| Selecting Key Poses on Manifold for Pairwise Action Recognition | |
| Cao, Xianbin1,2; Ning, Bo1; Yan, Pingkun3; Li, Xuelong3 | |
| 作者部门 | 光学影像分析与学习中心 |
| 2012-02-01 | |
| 发表期刊 | IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
 |
| ISSN | 1551-3203 |
| 卷号 | 8期号:1页码:168-177 |
| 产权排序 | 3 |
| 摘要 | In action recognition, bag of visual words based approaches have been shown to be successful, for which the quality of codebook is critical. In a large vocabulary of poses (visual words), some key poses play a more decisive role than others in the codebook. This paper proposes a novel approach for key poses selection, which models the descriptor space utilizing a manifold learning technique to recover the geometric structure of the descriptors on a lower dimensional manifold. A PageRank-based centrality measure is developed to select key poses according to the recovered geometric structure. In each step, a key pose is selected from the manifold and the remaining model is modified to maximize the discriminative power of selected codebook. With the obtained codebook, each action can be represented with a histogram of the key poses. To solve the ambiguity between some action classes, a pairwise subdivision is executed to select discriminative codebooks for further recognition. Experiments on benchmark datasets showed that our method is able to obtain better performance compared with other state-of-the-art methods. |
| 文章类型 | Article |
| 关键词 | Action Recognition Bag Of Words Centrality Measure Key Poses Manifold Leaning |
| 学科领域 | Automation & Control Systems |
| WOS标题词 | Science & Technology ; Technology |
| DOI | 10.1109/TII.2011.2172452 |
| 收录类别 | SCI ; EI |
| 关键词[WOS] | NONLINEAR DIMENSIONALITY REDUCTION ; HUMAN MOTION ; HUMAN MOVEMENT |
| 语种 | 英语 |
| WOS研究方向 | Automation & Control Systems ; Computer Science ; Engineering |
| WOS类目 | Automation & Control Systems ; Computer Science, Interdisciplinary Applications ; Engineering, Industrial |
| WOS记录号 | WOS:000299526800019 |
| 引用统计 | |
| 文献类型 | 期刊论文 |
| 条目标识符 | http://ir.opt.ac.cn/handle/181661/20248 |
| 专题 | 光谱成像技术研究室 |
| 作者单位 | 1.Univ Sci & Technol China, Hefei 230026, Peoples R China 2.BeiHang Univ, Beijing 100083, Peoples R China 3.Chinese Acad Sci, Ctr Opt Imagery Anal & Learning, State Key Lab Transient Opt & Photon, Xian Inst Opt & Precis Mech, Xian 710119, Peoples R China |
| 推荐引用方式 GB/T 7714 | Cao, Xianbin,Ning, Bo,Yan, Pingkun,et al. Selecting Key Poses on Manifold for Pairwise Action Recognition[J]. IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS,2012,8(1):168-177. |
| APA | Cao, Xianbin,Ning, Bo,Yan, Pingkun,&Li, Xuelong.(2012).Selecting Key Poses on Manifold for Pairwise Action Recognition.IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS,8(1),168-177. |
| MLA | Cao, Xianbin,et al."Selecting Key Poses on Manifold for Pairwise Action Recognition".IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS 8.1(2012):168-177. |
| 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 | ||
| Selecting Key Poses （1194KB） | 期刊论文 | 出版稿 | 限制开放 | CC BY | 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