Martin Köstinger, Paul Wohlhart, P. Roth, H. Bischof
In this paper, we raise important issues concerning the evaluation complexity of existing Mahalanobis metric learning methods. The complexity scales linearly with the size of the dataset. This is especially cumbersome on large scale or for real-time applications with limited time budget. To alleviate this problem we propose to represent the dataset by a fixed number of discriminative prototypes. In particular, we introduce a new method that jointly chooses the positioning of prototypes and also optimizes the Mahalanobis distance metric with respect to these. We show that choosing the positioning of the prototypes and learning the metric in parallel leads to a drastically reduced evaluation effort while maintaining the discriminative essence of the original dataset. Moreover, for most problems our method performing k-nearest prototype (k-NP) classification on the condensed dataset leads to even better generalization compared to k-NN classification using all data. Results on a variety of challenging benchmarks demonstrate the power of our method. These include standard machine learning datasets as well as the challenging Public Figures Face Database. On the competitive machine learning benchmarks we are comparable to the state-of-the-art while being more efficient. On the face benchmark we clearly outperform the state-of-the-art in Mahalanobis metric learning with drastically reduced evaluation effort.
{"title":"Joint Learning of Discriminative Prototypes and Large Margin Nearest Neighbor Classifiers","authors":"Martin Köstinger, Paul Wohlhart, P. Roth, H. Bischof","doi":"10.1109/ICCV.2013.386","DOIUrl":"https://doi.org/10.1109/ICCV.2013.386","url":null,"abstract":"In this paper, we raise important issues concerning the evaluation complexity of existing Mahalanobis metric learning methods. The complexity scales linearly with the size of the dataset. This is especially cumbersome on large scale or for real-time applications with limited time budget. To alleviate this problem we propose to represent the dataset by a fixed number of discriminative prototypes. In particular, we introduce a new method that jointly chooses the positioning of prototypes and also optimizes the Mahalanobis distance metric with respect to these. We show that choosing the positioning of the prototypes and learning the metric in parallel leads to a drastically reduced evaluation effort while maintaining the discriminative essence of the original dataset. Moreover, for most problems our method performing k-nearest prototype (k-NP) classification on the condensed dataset leads to even better generalization compared to k-NN classification using all data. Results on a variety of challenging benchmarks demonstrate the power of our method. These include standard machine learning datasets as well as the challenging Public Figures Face Database. On the competitive machine learning benchmarks we are comparable to the state-of-the-art while being more efficient. On the face benchmark we clearly outperform the state-of-the-art in Mahalanobis metric learning with drastically reduced evaluation effort.","PeriodicalId":6351,"journal":{"name":"2013 IEEE International Conference on Computer Vision","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76760411","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}
Matthijs Douze, Jérôme Revaud, C. Schmid, H. Jégou
This paper makes two complementary contributions to event retrieval in large collections of videos. First, we propose hyper-pooling strategies that encode the frame descriptors into a representation of the video sequence in a stable manner. Our best choices compare favorably with regular pooling techniques based on k-means quantization. Second, we introduce a technique to improve the ranking. It can be interpreted either as a query expansion method or as a similarity adaptation based on the local context of the query video descriptor. Experiments on public benchmarks show that our methods are complementary and improve event retrieval results, without sacrificing efficiency.
{"title":"Stable Hyper-pooling and Query Expansion for Event Detection","authors":"Matthijs Douze, Jérôme Revaud, C. Schmid, H. Jégou","doi":"10.1109/ICCV.2013.229","DOIUrl":"https://doi.org/10.1109/ICCV.2013.229","url":null,"abstract":"This paper makes two complementary contributions to event retrieval in large collections of videos. First, we propose hyper-pooling strategies that encode the frame descriptors into a representation of the video sequence in a stable manner. Our best choices compare favorably with regular pooling techniques based on k-means quantization. Second, we introduce a technique to improve the ranking. It can be interpreted either as a query expansion method or as a similarity adaptation based on the local context of the query video descriptor. Experiments on public benchmarks show that our methods are complementary and improve event retrieval results, without sacrificing efficiency.","PeriodicalId":6351,"journal":{"name":"2013 IEEE International Conference on Computer Vision","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78129247","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 methods have been proposed to solve the image classification problem for a large number of categories. Among them, methods based on tree-based representations achieve good trade-off between accuracy and test time efficiency. While focusing on learning a tree-shaped hierarchy and the corresponding set of classifiers, most of them [11, 2, 14] use a greedy prediction algorithm for test time efficiency. We argue that the dramatic decrease in accuracy at high efficiency is caused by the specific design choice of the learning and greedy prediction algorithms. In this work, we propose a classifier which achieves a better trade-off between efficiency and accuracy with a given tree-shaped hierarchy. First, we convert the classification problem as finding the best path in the hierarchy, and a novel branch-and-bound-like algorithm is introduced to efficiently search for the best path. Second, we jointly train the classifiers using a novel Structured SVM (SSVM) formulation with additional bound constraints. As a result, our method achieves a significant 4.65%, 5.43%, and 4.07% (relative 24.82%, 41.64%, and 109.79%) improvement in accuracy at high efficiency compared to state-of-the-art greedy "tree-based" methods [14] on Caltech-256 [15], SUN [32] and Image Net 1K [9] dataset, respectively. Finally, we show that our branch-and-bound-like algorithm naturally ranks the paths in the hierarchy (Fig. 8) so that users can further process them.
为了解决大量类别的图像分类问题，已经提出了许多方法。其中，基于树表示的方法在准确率和测试时间效率之间取得了很好的平衡。在集中学习树形层次结构和相应的分类器集的同时，大多数[11,2,14]使用贪婪预测算法来提高测试时间效率。我们认为，高效率下准确率的急剧下降是由学习和贪婪预测算法的特定设计选择引起的。在这项工作中，我们提出了一个分类器，它在给定的树形层次结构中实现了效率和准确性之间的更好权衡。首先，我们将分类问题转化为在层次结构中寻找最佳路径，并引入了一种新颖的类分支定界算法来有效地搜索最佳路径。其次，我们使用具有附加约束的新型结构化支持向量机(SSVM)公式联合训练分类器。结果，与最先进的贪婪“基于树”的方法[14]相比，我们的方法在Caltech-256[15]、SUN[32]和Image Net 1K[9]数据集上的准确率分别提高了4.65%、5.43%和4.07%(相对于24.82%、41.64%和109.79%)。最后，我们展示了我们的分支绑定算法自然地对层次结构中的路径进行排序(图8)，以便用户可以进一步处理它们。
{"title":"Find the Best Path: An Efficient and Accurate Classifier for Image Hierarchies","authors":"Min Sun, Wanming Huang, S. Savarese","doi":"10.1109/ICCV.2013.40","DOIUrl":"https://doi.org/10.1109/ICCV.2013.40","url":null,"abstract":"Many methods have been proposed to solve the image classification problem for a large number of categories. Among them, methods based on tree-based representations achieve good trade-off between accuracy and test time efficiency. While focusing on learning a tree-shaped hierarchy and the corresponding set of classifiers, most of them [11, 2, 14] use a greedy prediction algorithm for test time efficiency. We argue that the dramatic decrease in accuracy at high efficiency is caused by the specific design choice of the learning and greedy prediction algorithms. In this work, we propose a classifier which achieves a better trade-off between efficiency and accuracy with a given tree-shaped hierarchy. First, we convert the classification problem as finding the best path in the hierarchy, and a novel branch-and-bound-like algorithm is introduced to efficiently search for the best path. Second, we jointly train the classifiers using a novel Structured SVM (SSVM) formulation with additional bound constraints. As a result, our method achieves a significant 4.65%, 5.43%, and 4.07% (relative 24.82%, 41.64%, and 109.79%) improvement in accuracy at high efficiency compared to state-of-the-art greedy \"tree-based\" methods [14] on Caltech-256 [15], SUN [32] and Image Net 1K [9] dataset, respectively. Finally, we show that our branch-and-bound-like algorithm naturally ranks the paths in the hierarchy (Fig. 8) so that users can further process them.","PeriodicalId":6351,"journal":{"name":"2013 IEEE International Conference on Computer Vision","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78193589","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 investigate the problem of recognizing occupations of multiple people with arbitrary poses in a photo. Previous work utilizing single person's nearly frontal clothing information and fore/background context preliminarily proves that occupation recognition is computationally feasible in computer vision. However, in practice, multiple people with arbitrary poses are common in a photo, and recognizing their occupations is even more challenging. We argue that with appropriately built visual attributes, co-occurrence, and spatial configuration model that is learned through structure SVM, we can recognize multiple people's occupations in a photo simultaneously. To evaluate our method's performance, we conduct extensive experiments on a new well-labeled occupation database with 14 representative occupations and over 7K images. Results on this database validate our method's effectiveness and show that occupation recognition is solvable in a more general case.
{"title":"What Do You Do? Occupation Recognition in a Photo via Social Context","authors":"Ming Shao, Liangyue Li, Y. Fu","doi":"10.1109/ICCV.2013.451","DOIUrl":"https://doi.org/10.1109/ICCV.2013.451","url":null,"abstract":"In this paper, we investigate the problem of recognizing occupations of multiple people with arbitrary poses in a photo. Previous work utilizing single person's nearly frontal clothing information and fore/background context preliminarily proves that occupation recognition is computationally feasible in computer vision. However, in practice, multiple people with arbitrary poses are common in a photo, and recognizing their occupations is even more challenging. We argue that with appropriately built visual attributes, co-occurrence, and spatial configuration model that is learned through structure SVM, we can recognize multiple people's occupations in a photo simultaneously. To evaluate our method's performance, we conduct extensive experiments on a new well-labeled occupation database with 14 representative occupations and over 7K images. Results on this database validate our method's effectiveness and show that occupation recognition is solvable in a more general case.","PeriodicalId":6351,"journal":{"name":"2013 IEEE International Conference on Computer Vision","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75121827","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}
While saliency in images has been extensively studied in recent years, there is very little work on saliency of point sets. This is despite the fact that point sets and range data are becoming ever more widespread and have myriad applications. In this paper we present an algorithm for detecting the salient points in unorganized 3D point sets. Our algorithm is designed to cope with extremely large sets, which may contain tens of millions of points. Such data is typical of urban scenes, which have recently become commonly available on the web. No previous work has handled such data. For general data sets, we show that our results are competitive with those of saliency detection of surfaces, although we do not have any connectivity information. We demonstrate the utility of our algorithm in two applications: producing a set of the most informative viewpoints and suggesting an informative city tour given a city scan.
{"title":"Saliency Detection in Large Point Sets","authors":"Elizabeth Shtrom, G. Leifman, A. Tal","doi":"10.1109/ICCV.2013.446","DOIUrl":"https://doi.org/10.1109/ICCV.2013.446","url":null,"abstract":"While saliency in images has been extensively studied in recent years, there is very little work on saliency of point sets. This is despite the fact that point sets and range data are becoming ever more widespread and have myriad applications. In this paper we present an algorithm for detecting the salient points in unorganized 3D point sets. Our algorithm is designed to cope with extremely large sets, which may contain tens of millions of points. Such data is typical of urban scenes, which have recently become commonly available on the web. No previous work has handled such data. For general data sets, we show that our results are competitive with those of saliency detection of surfaces, although we do not have any connectivity information. We demonstrate the utility of our algorithm in two applications: producing a set of the most informative viewpoints and suggesting an informative city tour given a city scan.","PeriodicalId":6351,"journal":{"name":"2013 IEEE International Conference on Computer Vision","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75257843","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}
Recently, there is a considerable amount of efforts devoted to the problem of unconstrained face verification, where the task is to predict whether pairs of images are from the same person or not. This problem is challenging and difficult due to the large variations in face images. In this paper, we develop a novel regularization framework to learn similarity metrics for unconstrained face verification. We formulate its objective function by incorporating the robustness to the large intra-personal variations and the discriminative power of novel similarity metrics. In addition, our formulation is a convex optimization problem which guarantees the existence of its global solution. Experiments show that our proposed method achieves the state-of-the-art results on the challenging Labeled Faces in the Wild (LFW) database [10].
{"title":"Similarity Metric Learning for Face Recognition","authors":"Qiong Cao, Yiming Ying, Peng Li","doi":"10.1109/ICCV.2013.299","DOIUrl":"https://doi.org/10.1109/ICCV.2013.299","url":null,"abstract":"Recently, there is a considerable amount of efforts devoted to the problem of unconstrained face verification, where the task is to predict whether pairs of images are from the same person or not. This problem is challenging and difficult due to the large variations in face images. In this paper, we develop a novel regularization framework to learn similarity metrics for unconstrained face verification. We formulate its objective function by incorporating the robustness to the large intra-personal variations and the discriminative power of novel similarity metrics. In addition, our formulation is a convex optimization problem which guarantees the existence of its global solution. Experiments show that our proposed method achieves the state-of-the-art results on the challenging Labeled Faces in the Wild (LFW) database [10].","PeriodicalId":6351,"journal":{"name":"2013 IEEE International Conference on Computer Vision","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75270525","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 handle a special type of motion blur considering that cameras move primarily forward or backward. Solving this type of blur is of unique practical importance since nearly all car, traffic and bike-mounted cameras follow out-of-plane translational motion. We start with the study of geometric models and analyze the difficulty of existing methods to deal with them. We also propose a solution accounting for depth variation. Homographies associated with different 3D planes are considered and solved for in an optimization framework. Our method is verified on several natural image examples that cannot be satisfyingly dealt with by previous methods.
{"title":"Forward Motion Deblurring","authors":"Shicheng Zheng, Li Xu, Jiaya Jia","doi":"10.1109/ICCV.2013.185","DOIUrl":"https://doi.org/10.1109/ICCV.2013.185","url":null,"abstract":"We handle a special type of motion blur considering that cameras move primarily forward or backward. Solving this type of blur is of unique practical importance since nearly all car, traffic and bike-mounted cameras follow out-of-plane translational motion. We start with the study of geometric models and analyze the difficulty of existing methods to deal with them. We also propose a solution accounting for depth variation. Homographies associated with different 3D planes are considered and solved for in an optimization framework. Our method is verified on several natural image examples that cannot be satisfyingly dealt with by previous methods.","PeriodicalId":6351,"journal":{"name":"2013 IEEE International Conference on Computer Vision","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75716635","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}
Edge detection is a critical component of many vision systems, including object detectors and image segmentation algorithms. Patches of edges exhibit well-known forms of local structure, such as straight lines or T-junctions. In this paper we take advantage of the structure present in local image patches to learn both an accurate and computationally efficient edge detector. We formulate the problem of predicting local edge masks in a structured learning framework applied to random decision forests. Our novel approach to learning decision trees robustly maps the structured labels to a discrete space on which standard information gain measures may be evaluated. The result is an approach that obtains real time performance that is orders of magnitude faster than many competing state-of-the-art approaches, while also achieving state-of-the-art edge detection results on the BSDS500 Segmentation dataset and NYU Depth dataset. Finally, we show the potential of our approach as a general purpose edge detector by showing our learned edge models generalize well across datasets.
{"title":"Structured Forests for Fast Edge Detection","authors":"Piotr Dollár, C. L. Zitnick","doi":"10.1109/ICCV.2013.231","DOIUrl":"https://doi.org/10.1109/ICCV.2013.231","url":null,"abstract":"Edge detection is a critical component of many vision systems, including object detectors and image segmentation algorithms. Patches of edges exhibit well-known forms of local structure, such as straight lines or T-junctions. In this paper we take advantage of the structure present in local image patches to learn both an accurate and computationally efficient edge detector. We formulate the problem of predicting local edge masks in a structured learning framework applied to random decision forests. Our novel approach to learning decision trees robustly maps the structured labels to a discrete space on which standard information gain measures may be evaluated. The result is an approach that obtains real time performance that is orders of magnitude faster than many competing state-of-the-art approaches, while also achieving state-of-the-art edge detection results on the BSDS500 Segmentation dataset and NYU Depth dataset. Finally, we show the potential of our approach as a general purpose edge detector by showing our learned edge models generalize well across datasets.","PeriodicalId":6351,"journal":{"name":"2013 IEEE International Conference on Computer Vision","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74677878","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}
S. Karthikeyan, V. Jagadeesh, Renuka Shenoy, M. Eckstein, B. S. Manjunath
Eye movement studies have confirmed that overt attention is highly biased towards faces and text regions in images. In this paper we explore a novel problem of predicting face and text regions in images using eye tracking data from multiple subjects. The problem is challenging as we aim to predict the semantics (face/text/background) only from eye tracking data without utilizing any image information. The proposed algorithm spatially clusters eye tracking data obtained in an image into different coherent groups and subsequently models the likelihood of the clusters containing faces and text using a fully connected Markov Random Field (MRF). Given the eye tracking data from a test image, it predicts potential face/head (humans, dogs and cats) and text locations reliably. Furthermore, the approach can be used to select regions of interest for further analysis by object detectors for faces and text. The hybrid eye position/object detector approach achieves better detection performance and reduced computation time compared to using only the object detection algorithm. We also present a new eye tracking dataset on 300 images selected from ICDAR, Street-view, Flickr and Oxford-IIIT Pet Dataset from 15 subjects.
{"title":"From Where and How to What We See","authors":"S. Karthikeyan, V. Jagadeesh, Renuka Shenoy, M. Eckstein, B. S. Manjunath","doi":"10.1109/ICCV.2013.83","DOIUrl":"https://doi.org/10.1109/ICCV.2013.83","url":null,"abstract":"Eye movement studies have confirmed that overt attention is highly biased towards faces and text regions in images. In this paper we explore a novel problem of predicting face and text regions in images using eye tracking data from multiple subjects. The problem is challenging as we aim to predict the semantics (face/text/background) only from eye tracking data without utilizing any image information. The proposed algorithm spatially clusters eye tracking data obtained in an image into different coherent groups and subsequently models the likelihood of the clusters containing faces and text using a fully connected Markov Random Field (MRF). Given the eye tracking data from a test image, it predicts potential face/head (humans, dogs and cats) and text locations reliably. Furthermore, the approach can be used to select regions of interest for further analysis by object detectors for faces and text. The hybrid eye position/object detector approach achieves better detection performance and reduced computation time compared to using only the object detection algorithm. We also present a new eye tracking dataset on 300 images selected from ICDAR, Street-view, Flickr and Oxford-IIIT Pet Dataset from 15 subjects.","PeriodicalId":6351,"journal":{"name":"2013 IEEE International Conference on Computer Vision","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74679659","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}
Wei-Xin Li, Qian Yu, Ajay Divakaran, N. Vasconcelos
The problem of adaptively selecting pooling regions for the classification of complex video events is considered. Complex events are defined as events composed of several characteristic behaviors, whose temporal configuration can change from sequence to sequence. A dynamic pooling operator is defined so as to enable a unified solution to the problems of event specific video segmentation, temporal structure modeling, and event detection. Video is decomposed into segments, and the segments most informative for detecting a given event are identified, so as to dynamically determine the pooling operator most suited for each sequence. This dynamic pooling is implemented by treating the locations of characteristic segments as hidden information, which is inferred, on a sequence-by-sequence basis, via a large-margin classification rule with latent variables. Although the feasible set of segment selections is combinatorial, it is shown that a globally optimal solution to the inference problem can be obtained efficiently, through the solution of a series of linear programs. Besides the coarse-level location of segments, a finer model of video structure is implemented by jointly pooling features of segment-tuples. Experimental evaluation demonstrates that the resulting event detector has state-of-the-art performance on challenging video datasets.
{"title":"Dynamic Pooling for Complex Event Recognition","authors":"Wei-Xin Li, Qian Yu, Ajay Divakaran, N. Vasconcelos","doi":"10.1109/ICCV.2013.339","DOIUrl":"https://doi.org/10.1109/ICCV.2013.339","url":null,"abstract":"The problem of adaptively selecting pooling regions for the classification of complex video events is considered. Complex events are defined as events composed of several characteristic behaviors, whose temporal configuration can change from sequence to sequence. A dynamic pooling operator is defined so as to enable a unified solution to the problems of event specific video segmentation, temporal structure modeling, and event detection. Video is decomposed into segments, and the segments most informative for detecting a given event are identified, so as to dynamically determine the pooling operator most suited for each sequence. This dynamic pooling is implemented by treating the locations of characteristic segments as hidden information, which is inferred, on a sequence-by-sequence basis, via a large-margin classification rule with latent variables. Although the feasible set of segment selections is combinatorial, it is shown that a globally optimal solution to the inference problem can be obtained efficiently, through the solution of a series of linear programs. Besides the coarse-level location of segments, a finer model of video structure is implemented by jointly pooling features of segment-tuples. Experimental evaluation demonstrates that the resulting event detector has state-of-the-art performance on challenging video datasets.","PeriodicalId":6351,"journal":{"name":"2013 IEEE International Conference on Computer Vision","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73043738","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：