Unsupervised learning of human action categories in still images with deep representations | |
Zheng, Yunpeng1; Li, Xuelong2; Lu, Xiaoqiang3 | |
作者部门 | 光谱成像技术研究室 |
2019-12 | |
发表期刊 | ACM Transactions on Multimedia Computing, Communications and Applications |
ISSN | 15516857;15516865 |
卷号 | 15期号:4 |
产权排序 | 3 |
摘要 | In this article, we propose a novel method for unsupervised learning of human action categories in still images. In contrast to previous methods, the proposed method explores distinctive information of actions directly from unlabeled image databases, attempting to learn discriminative deep representations in an unsupervised manner to distinguish different actions. In the proposed method, action image collections can be used without manual annotations. Specifically, (i) to deal with the problem that unsupervised discriminative deep representations are difficult to learn, the proposed method builds a training dataset with surrogate labels from the unlabeled dataset, then learns discriminative representations by alternately updating convolutional neural network (CNN) parameters and the surrogate training dataset in an iterative manner; (ii) to explore the discriminatory information among different action categories, training batches for updating the CNN parameters are built with triplet groups and the triplet loss function is introduced to update the CNN parameters; and (iii) to learn more discriminative deep representations, a Random Forest classifier is adopted to update the surrogate training dataset, and more beneficial triplet groups then can be built with the updated surrogate training dataset. Extensive experiments on four benchmark datasets demonstrate the effectiveness of the proposed method. © 2019 Association for Computing Machinery. |
关键词 | Action categorization unsupervised learning deep representations |
DOI | 10.1145/3362161 |
收录类别 | SCI ; EI |
语种 | 英语 |
WOS记录号 | WOS:000512285800012 |
出版者 | Association for Computing Machinery |
EI入藏号 | 20195207939683 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.opt.ac.cn/handle/181661/83119 |
专题 | 光谱成像技术研究室 |
通讯作者 | Lu, Xiaoqiang |
作者单位 | 1.Key Laboratory of Spectral Imaging Technology CAS, Xi'an Institute of Optics and PrecisionMechanics, ChineseAcademy of Sciences, University of ChineseAcademy of Sciences, China; 2.School of Computer Science and Center for OPTical IMagery Analysis and Learning (OPTIMAL), Northwestern Polytechnical University, China; 3.Key Laboratory of Spectral Imaging Technology CAS, Xi'an Institute of Optics and Precision Mechanics, Chinese Academy of Sciences, China |
推荐引用方式 GB/T 7714 | Zheng, Yunpeng,Li, Xuelong,Lu, Xiaoqiang. Unsupervised learning of human action categories in still images with deep representations[J]. ACM Transactions on Multimedia Computing, Communications and Applications,2019,15(4). |
APA | Zheng, Yunpeng,Li, Xuelong,&Lu, Xiaoqiang.(2019).Unsupervised learning of human action categories in still images with deep representations.ACM Transactions on Multimedia Computing, Communications and Applications,15(4). |
MLA | Zheng, Yunpeng,et al."Unsupervised learning of human action categories in still images with deep representations".ACM Transactions on Multimedia Computing, Communications and Applications 15.4(2019). |
条目包含的文件 | ||||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Unsupervised learnin(23484KB) | 期刊论文 | 出版稿 | 限制开放 | CC BY-NC-SA | 请求全文 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论