Principal motion components for one-shot gesture recognition

doi:10.1007/s10044-015-0481-3

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 生物识别与安全技术

	Principal motion components for one-shot gesture recognition
	Escalante, Hugo Jair 1,2; Guyon, Isabelle 2; Athitsos, Vassilis 3; Jangyodsuk, Pat 3; Wan, Jun4
发表期刊	PATTERN ANALYSIS AND APPLICATIONS
	2017-02-01
卷号	20 期号:1 页码:167-182
文章类型	Article
摘要	This paper introduces principal motion components (PMC), a new method for one-shot gesture recognition. In the considered scenario a single training video is available for each gesture to be recognized, which limits the application of traditional techniques (e.g., HMMs). In PMC, a 2D map of motion energy is obtained per each pair of consecutive frames in a video. Motion maps associated to a video are processed to obtain a PCA model, which is used for recognition under a reconstruction-error approach. The main benefits of the proposed approach are its simplicity, easiness of implementation, competitive performance and efficiency. We report experimental results in one-shot gesture recognition using the ChaLearn Gesture Dataset; a benchmark comprising more than 50,000 gestures, recorded as both RGB and depth video with a Kinect (TM) camera. Results obtained with PMC are competitive with alternative methods proposed for the same data set.
关键词	Motion Energy Maps Pca One-shot Learning Gesture Recognition Chalearn Gesture Challenge
WOS标题词	Science & Technology ; Technology
DOI	10.1007/s10044-015-0481-3
关键词[WOS]	PCA ; RECONSTRUCTION ; HISTOGRAMS
收录类别	SCI
语种	英语
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence
WOS记录号	WOS:000393053200012
引用统计	被引频次：20[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/14370
专题	多模态人工智能系统全国重点实验室_生物识别与安全技术
作者单位	1.Inst Nacl Astrfis Opt & Elect, Luis Enrique Erro 1, Puebla 72840, Mexico 2.ChaLearn, 955 Creston Rd, Berkeley, CA 94708 USA 3.Univ Texas Arlington, Comp Sci & Engn Dept, 701 S Nedderman Dr, Arlington, TX 76019 USA 4.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Escalante, Hugo Jair,Guyon, Isabelle,Athitsos, Vassilis,et al. Principal motion components for one-shot gesture recognition[J]. PATTERN ANALYSIS AND APPLICATIONS,2017,20(1):167-182.
APA	Escalante, Hugo Jair,Guyon, Isabelle,Athitsos, Vassilis,Jangyodsuk, Pat,&Wan, Jun.(2017).Principal motion components for one-shot gesture recognition.PATTERN ANALYSIS AND APPLICATIONS,20(1),167-182.
MLA	Escalante, Hugo Jair,et al."Principal motion components for one-shot gesture recognition".PATTERN ANALYSIS AND APPLICATIONS 20.1(2017):167-182.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
PAA2017_gesture.pdf（3519KB）	期刊论文	作者接受稿	开放获取	CC BY-NC-SA	浏览下载