,"abstract":"We introduce a novel framework for modeling articulated objects based on the aspects of their components. By decomposing the object into components, we divide the problem in smaller modeling tasks. After obtaining 3D models for each component aspect by employing a shape deformation paradigm, we merge them together, forming the object components. The final model is obtained by assembling the components using an optimization scheme which fits the respective 3D models to the corresponding apparent contours in a reference pose. The results suggest that our approach can produce realistic 3D models of articulated objects in reasonable time.","PeriodicalId":6633,"journal":{"name":"2015 IEEE International Conference on Computer Vision (ICCV)","volume":"1 1","pages":"2327-2335"},"PeriodicalIF":0.0,"publicationDate":"2015-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75275605","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}
Wanli Ouyang, Hongyang Li, Xingyu Zeng, Xiaogang Wang
Learning strong feature representations from large scale supervision has achieved remarkable success in computer vision as the emergence of deep learning techniques. It is driven by big visual data with rich annotations. This paper contributes a large-scale object attribute database that contains rich attribute annotations (over 300 attributes) for ~180k samples and 494 object classes. Based on the ImageNet object detection dataset, it annotates the rotation, viewpoint, object part location, part occlusion, part existence, common attributes, and class-specific attributes. Then we use this dataset to train deep representations and extensively evaluate how these attributes are useful on the general object detection task. In order to make better use of the attribute annotations, a deep learning scheme is proposed by modeling the relationship of attributes and hierarchically clustering them into semantically meaningful mixture types. Experimental results show that the attributes are helpful in learning better features and improving the object detection accuracy by 2.6% in mAP on the ILSVRC 2014 object detection dataset and 2.4% in mAP on PASCAL VOC 2007 object detection dataset. Such improvement is well generalized across datasets.
{"title":"Learning Deep Representation with Large-Scale Attributes","authors":"Wanli Ouyang, Hongyang Li, Xingyu Zeng, Xiaogang Wang","doi":"10.1109/ICCV.2015.220","DOIUrl":"https://doi.org/10.1109/ICCV.2015.220","url":null,"abstract":"Learning strong feature representations from large scale supervision has achieved remarkable success in computer vision as the emergence of deep learning techniques. It is driven by big visual data with rich annotations. This paper contributes a large-scale object attribute database that contains rich attribute annotations (over 300 attributes) for ~180k samples and 494 object classes. Based on the ImageNet object detection dataset, it annotates the rotation, viewpoint, object part location, part occlusion, part existence, common attributes, and class-specific attributes. Then we use this dataset to train deep representations and extensively evaluate how these attributes are useful on the general object detection task. In order to make better use of the attribute annotations, a deep learning scheme is proposed by modeling the relationship of attributes and hierarchically clustering them into semantically meaningful mixture types. Experimental results show that the attributes are helpful in learning better features and improving the object detection accuracy by 2.6% in mAP on the ILSVRC 2014 object detection dataset and 2.4% in mAP on PASCAL VOC 2007 object detection dataset. Such improvement is well generalized across datasets.","PeriodicalId":6633,"journal":{"name":"2015 IEEE International Conference on Computer Vision (ICCV)","volume":"42 1","pages":"1895-1903"},"PeriodicalIF":0.0,"publicationDate":"2015-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75493703","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}
Zero-shot learning (ZSL) can be considered as a special case of transfer learning where the source and target domains have different tasks/label spaces and the target domain is unlabelled, providing little guidance for the knowledge transfer. A ZSL method typically assumes that the two domains share a common semantic representation space, where a visual feature vector extracted from an image/video can be projected/embedded using a projection function. Existing approaches learn the projection function from the source domain and apply it without adaptation to the target domain. They are thus based on naive knowledge transfer and the learned projections are prone to the domain shift problem. In this paper a novel ZSL method is proposed based on unsupervised domain adaptation. Specifically, we formulate a novel regularised sparse coding framework which uses the target domain class labels' projections in the semantic space to regularise the learned target domain projection thus effectively overcoming the projection domain shift problem. Extensive experiments on four object and action recognition benchmark datasets show that the proposed ZSL method significantly outperforms the state-of-the-arts.
{"title":"Unsupervised Domain Adaptation for Zero-Shot Learning","authors":"Elyor Kodirov, T. Xiang, Zhenyong Fu, S. Gong","doi":"10.1109/ICCV.2015.282","DOIUrl":"https://doi.org/10.1109/ICCV.2015.282","url":null,"abstract":"Zero-shot learning (ZSL) can be considered as a special case of transfer learning where the source and target domains have different tasks/label spaces and the target domain is unlabelled, providing little guidance for the knowledge transfer. A ZSL method typically assumes that the two domains share a common semantic representation space, where a visual feature vector extracted from an image/video can be projected/embedded using a projection function. Existing approaches learn the projection function from the source domain and apply it without adaptation to the target domain. They are thus based on naive knowledge transfer and the learned projections are prone to the domain shift problem. In this paper a novel ZSL method is proposed based on unsupervised domain adaptation. Specifically, we formulate a novel regularised sparse coding framework which uses the target domain class labels' projections in the semantic space to regularise the learned target domain projection thus effectively overcoming the projection domain shift problem. Extensive experiments on four object and action recognition benchmark datasets show that the proposed ZSL method significantly outperforms the state-of-the-arts.","PeriodicalId":6633,"journal":{"name":"2015 IEEE International Conference on Computer Vision (ICCV)","volume":"43 1","pages":"2452-2460"},"PeriodicalIF":0.0,"publicationDate":"2015-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73580029","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}
Hashing is very effective for many tasks in reducing the processing time and in compressing massive databases. Although lots of approaches have been developed to learn data-dependent hash functions in recent years, how to learn hash functions to yield good performance with acceptable computational and memory cost is still a challenging problem. Based on the observation that retrieval precision is highly related to the kNN classification accuracy, this paper proposes a novel kNN-based supervised hashing method, which learns hash functions by directly maximizing the kNN accuracy of the Hamming-embedded training data. To make it scalable well to large problem, we propose a factorized neighborhood representation to parsimoniously model the neighborhood relationships inherent in training data. Considering that real-world data are often linearly inseparable, we further kernelize this basic model to improve its performance. As a result, the proposed method is able to learn accurate hashing functions with tolerable computation and storage cost. Experiments on four benchmarks demonstrate that our method outperforms the state-of-the-arts.
{"title":"kNN Hashing with Factorized Neighborhood Representation","authors":"Kun Ding, Chunlei Huo, Bin Fan, Chunhong Pan","doi":"10.1109/ICCV.2015.131","DOIUrl":"https://doi.org/10.1109/ICCV.2015.131","url":null,"abstract":"Hashing is very effective for many tasks in reducing the processing time and in compressing massive databases. Although lots of approaches have been developed to learn data-dependent hash functions in recent years, how to learn hash functions to yield good performance with acceptable computational and memory cost is still a challenging problem. Based on the observation that retrieval precision is highly related to the kNN classification accuracy, this paper proposes a novel kNN-based supervised hashing method, which learns hash functions by directly maximizing the kNN accuracy of the Hamming-embedded training data. To make it scalable well to large problem, we propose a factorized neighborhood representation to parsimoniously model the neighborhood relationships inherent in training data. Considering that real-world data are often linearly inseparable, we further kernelize this basic model to improve its performance. As a result, the proposed method is able to learn accurate hashing functions with tolerable computation and storage cost. Experiments on four benchmarks demonstrate that our method outperforms the state-of-the-arts.","PeriodicalId":6633,"journal":{"name":"2015 IEEE International Conference on Computer Vision (ICCV)","volume":"6 1","pages":"1098-1106"},"PeriodicalIF":0.0,"publicationDate":"2015-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90110912","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：