Analysis sparse representation (ASR) and synthesis sparse representation (SSR) are two representative approaches for sparsity-based image modeling. An image is described mainly by the non-zero coefficients in SSR, while is mainly characterized by the indices of zeros in ASR. To exploit the complementary representation mechanisms of ASR and SSR, we integrate the two models and propose a joint convolutional analysis and synthesis (JCAS) sparse representation model. The convolutional implementation is adopted to more effectively exploit the image global information. In JCAS, a single image is decomposed into two layers, one is approximated by ASR to represent image large-scale structures, and the other by SSR to represent image fine-scale textures. The synthesis dictionary is adaptively learned in JCAS to describe the texture patterns for different single image layer separation tasks. We evaluate the proposed JCAS model on a variety of applications, including rain streak removal, high dynamic range image tone mapping, etc. The results show that our JCAS method outperforms state-of-the-arts in these applications in terms of both quantitative measure and visual perception quality.
{"title":"Joint Convolutional Analysis and Synthesis Sparse Representation for Single Image Layer Separation","authors":"Shuhang Gu, Deyu Meng, W. Zuo, Lei Zhang","doi":"10.1109/ICCV.2017.189","DOIUrl":"https://doi.org/10.1109/ICCV.2017.189","url":null,"abstract":"Analysis sparse representation (ASR) and synthesis sparse representation (SSR) are two representative approaches for sparsity-based image modeling. An image is described mainly by the non-zero coefficients in SSR, while is mainly characterized by the indices of zeros in ASR. To exploit the complementary representation mechanisms of ASR and SSR, we integrate the two models and propose a joint convolutional analysis and synthesis (JCAS) sparse representation model. The convolutional implementation is adopted to more effectively exploit the image global information. In JCAS, a single image is decomposed into two layers, one is approximated by ASR to represent image large-scale structures, and the other by SSR to represent image fine-scale textures. The synthesis dictionary is adaptively learned in JCAS to describe the texture patterns for different single image layer separation tasks. We evaluate the proposed JCAS model on a variety of applications, including rain streak removal, high dynamic range image tone mapping, etc. The results show that our JCAS method outperforms state-of-the-arts in these applications in terms of both quantitative measure and visual perception quality.","PeriodicalId":6559,"journal":{"name":"2017 IEEE International Conference on Computer Vision (ICCV)","volume":"51 1","pages":"1717-1725"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76184818","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 new solution to the text detection problem via border learning. Specifically, we make four major contributions: 1) We analyze the insufficiencies of the classic non-text and text settings for text detection. 2) We introduce the border class to the text detection problem for the first time, and validate that the decoding process is largely simplified with the help of text border. 3) We collect and release a new text detection PPT dataset containing 10,692 images with non-text, border, and text annotations. 4) We develop a lightweight (only 0.28M parameters), fully convolutional network (FCN) to effectively learn borders in text images. The results of our extensive experiments show that the proposed solution achieves comparable performance, and often outperforms state-of-theart approaches on standard benchmarks–even though our solution only requires minimal post-processing to parse a bounding box from a detected text map, while others often require heavy post-processing.
{"title":"Self-Organized Text Detection with Minimal Post-processing via Border Learning","authors":"Yue Wu, P. Natarajan","doi":"10.1109/ICCV.2017.535","DOIUrl":"https://doi.org/10.1109/ICCV.2017.535","url":null,"abstract":"In this paper we propose a new solution to the text detection problem via border learning. Specifically, we make four major contributions: 1) We analyze the insufficiencies of the classic non-text and text settings for text detection. 2) We introduce the border class to the text detection problem for the first time, and validate that the decoding process is largely simplified with the help of text border. 3) We collect and release a new text detection PPT dataset containing 10,692 images with non-text, border, and text annotations. 4) We develop a lightweight (only 0.28M parameters), fully convolutional network (FCN) to effectively learn borders in text images. The results of our extensive experiments show that the proposed solution achieves comparable performance, and often outperforms state-of-theart approaches on standard benchmarks–even though our solution only requires minimal post-processing to parse a bounding box from a detected text map, while others often require heavy post-processing.","PeriodicalId":6559,"journal":{"name":"2017 IEEE International Conference on Computer Vision (ICCV)","volume":"2 1","pages":"5010-5019"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82794502","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
We present a method for Modeling Urban Scenes from Pointclouds (MUSP). In contrast to existing approaches, MUSP is robust, scalable and provides a more complete description by not making a Manhattan-World assumption and modeling both buildings (with polyhedra) as well as the non-planar ground (using NURBS). First, we segment the scene into consistent patches using a divide-and-conquer based algorithm within a nonparametric Bayesian framework (stick-breaking construction). These patches often correspond to meaningful structures, such as the ground, facades, roofs and roof superstructures. We use polygon sweeping to fit predefined templates for buildings, and for the ground, a NURBS surface is fit and uniformly tessellated. Finally, we apply boolean operations to the polygons for buildings, buildings parts and the tesselated ground to clip unnecessary geometry (e.g., facades protrusions below the non-planar ground), leading to the final model. The explicit Bayesian formulation of scene segmentation makes our approach suitable for challenging datasets with varying amounts of noise, outliers, and point density. We demonstrate the robustness of MUSP on 3D pointclouds from image matching as well as LiDAR.
{"title":"Modeling Urban Scenes from Pointclouds","authors":"William Nguatem, H. Mayer","doi":"10.1109/ICCV.2017.414","DOIUrl":"https://doi.org/10.1109/ICCV.2017.414","url":null,"abstract":"We present a method for Modeling Urban Scenes from Pointclouds (MUSP). In contrast to existing approaches, MUSP is robust, scalable and provides a more complete description by not making a Manhattan-World assumption and modeling both buildings (with polyhedra) as well as the non-planar ground (using NURBS). First, we segment the scene into consistent patches using a divide-and-conquer based algorithm within a nonparametric Bayesian framework (stick-breaking construction). These patches often correspond to meaningful structures, such as the ground, facades, roofs and roof superstructures. We use polygon sweeping to fit predefined templates for buildings, and for the ground, a NURBS surface is fit and uniformly tessellated. Finally, we apply boolean operations to the polygons for buildings, buildings parts and the tesselated ground to clip unnecessary geometry (e.g., facades protrusions below the non-planar ground), leading to the final model. The explicit Bayesian formulation of scene segmentation makes our approach suitable for challenging datasets with varying amounts of noise, outliers, and point density. We demonstrate the robustness of MUSP on 3D pointclouds from image matching as well as LiDAR.","PeriodicalId":6559,"journal":{"name":"2017 IEEE International Conference on Computer Vision (ICCV)","volume":"3 1","pages":"3857-3866"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91545183","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}
This paper proposes a novel approach for segmenting primary video objects by using Complementary Convolutional Neural Networks (CCNN) and neighborhood reversible flow. The proposed approach first pre-trains CCNN on massive images with manually annotated salient objects in an end-to-end manner, and the trained CCNN has two separate branches that simultaneously handle two complementary tasks, i.e., foregroundness and backgroundness estimation. By applying CCNN on each video frame, the spatial foregroundness and backgroundness maps can be initialized, which are then propagated between various frames so as to segment primary video objects and suppress distractors. To enforce efficient temporal propagation, we divide each frame into superpixels and construct neighborhood reversible flow that reflects the most reliable temporal correspondences between superpixels in far-away frames. Within such flow, the initialized foregroundness and backgroundness can be efficiently and accurately propagated along the temporal axis so that primary video objects gradually pop-out and distractors are well suppressed. Extensive experimental results on three video datasets show that the proposed approach achieves impressive performance in comparisons with 18 state-of-the-art models.
{"title":"Primary Video Object Segmentation via Complementary CNNs and Neighborhood Reversible Flow","authors":"Jia Li, Anlin Zheng, Xiaowu Chen, Bin Zhou","doi":"10.1109/ICCV.2017.158","DOIUrl":"https://doi.org/10.1109/ICCV.2017.158","url":null,"abstract":"This paper proposes a novel approach for segmenting primary video objects by using Complementary Convolutional Neural Networks (CCNN) and neighborhood reversible flow. The proposed approach first pre-trains CCNN on massive images with manually annotated salient objects in an end-to-end manner, and the trained CCNN has two separate branches that simultaneously handle two complementary tasks, i.e., foregroundness and backgroundness estimation. By applying CCNN on each video frame, the spatial foregroundness and backgroundness maps can be initialized, which are then propagated between various frames so as to segment primary video objects and suppress distractors. To enforce efficient temporal propagation, we divide each frame into superpixels and construct neighborhood reversible flow that reflects the most reliable temporal correspondences between superpixels in far-away frames. Within such flow, the initialized foregroundness and backgroundness can be efficiently and accurately propagated along the temporal axis so that primary video objects gradually pop-out and distractors are well suppressed. Extensive experimental results on three video datasets show that the proposed approach achieves impressive performance in comparisons with 18 state-of-the-art models.","PeriodicalId":6559,"journal":{"name":"2017 IEEE International Conference on Computer Vision (ICCV)","volume":"96 17","pages":"1426-1434"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91406898","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 recent years, there have been a variety of proposals for high quality 3D reconstruction by fusion of depth and normal maps that contain good low and high frequency information respectively. Typically, these methods create an initial mesh representation of the complete object or scene being scanned. Subsequently, normal estimates are assigned to each mesh vertex and a mesh-normal fusion step is carried out. In this paper, we present a complete pipeline for such depth-normal fusion. The key innovations in our pipeline are twofold. Firstly, we introduce a global multi-view non-rigid refinement step that corrects for the non-rigid misalignment present in the depth and normal maps. We demonstrate that such a correction is crucial for preserving fine-scale 3D features in the final reconstruction. Secondly, despite adequate care, the averaging of multiple normals invariably results in blurring of3D detail. To mitigate this problem, we propose an approach that selects one out of many available normals. Our global cost for normal selection incorporates a variety of desirable properties and can be efficiently solved using graph cuts. We demonstrate the efficacy of our approach in generating high quality 3D reconstructions of both synthetic and real 3D models and compare with existing methods in the literature.
{"title":"Multi-view Non-rigid Refinement and Normal Selection for High Quality 3D Reconstruction","authors":"Sk. Mohammadul Haque, V. Govindu","doi":"10.1109/ICCV.2017.261","DOIUrl":"https://doi.org/10.1109/ICCV.2017.261","url":null,"abstract":"In recent years, there have been a variety of proposals for high quality 3D reconstruction by fusion of depth and normal maps that contain good low and high frequency information respectively. Typically, these methods create an initial mesh representation of the complete object or scene being scanned. Subsequently, normal estimates are assigned to each mesh vertex and a mesh-normal fusion step is carried out. In this paper, we present a complete pipeline for such depth-normal fusion. The key innovations in our pipeline are twofold. Firstly, we introduce a global multi-view non-rigid refinement step that corrects for the non-rigid misalignment present in the depth and normal maps. We demonstrate that such a correction is crucial for preserving fine-scale 3D features in the final reconstruction. Secondly, despite adequate care, the averaging of multiple normals invariably results in blurring of3D detail. To mitigate this problem, we propose an approach that selects one out of many available normals. Our global cost for normal selection incorporates a variety of desirable properties and can be efficiently solved using graph cuts. We demonstrate the efficacy of our approach in generating high quality 3D reconstructions of both synthetic and real 3D models and compare with existing methods in the literature.","PeriodicalId":6559,"journal":{"name":"2017 IEEE International Conference on Computer Vision (ICCV)","volume":"78 1","pages":"2401-2409"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83071919","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}
Image and video understanding enables better reconstruction of the physical world. Existing methods focus largely on geometry and visual appearance of the reconstructed scene. In this paper, we extend the frontier in image understanding and present a method to recover the material properties of cloth from a video. Previous cloth material recovery methods often require markers or complex experimental set-up to acquire physical properties, or are limited to certain types of images or videos. Our approach takes advantages of the appearance changes of the moving cloth to infer its physical properties. To extract information about the cloth, our method characterizes both the motion and the visual appearance of the cloth geometry. We apply the Convolutional Neural Network (CNN) and the Long Short Term Memory (LSTM) neural network to material recovery of cloth from videos. We also exploit simulated data to help statistical learning of mapping between the visual appearance and material type of the cloth. The effectiveness of our method is demonstrated via validation using both the simulated datasets and the real-life recorded videos.
{"title":"Learning-Based Cloth Material Recovery from Video","authors":"Shan Yang, Junbang Liang, M. Lin","doi":"10.1109/ICCV.2017.470","DOIUrl":"https://doi.org/10.1109/ICCV.2017.470","url":null,"abstract":"Image and video understanding enables better reconstruction of the physical world. Existing methods focus largely on geometry and visual appearance of the reconstructed scene. In this paper, we extend the frontier in image understanding and present a method to recover the material properties of cloth from a video. Previous cloth material recovery methods often require markers or complex experimental set-up to acquire physical properties, or are limited to certain types of images or videos. Our approach takes advantages of the appearance changes of the moving cloth to infer its physical properties. To extract information about the cloth, our method characterizes both the motion and the visual appearance of the cloth geometry. We apply the Convolutional Neural Network (CNN) and the Long Short Term Memory (LSTM) neural network to material recovery of cloth from videos. We also exploit simulated data to help statistical learning of mapping between the visual appearance and material type of the cloth. The effectiveness of our method is demonstrated via validation using both the simulated datasets and the real-life recorded videos.","PeriodicalId":6559,"journal":{"name":"2017 IEEE International Conference on Computer Vision (ICCV)","volume":"12 1","pages":"4393-4403"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88773290","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}
Zhu Teng, Junliang Xing, Qiang Wang, Congyan Lang, Songhe Feng, Yi Jin
Recently deep neural networks have been widely employed to deal with the visual tracking problem. In this work, we present a new deep architecture which incorporates the temporal and spatial information to boost the tracking performance. Our deep architecture contains three networks, a Feature Net, a Temporal Net, and a Spatial Net. The Feature Net extracts general feature representations of the target. With these feature representations, the Temporal Net encodes the trajectory of the target and directly learns temporal correspondences to estimate the object state from a global perspective. Based on the learning results of the Temporal Net, the Spatial Net further refines the object tracking state using local spatial object information. Extensive experiments on four of the largest tracking benchmarks, including VOT2014, VOT2016, OTB50, and OTB100, demonstrate competing performance of the proposed tracker over a number of state-of-the-art algorithms.
{"title":"Robust Object Tracking Based on Temporal and Spatial Deep Networks","authors":"Zhu Teng, Junliang Xing, Qiang Wang, Congyan Lang, Songhe Feng, Yi Jin","doi":"10.1109/ICCV.2017.130","DOIUrl":"https://doi.org/10.1109/ICCV.2017.130","url":null,"abstract":"Recently deep neural networks have been widely employed to deal with the visual tracking problem. In this work, we present a new deep architecture which incorporates the temporal and spatial information to boost the tracking performance. Our deep architecture contains three networks, a Feature Net, a Temporal Net, and a Spatial Net. The Feature Net extracts general feature representations of the target. With these feature representations, the Temporal Net encodes the trajectory of the target and directly learns temporal correspondences to estimate the object state from a global perspective. Based on the learning results of the Temporal Net, the Spatial Net further refines the object tracking state using local spatial object information. Extensive experiments on four of the largest tracking benchmarks, including VOT2014, VOT2016, OTB50, and OTB100, demonstrate competing performance of the proposed tracker over a number of state-of-the-art algorithms.","PeriodicalId":6559,"journal":{"name":"2017 IEEE International Conference on Computer Vision (ICCV)","volume":"38 1","pages":"1153-1162"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91330576","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}
This paper addresses the problem of converting a rasterized floorplan image into a vector-graphics representation. Unlike existing approaches that rely on a sequence of lowlevel image processing heuristics, we adopt a learning-based approach. A neural architecture first transforms a rasterized image to a set of junctions that represent low-level geometric and semantic information (e.g., wall corners or door end-points). Integer programming is then formulated to aggregate junctions into a set of simple primitives (e.g., wall lines, door lines, or icon boxes) to produce a vectorized floorplan, while ensuring a topologically and geometrically consistent result. Our algorithm significantly outperforms existing methods and achieves around 90% precision and recall, getting to the range of production-ready performance. The vector representation allows 3D model popup for better indoor scene visualization, direct model manipulation for architectural remodeling, and further computational applications such as data analysis. Our system is efficient: we have converted hundred thousand production-level floorplan images into the vector representation and generated 3D popup models.
{"title":"Raster-to-Vector: Revisiting Floorplan Transformation","authors":"Chen Liu, Jiajun Wu, Pushmeet Kohli, Yasutaka Furukawa","doi":"10.1109/ICCV.2017.241","DOIUrl":"https://doi.org/10.1109/ICCV.2017.241","url":null,"abstract":"This paper addresses the problem of converting a rasterized floorplan image into a vector-graphics representation. Unlike existing approaches that rely on a sequence of lowlevel image processing heuristics, we adopt a learning-based approach. A neural architecture first transforms a rasterized image to a set of junctions that represent low-level geometric and semantic information (e.g., wall corners or door end-points). Integer programming is then formulated to aggregate junctions into a set of simple primitives (e.g., wall lines, door lines, or icon boxes) to produce a vectorized floorplan, while ensuring a topologically and geometrically consistent result. Our algorithm significantly outperforms existing methods and achieves around 90% precision and recall, getting to the range of production-ready performance. The vector representation allows 3D model popup for better indoor scene visualization, direct model manipulation for architectural remodeling, and further computational applications such as data analysis. Our system is efficient: we have converted hundred thousand production-level floorplan images into the vector representation and generated 3D popup models.","PeriodicalId":6559,"journal":{"name":"2017 IEEE International Conference on Computer Vision (ICCV)","volume":"1 1","pages":"2214-2222"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90461539","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 work, we address multimodal learning problem with Gaussian process latent variable models (GPLVMs) and their application to cross-modal retrieval. Existing GPLVM based studies generally impose individual priors over the model parameters and ignore the intrinsic relations among these parameters. Considering the strong complementarity between modalities, we propose a novel joint prior over the parameters for multimodal GPLVMs to propagate multimodal information in both kernel hyperparameter spaces and latent space. The joint prior is formulated as a harmonization constraint on the model parameters, which enforces the agreement among the modality-specific GP kernels and the similarity in the latent space. We incorporate the harmonization mechanism into the learning process of multimodal GPLVMs. The proposed methods are evaluated on three widely used multimodal datasets for cross-modal retrieval. Experimental results show that the harmonization mechanism is beneficial to the GPLVM algorithms for learning non-linear correlation among heterogeneous modalities.
{"title":"Multimodal Gaussian Process Latent Variable Models with Harmonization","authors":"Guoli Song, Shuhui Wang, Qingming Huang, Q. Tian","doi":"10.1109/ICCV.2017.538","DOIUrl":"https://doi.org/10.1109/ICCV.2017.538","url":null,"abstract":"In this work, we address multimodal learning problem with Gaussian process latent variable models (GPLVMs) and their application to cross-modal retrieval. Existing GPLVM based studies generally impose individual priors over the model parameters and ignore the intrinsic relations among these parameters. Considering the strong complementarity between modalities, we propose a novel joint prior over the parameters for multimodal GPLVMs to propagate multimodal information in both kernel hyperparameter spaces and latent space. The joint prior is formulated as a harmonization constraint on the model parameters, which enforces the agreement among the modality-specific GP kernels and the similarity in the latent space. We incorporate the harmonization mechanism into the learning process of multimodal GPLVMs. The proposed methods are evaluated on three widely used multimodal datasets for cross-modal retrieval. Experimental results show that the harmonization mechanism is beneficial to the GPLVM algorithms for learning non-linear correlation among heterogeneous modalities.","PeriodicalId":6559,"journal":{"name":"2017 IEEE International Conference on Computer Vision (ICCV)","volume":"37 1","pages":"5039-5047"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76644501","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}
Venice Erin Liong, Jiwen Lu, Yap-Peng Tan, Jie Zhou
In this paper, we propose a cross-modal deep variational hashing (CMDVH) method for cross-modality multimedia retrieval. Unlike existing cross-modal hashing methods which learn a single pair of projections to map each example as a binary vector, we design a couple of deep neural network to learn non-linear transformations from image-text input pairs, so that unified binary codes can be obtained. We then design the modality-specific neural networks in a probabilistic manner where we model a latent variable as close as possible from the inferred binary codes, which is approximated by a posterior distribution regularized by a known prior. Experimental results on three benchmark datasets show the efficacy of the proposed approach.
{"title":"Cross-Modal Deep Variational Hashing","authors":"Venice Erin Liong, Jiwen Lu, Yap-Peng Tan, Jie Zhou","doi":"10.1109/ICCV.2017.439","DOIUrl":"https://doi.org/10.1109/ICCV.2017.439","url":null,"abstract":"In this paper, we propose a cross-modal deep variational hashing (CMDVH) method for cross-modality multimedia retrieval. Unlike existing cross-modal hashing methods which learn a single pair of projections to map each example as a binary vector, we design a couple of deep neural network to learn non-linear transformations from image-text input pairs, so that unified binary codes can be obtained. We then design the modality-specific neural networks in a probabilistic manner where we model a latent variable as close as possible from the inferred binary codes, which is approximated by a posterior distribution regularized by a known prior. Experimental results on three benchmark datasets show the efficacy of the proposed approach.","PeriodicalId":6559,"journal":{"name":"2017 IEEE International Conference on Computer Vision (ICCV)","volume":"18 1","pages":"4097-4105"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75080068","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：