Objects in a real world image cannot have arbitrary appearance, sizes and locations due to geometric constraints in 3D space. Such a 3D geometric context plays an important role in resolving visual ambiguities and achieving coherent object detection. In this paper, we develop a RANSAC-CRF framework to detect objects that are geometrically coherent in the 3D world. Different from existing methods, we propose a novel generalized RANSAC algorithm to generate global 3D geometry hypotheses from local entities such that outlier suppression and noise reduction is achieved simultaneously. In addition, we evaluate those hypotheses using a CRF which considers both the compatibility of individual objects under global 3D geometric context and the compatibility between adjacent objects under local 3D geometric context. Experiment results show that our approach compares favorably with the state of the art.
{"title":"Coherent Object Detection with 3D Geometric Context from a Single Image","authors":"Jiyan Pan, T. Kanade","doi":"10.1109/ICCV.2013.320","DOIUrl":"https://doi.org/10.1109/ICCV.2013.320","url":null,"abstract":"Objects in a real world image cannot have arbitrary appearance, sizes and locations due to geometric constraints in 3D space. Such a 3D geometric context plays an important role in resolving visual ambiguities and achieving coherent object detection. In this paper, we develop a RANSAC-CRF framework to detect objects that are geometrically coherent in the 3D world. Different from existing methods, we propose a novel generalized RANSAC algorithm to generate global 3D geometry hypotheses from local entities such that outlier suppression and noise reduction is achieved simultaneously. In addition, we evaluate those hypotheses using a CRF which considers both the compatibility of individual objects under global 3D geometric context and the compatibility between adjacent objects under local 3D geometric context. Experiment results show that our approach compares favorably with the state of the art.","PeriodicalId":6351,"journal":{"name":"2013 IEEE International Conference on Computer Vision","volume":"20 1","pages":"2576-2583"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83937496","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}
Many tensor based algorithms have been proposed for the study of high dimensional data in a large variety of computer vision and machine learning applications. However, most of the existing tensor analysis approaches are based on Frobenius norm, which makes them sensitive to outliers, because they minimize the sum of squared errors and enlarge the influence of both outliers and large feature noises. In this paper, we propose a robust Tucker tensor decomposition model (RTD) to suppress the influence of outliers, which uses L1-norm loss function. Yet, the optimization on L1-norm based tensor analysis is much harder than standard tensor decomposition. In this paper, we propose a simple and efficient algorithm to solve our RTD model. Moreover, tensor factorization-based image storage needs much less space than PCA based methods. We carry out extensive experiments to evaluate the proposed algorithm, and verify the robustness against image occlusions. Both numerical and visual results show that our RTD model is consistently better against the existence of outliers than previous tensor and PCA methods.
{"title":"Robust Tucker Tensor Decomposition for Effective Image Representation","authors":"Miao Zhang, C. Ding","doi":"10.1109/ICCV.2013.304","DOIUrl":"https://doi.org/10.1109/ICCV.2013.304","url":null,"abstract":"Many tensor based algorithms have been proposed for the study of high dimensional data in a large variety of computer vision and machine learning applications. However, most of the existing tensor analysis approaches are based on Frobenius norm, which makes them sensitive to outliers, because they minimize the sum of squared errors and enlarge the influence of both outliers and large feature noises. In this paper, we propose a robust Tucker tensor decomposition model (RTD) to suppress the influence of outliers, which uses L1-norm loss function. Yet, the optimization on L1-norm based tensor analysis is much harder than standard tensor decomposition. In this paper, we propose a simple and efficient algorithm to solve our RTD model. Moreover, tensor factorization-based image storage needs much less space than PCA based methods. We carry out extensive experiments to evaluate the proposed algorithm, and verify the robustness against image occlusions. Both numerical and visual results show that our RTD model is consistently better against the existence of outliers than previous tensor and PCA methods.","PeriodicalId":6351,"journal":{"name":"2013 IEEE International Conference on Computer Vision","volume":"33 1","pages":"2448-2455"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86216896","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}
Visual reranking has been widely deployed to refine the quality of conventional content-based image retrieval engines. The current trend lies in employing a crowd of retrieved results stemming from multiple feature modalities to boost the overall performance of visual reranking. However, a major challenge pertaining to current reranking methods is how to take full advantage of the complementary property of distinct feature modalities. Given a query image and one feature modality, a regular visual reranking framework treats the top-ranked images as pseudo positive instances which are inevitably noisy, difficult to reveal this complementary property, and thus lead to inferior ranking performance. This paper proposes a novel image reranking approach by introducing a Co-Regularized Multi-Graph Learning (Co-RMGL) framework, in which the intra-graph and inter-graph constraints are simultaneously imposed to encode affinities in a single graph and consistency across different graphs. Moreover, weakly supervised learning driven by image attributes is performed to denoise the pseudo-labeled instances, thereby highlighting the unique strength of individual feature modality. Meanwhile, such learning can yield a few anchors in graphs that vitally enable the alignment and fusion of multiple graphs. As a result, an edge weight matrix learned from the fused graph automatically gives the ordering to the initially retrieved results. We evaluate our approach on four benchmark image retrieval datasets, demonstrating a significant performance gain over the state-of-the-arts.
{"title":"Visual Reranking through Weakly Supervised Multi-graph Learning","authors":"Cheng Deng, R. Ji, W. Liu, D. Tao, Xinbo Gao","doi":"10.1109/ICCV.2013.323","DOIUrl":"https://doi.org/10.1109/ICCV.2013.323","url":null,"abstract":"Visual reranking has been widely deployed to refine the quality of conventional content-based image retrieval engines. The current trend lies in employing a crowd of retrieved results stemming from multiple feature modalities to boost the overall performance of visual reranking. However, a major challenge pertaining to current reranking methods is how to take full advantage of the complementary property of distinct feature modalities. Given a query image and one feature modality, a regular visual reranking framework treats the top-ranked images as pseudo positive instances which are inevitably noisy, difficult to reveal this complementary property, and thus lead to inferior ranking performance. This paper proposes a novel image reranking approach by introducing a Co-Regularized Multi-Graph Learning (Co-RMGL) framework, in which the intra-graph and inter-graph constraints are simultaneously imposed to encode affinities in a single graph and consistency across different graphs. Moreover, weakly supervised learning driven by image attributes is performed to denoise the pseudo-labeled instances, thereby highlighting the unique strength of individual feature modality. Meanwhile, such learning can yield a few anchors in graphs that vitally enable the alignment and fusion of multiple graphs. As a result, an edge weight matrix learned from the fused graph automatically gives the ordering to the initially retrieved results. We evaluate our approach on four benchmark image retrieval datasets, demonstrating a significant performance gain over the state-of-the-arts.","PeriodicalId":6351,"journal":{"name":"2013 IEEE International Conference on Computer Vision","volume":"126 1","pages":"2600-2607"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77525433","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 aim to decompose a global histogram representation of an image into histograms of its associated objects and regions. This task is formulated as an optimization problem, given a set of linear classifiers, which can effectively discriminate the object categories present in the image. Our decomposition bypasses harder problems associated with accurately localizing and segmenting objects. We evaluate our method on a wide variety of composite histograms, and also compare it with MRF-based solutions. In addition to merely measuring the accuracy of decomposition, we also show the utility of the estimated object and background histograms for the task of image classification on the PASCAL VOC 2007 dataset.
{"title":"Decomposing Bag of Words Histograms","authors":"Ankit Gandhi, Alahari Karteek, C. V. Jawahar","doi":"10.1109/ICCV.2013.45","DOIUrl":"https://doi.org/10.1109/ICCV.2013.45","url":null,"abstract":"We aim to decompose a global histogram representation of an image into histograms of its associated objects and regions. This task is formulated as an optimization problem, given a set of linear classifiers, which can effectively discriminate the object categories present in the image. Our decomposition bypasses harder problems associated with accurately localizing and segmenting objects. We evaluate our method on a wide variety of composite histograms, and also compare it with MRF-based solutions. In addition to merely measuring the accuracy of decomposition, we also show the utility of the estimated object and background histograms for the task of image classification on the PASCAL VOC 2007 dataset.","PeriodicalId":6351,"journal":{"name":"2013 IEEE International Conference on Computer Vision","volume":"6 1","pages":"305-312"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91529516","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}
T. Kazmar, E. Kvon, A. Stark, Christoph H. Lampert
In this work we propose a system for automatic classification of Drosophila embryos into developmental stages. While the system is designed to solve an actual problem in biological research, we believe that the principle underlying it is interesting not only for biologists, but also for researchers in computer vision. The main idea is to combine two orthogonal sources of information: one is a classifier trained on strongly invariant features, which makes it applicable to images of very different conditions, but also leads to rather noisy predictions. The other is a label propagation step based on a more powerful similarity measure that however is only consistent within specific subsets of the data at a time. In our biological setup, the information sources are the shape and the staining patterns of embryo images. We show experimentally that while neither of the methods can be used by itself to achieve satisfactory results, their combination achieves prediction quality comparable to human performance.
{"title":"Drosophila Embryo Stage Annotation Using Label Propagation","authors":"T. Kazmar, E. Kvon, A. Stark, Christoph H. Lampert","doi":"10.1109/ICCV.2013.139","DOIUrl":"https://doi.org/10.1109/ICCV.2013.139","url":null,"abstract":"In this work we propose a system for automatic classification of Drosophila embryos into developmental stages. While the system is designed to solve an actual problem in biological research, we believe that the principle underlying it is interesting not only for biologists, but also for researchers in computer vision. The main idea is to combine two orthogonal sources of information: one is a classifier trained on strongly invariant features, which makes it applicable to images of very different conditions, but also leads to rather noisy predictions. The other is a label propagation step based on a more powerful similarity measure that however is only consistent within specific subsets of the data at a time. In our biological setup, the information sources are the shape and the staining patterns of embryo images. We show experimentally that while neither of the methods can be used by itself to achieve satisfactory results, their combination achieves prediction quality comparable to human performance.","PeriodicalId":6351,"journal":{"name":"2013 IEEE International Conference on Computer Vision","volume":"58 1","pages":"1089-1096"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91299244","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 an unsupervised domain adaptation method that exploits intrinsic compact structures of categories across different domains using binary attributes. Our method directly optimizes for classification in the target domain. The key insight is finding attributes that are discriminative across categories and predictable across domains. We achieve a performance that significantly exceeds the state-of-the-art results on standard benchmarks. In fact, in many cases, our method reaches the same-domain performance, the upper bound, in unsupervised domain adaptation scenarios.
{"title":"Domain Adaptive Classification","authors":"Fatemeh Mirrashed, Mohammad Rastegari","doi":"10.1109/ICCV.2013.324","DOIUrl":"https://doi.org/10.1109/ICCV.2013.324","url":null,"abstract":"We propose an unsupervised domain adaptation method that exploits intrinsic compact structures of categories across different domains using binary attributes. Our method directly optimizes for classification in the target domain. The key insight is finding attributes that are discriminative across categories and predictable across domains. We achieve a performance that significantly exceeds the state-of-the-art results on standard benchmarks. In fact, in many cases, our method reaches the same-domain performance, the upper bound, in unsupervised domain adaptation scenarios.","PeriodicalId":6351,"journal":{"name":"2013 IEEE International Conference on Computer Vision","volume":"49 1","pages":"2608-2615"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85701711","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}
Sparsity models have recently shown great promise in many vision tasks. Using a learned dictionary in sparsity models can in general outperform predefined bases in clean data. In practice, both training and testing data may be corrupted and contain noises and outliers. Although recent studies attempted to cope with corrupted data and achieved encouraging results in testing phase, how to handle corruption in training phase still remains a very difficult problem. In contrast to most existing methods that learn the dictionary from clean data, this paper is targeted at handling corruptions and outliers in training data for dictionary learning. We propose a general method to decompose the reconstructive residual into two components: a non-sparse component for small universal noises and a sparse component for large outliers, respectively. In addition, further analysis reveals the connection between our approach and the ``partial'' dictionary learning approach, updating only part of the prototypes (or informative code words) with remaining (or noisy code words) fixed. Experiments on synthetic data as well as real applications have shown satisfactory performance of this new robust dictionary learning approach.
{"title":"Robust Dictionary Learning by Error Source Decomposition","authors":"Zhuoyuan Chen, Ying Wu","doi":"10.1109/ICCV.2013.276","DOIUrl":"https://doi.org/10.1109/ICCV.2013.276","url":null,"abstract":"Sparsity models have recently shown great promise in many vision tasks. Using a learned dictionary in sparsity models can in general outperform predefined bases in clean data. In practice, both training and testing data may be corrupted and contain noises and outliers. Although recent studies attempted to cope with corrupted data and achieved encouraging results in testing phase, how to handle corruption in training phase still remains a very difficult problem. In contrast to most existing methods that learn the dictionary from clean data, this paper is targeted at handling corruptions and outliers in training data for dictionary learning. We propose a general method to decompose the reconstructive residual into two components: a non-sparse component for small universal noises and a sparse component for large outliers, respectively. In addition, further analysis reveals the connection between our approach and the ``partial'' dictionary learning approach, updating only part of the prototypes (or informative code words) with remaining (or noisy code words) fixed. Experiments on synthetic data as well as real applications have shown satisfactory performance of this new robust dictionary learning approach.","PeriodicalId":6351,"journal":{"name":"2013 IEEE International Conference on Computer Vision","volume":"122 1","pages":"2216-2223"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86056897","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 aim to unsupervisedly discover human's action (motion) patterns of manipulating various objects in scenarios such as assisted living. We are motivated by two key observations. First, large variation exists in motion patterns associated with various types of objects being manipulated, thus manually defining motion primitives is infeasible. Second, some motion patterns are shared among different objects being manipulated while others are object specific. We therefore propose a nonparametric Bayesian method that adopts a hierarchical Dirichlet process prior to learn representative manipulation (motion) patterns in an unsupervised manner. Taking easy-to-obtain object detection score maps and dense motion trajectories as inputs, the proposed probabilistic model can discover motion pattern groups associated with different types of objects being manipulated with a shared manipulation pattern dictionary. The size of the learned dictionary is automatically inferred. Comprehensive experiments on two assisted living benchmarks and a cooking motion dataset demonstrate superiority of our learned manipulation pattern dictionary in representing manipulation actions for recognition.
{"title":"Manipulation Pattern Discovery: A Nonparametric Bayesian Approach","authors":"Bingbing Ni, P. Moulin","doi":"10.1109/ICCV.2013.172","DOIUrl":"https://doi.org/10.1109/ICCV.2013.172","url":null,"abstract":"We aim to unsupervisedly discover human's action (motion) patterns of manipulating various objects in scenarios such as assisted living. We are motivated by two key observations. First, large variation exists in motion patterns associated with various types of objects being manipulated, thus manually defining motion primitives is infeasible. Second, some motion patterns are shared among different objects being manipulated while others are object specific. We therefore propose a nonparametric Bayesian method that adopts a hierarchical Dirichlet process prior to learn representative manipulation (motion) patterns in an unsupervised manner. Taking easy-to-obtain object detection score maps and dense motion trajectories as inputs, the proposed probabilistic model can discover motion pattern groups associated with different types of objects being manipulated with a shared manipulation pattern dictionary. The size of the learned dictionary is automatically inferred. Comprehensive experiments on two assisted living benchmarks and a cooking motion dataset demonstrate superiority of our learned manipulation pattern dictionary in representing manipulation actions for recognition.","PeriodicalId":6351,"journal":{"name":"2013 IEEE International Conference on Computer Vision","volume":"75 1","pages":"1361-1368"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81230042","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}
Automatic image categorization has become increasingly important with the development of Internet and the growth in the size of image databases. Although the image categorization can be formulated as a typical multi-class classification problem, two major challenges have been raised by the real-world images. On one hand, though using more labeled training data may improve the prediction performance, obtaining the image labels is a time consuming as well as biased process. On the other hand, more and more visual descriptors have been proposed to describe objects and scenes appearing in images and different features describe different aspects of the visual characteristics. Therefore, how to integrate heterogeneous visual features to do the semi-supervised learning is crucial for categorizing large-scale image data. In this paper, we propose a novel approach to integrate heterogeneous features by performing multi-modal semi-supervised classification on unlabeled as well as unsegmented images. Considering each type of feature as one modality, taking advantage of the large amount of unlabeled data information, our new adaptive multi-modal semi-supervised classification (AMMSS) algorithm learns a commonly shared class indicator matrix and the weights for different modalities (image features) simultaneously.
{"title":"Heterogeneous Image Features Integration via Multi-modal Semi-supervised Learning Model","authors":"Xiao Cai, F. Nie, Weidong (Tom) Cai, Heng Huang","doi":"10.1109/ICCV.2013.218","DOIUrl":"https://doi.org/10.1109/ICCV.2013.218","url":null,"abstract":"Automatic image categorization has become increasingly important with the development of Internet and the growth in the size of image databases. Although the image categorization can be formulated as a typical multi-class classification problem, two major challenges have been raised by the real-world images. On one hand, though using more labeled training data may improve the prediction performance, obtaining the image labels is a time consuming as well as biased process. On the other hand, more and more visual descriptors have been proposed to describe objects and scenes appearing in images and different features describe different aspects of the visual characteristics. Therefore, how to integrate heterogeneous visual features to do the semi-supervised learning is crucial for categorizing large-scale image data. In this paper, we propose a novel approach to integrate heterogeneous features by performing multi-modal semi-supervised classification on unlabeled as well as unsegmented images. Considering each type of feature as one modality, taking advantage of the large amount of unlabeled data information, our new adaptive multi-modal semi-supervised classification (AMMSS) algorithm learns a commonly shared class indicator matrix and the weights for different modalities (image features) simultaneously.","PeriodicalId":6351,"journal":{"name":"2013 IEEE International Conference on Computer Vision","volume":"5 1","pages":"1737-1744"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85104914","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}
A. Khosla, Wilma A. Bainbridge, A. Torralba, A. Oliva
Contemporary life bombards us with many new images of faces every day, which poses non-trivial constraints on human memory. The vast majority of face photographs are intended to be remembered, either because of personal relevance, commercial interests or because the pictures were deliberately designed to be memorable. Can we make a portrait more memorable or more forgettable automatically? Here, we provide a method to modify the memorability of individual face photographs, while keeping the identity and other facial traits (e.g. age, attractiveness, and emotional magnitude) of the individual fixed. We show that face photographs manipulated to be more memorable (or more forgettable) are indeed more often remembered (or forgotten) in a crowd-sourcing experiment with an accuracy of 74%. Quantifying and modifying the 'memorability' of a face lends itself to many useful applications in computer vision and graphics, such as mnemonic aids for learning, photo editing applications for social networks and tools for designing memorable advertisements.
{"title":"Modifying the Memorability of Face Photographs","authors":"A. Khosla, Wilma A. Bainbridge, A. Torralba, A. Oliva","doi":"10.1109/ICCV.2013.397","DOIUrl":"https://doi.org/10.1109/ICCV.2013.397","url":null,"abstract":"Contemporary life bombards us with many new images of faces every day, which poses non-trivial constraints on human memory. The vast majority of face photographs are intended to be remembered, either because of personal relevance, commercial interests or because the pictures were deliberately designed to be memorable. Can we make a portrait more memorable or more forgettable automatically? Here, we provide a method to modify the memorability of individual face photographs, while keeping the identity and other facial traits (e.g. age, attractiveness, and emotional magnitude) of the individual fixed. We show that face photographs manipulated to be more memorable (or more forgettable) are indeed more often remembered (or forgotten) in a crowd-sourcing experiment with an accuracy of 74%. Quantifying and modifying the 'memorability' of a face lends itself to many useful applications in computer vision and graphics, such as mnemonic aids for learning, photo editing applications for social networks and tools for designing memorable advertisements.","PeriodicalId":6351,"journal":{"name":"2013 IEEE International Conference on Computer Vision","volume":"37 1","pages":"3200-3207"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90924104","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：