Action recognition by joint learning

CORC > 西安光学精密机械研究所 > 中国科学院西安光学精密机械研究所 > 光学影像学习与分析中心

	Action recognition by joint learning
	Yuan, Yuan; Qi, Lei; Lu, Xiaoqiang
刊名	image and vision computing
	2016-11-01
卷号	55 页码:77-85
关键词	Computer vision Action recognition Sparse coding Multinomial logistic regression (MLR) Joint learning
ISSN号	0262-8856
通讯作者	lu, xq (reprint author), chinese acad sci, state key lab transient opt & photon, ctr opt imagery anal & learning optimal, xian inst opt & precis mech, xian 710119, shaanxi, peoples r china.
产权排序	1
英文摘要	due to the promising applications including video surveillance, video annotation, and interaction gaming, human action recognition from videos has attracted much research interest. although various works have been proposed for human action recognition, there still exist many challenges such as illumination condition, viewpoint, camera motion and cluttered background. extracting discriminative representation is one of the main ways to handle these challenges. in this paper, we propose a novel action recognition method that simultaneously learns middle-level representation and classifier by jointly training a multinomial logistic regression (mlr) model and a discriminative dictionary. in the proposed method, sparse code of low-level representation, conducting as latent variables of mlr, can capture the structure of low-level feature and thus is more discriminate. meanwhile, the training of dictionary and mlr model are integrated into one objective function for considering the information of categories. by optimizing this objective function, we can learn a discriminative dictionary modulated by mlr and a mlr model driven by sparse coding. the proposed method is evaluated on youtube action dataset and hmdb51 dataset. experimental results demonstrate that our method is comparable with mainstream methods. (c) 2016 elsevier b.v. all rights reserved.
学科主题	computer science, artificial intelligence ; computer science, software engineering ; computer science, theory & methods ; engineering, electrical & electronic ; optics
WOS标题词	science & technology ; technology ; physical sciences
类目[WOS]	computer science, artificial intelligence ; computer science, software engineering ; computer science, theory & methods ; engineering, electrical & electronic ; optics
研究领域[WOS]	computer science ; engineering ; optics
收录类别	SCI
语种	英语
WOS记录号	WOS:000389164300005
内容类型	期刊论文
源URL	[http://ir.opt.ac.cn/handle/181661/28564]
专题	西安光学精密机械研究所_光学影像学习与分析中心
作者单位	Chinese Acad Sci, State Key Lab Transient Opt & Photon, Ctr OPT IMagery Anal & Learning OPTIMAL, Xian Inst Opt & Precis Mech, Xian 710119, Shaanxi, Peoples R China
推荐引用方式 GB/T 7714	Yuan, Yuan,Qi, Lei,Lu, Xiaoqiang. Action recognition by joint learning[J]. image and vision computing,2016,55:77-85.
APA	Yuan, Yuan,Qi, Lei,&Lu, Xiaoqiang.(2016).Action recognition by joint learning.image and vision computing,55,77-85.
MLA	Yuan, Yuan,et al."Action recognition by joint learning".image and vision computing 55(2016):77-85.