QQ客服 官方微博 反馈留言

	Learning discriminative visual codebook for human action recognition
	Lei, Qing ; Li, Shao-Zi ; Zhang, Hong-Bo ; Li SZ(李绍滋)
刊名	http://dx.doi.org/10.4304/jcp.8.12.3093-3102
	2013
关键词	Computer science
英文摘要	This paper explores how to improve BOW model for human action recognition in real environment. Traditional codebook learning uses single appearance based local features, thus spatial and temporal correlations of local features are ignored. This leads to a considerable amount of mismatch between sample vectors and noisy visual words resulted from background clutters. To improve the performance of BOW modeling in real settings, we propose a novel action modeling approach. First, two-level feature selection is applied in the pre-process phase of codebook learning to remove noisy features, thus descriptive and discriminative features are obtained. Then spatial-temporal pyramid matching (STPM) is employed in the feature coding process, in which we model human actions considering not only the appearance similarity between local features but also the spatial relationship of features in space and time. We validate our approach on several benchmark datasets and experimental results show that our approach significantly outperforms K-means clustering on more challenge datasets such as KTH, UCF sports and Youtube datasets. ? 2013 ACADEMY PUBLISHER.
语种	英语
出版者	Academy Publisher
内容类型	期刊论文
源URL	[http://dspace.xmu.edu.cn/handle/2288/92644]
专题	信息技术－已发表论文
推荐引用方式 GB/T 7714	Lei, Qing,Li, Shao-Zi,Zhang, Hong-Bo,et al. Learning discriminative visual codebook for human action recognition[J]. http://dx.doi.org/10.4304/jcp.8.12.3093-3102,2013.
APA	Lei, Qing,Li, Shao-Zi,Zhang, Hong-Bo,&李绍滋.(2013).Learning discriminative visual codebook for human action recognition.http://dx.doi.org/10.4304/jcp.8.12.3093-3102.
MLA	Lei, Qing,et al."Learning discriminative visual codebook for human action recognition".http://dx.doi.org/10.4304/jcp.8.12.3093-3102 (2013).

个性服务

查看访问统计

相关权益政策

暂无数据

收藏/分享

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。