Adaptive learning codebook for action recognition
文献类型：期刊论文
| 作者 | Kong, Yu1,2; Zhang, Xiaoqin2; Hu, Weiming2 ; Jia, Yunde1
|
| 刊名 | PATTERN RECOGNITION LETTERS
 |
| 出版日期 | 2011-06-01 |
| 卷号 | 32期号:8页码:1178-1186 |
| 关键词 | Action recognition Visual codebook Metric learning |
| 英文摘要 | Learning a compact and yet discriminative codebook is an important procedure for local feature-based action recognition. A common procedure involves two independent phases: reducing the dimensionality of local features and then performing clustering. Since the two phases are disconnected, dimensionality reduction does not necessarily capture the dimensions that are greatly helpful for codebook creation. What's more, some dimensionality reduction techniques such as the principal component analysis do not take class separability into account and thus may not help build an effective codebook. In this paper, we propose the weighted adaptive metric learning (WAML) which integrates the two independent phases into a unified optimization framework. This framework enables to select indispensable and crucial dimensions for building a discriminative codebook. The dimensionality reduction phase in the WAML is optimized for class separability and adaptively adjusts the distance metric to improve the separability of data. In addition, the video word weighting is smoothly incorporated into the WAML to accurately generate video words. Experimental results demonstrate that our approach builds a highly discriminative codebook and achieves comparable results to other state-of-the-art approaches. (C) 2011 Elsevier B.V. All rights reserved. |
| WOS标题词 | Science & Technology ; Technology |
| 类目[WOS] | Computer Science, Artificial Intelligence |
| 研究领域[WOS] | Computer Science |
| 收录类别 | SCI |
| 语种 | 英语 |
| WOS记录号 | WOS:000290745100011 |
| 源URL | [http://ir.ia.ac.cn/handle/173211/3245]  |
| 专题 | 自动化研究所_模式识别国家重点实验室_视频内容安全团队 |
| 作者单位 | 1.Beijing Inst Technol, Sch Comp Sci, Beijing Lab Intelligent Informat Technol, Beijing 100081, Peoples R China 2.Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China |
| 推荐引用方式 GB/T 7714 | Kong, Yu,Zhang, Xiaoqin,Hu, Weiming,et al. Adaptive learning codebook for action recognition[J]. PATTERN RECOGNITION LETTERS,2011,32(8):1178-1186. |
| APA | Kong, Yu,Zhang, Xiaoqin,Hu, Weiming,&Jia, Yunde.(2011).Adaptive learning codebook for action recognition.PATTERN RECOGNITION LETTERS,32(8),1178-1186. |
| MLA | Kong, Yu,et al."Adaptive learning codebook for action recognition".PATTERN RECOGNITION LETTERS 32.8(2011):1178-1186. |
入库方式： OAI收割
来源：自动化研究所
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。