Localized Multiple Kernel Learning for Realistic Human Action Recognition in Videos
文献类型：期刊论文
| 作者 | Song, Yan2; Zheng, Yan-Tao3; Tang, Sheng; Zhou, Xiangdong1; Zhang, Yongdong; Lin, Shouxun; Chua, Tat-Seng4 |
| 刊名 | IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
 |
| 出版日期 | 2011-09-01 |
| 卷号 | 21期号:9页码:1193-1202 |
| 关键词 | Action recognition localized classifier multiple kernel learning |
| ISSN号 | 1051-8215 |
| DOI | 10.1109/TCSVT.2011.2130230 |
| 英文摘要 | Realistic human action recognition in videos has been a useful yet challenging task. Video shots of same actions may present huge intra-class variations in terms of visual appearance, kinetic patterns, video shooting, and editing styles. Heterogeneous feature representations of videos pose another challenge on how to effectively handle the redundancy, complementariness and disagreement in these features. This paper proposes a localized multiple kernel learning (L-MKL) algorithm to tackle the issues above. L-MKL integrates the localized classifier ensemble learning and multiple kernel learning in a unified framework to leverage the strengths of both. The basis of L-MKL is to build multiple kernel classifiers on diverse features at subspace localities of heterogeneous representations. L-MKL integrates the discriminability of complementary features locally and enables localized MKL classifiers to deliver better performance in its own region of expertise. Specifically, L-MKL develops a locality gating model to partition the input space of heterogeneous representations to a set of localities of simpler data structure. Each locality then learns its localized optimal combination of Mercer kernels of heterogeneous features. Finally, the gating model coordinates the localized multiple kernel classifiers globally to perform action recognition. Experiments on two datasets show that the proposed approach delivers promising performance. |
| 资助项目 | National Basic Research Program of China (973 Program)[2007CB311105] ; National Nature Science Foundation of China[60873165] ; Beijing Municipal Education Commission |
| WOS研究方向 | Engineering |
| 语种 | 英语 |
| WOS记录号 | WOS:000294669900002 |
| 出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| 源URL | [http://119.78.100.204/handle/2XEOYT63/12979]  |
| 专题 | 中国科学院计算技术研究所期刊论文_英文 |
| 通讯作者 | Song, Yan |
| 作者单位 | 1.Fudan Univ, Sch Comp Sci & Technol, Shanghai 200433, Peoples R China 2.Chinese Acad Sci, Lab Adv Comp Res, Inst Comp Technol, Beijing 100190, Peoples R China 3.ASTAR, Inst Infocomm Res, Singapore, Singapore 4.Natl Univ Singapore, Sch Comp, Singapore 117548, Singapore |
| 推荐引用方式 GB/T 7714 | Song, Yan,Zheng, Yan-Tao,Tang, Sheng,et al. Localized Multiple Kernel Learning for Realistic Human Action Recognition in Videos[J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,2011,21(9):1193-1202. |
| APA | Song, Yan.,Zheng, Yan-Tao.,Tang, Sheng.,Zhou, Xiangdong.,Zhang, Yongdong.,...&Chua, Tat-Seng.(2011).Localized Multiple Kernel Learning for Realistic Human Action Recognition in Videos.IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,21(9),1193-1202. |
| MLA | Song, Yan,et al."Localized Multiple Kernel Learning for Realistic Human Action Recognition in Videos".IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 21.9(2011):1193-1202. |
入库方式： OAI收割
来源：计算技术研究所
浏览0
下载0
收藏0
其他版本
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。