QQ客服 官方微博 反馈留言

	Mining 3D Key-Pose-Motifs for Action Recognition
	Wang, Chunyu ; Wang, Yizhou ; Yuille, Alan L.
	2016
关键词	SEQUENTIAL PATTERNS DEPTH PERCEPTION DATABASES
英文摘要	Recognizing an action from a sequence of 3D skeletal poses is a challenging task. First, different actors may perform the same action in various styles. Second, the estimated poses are sometimes inaccurate. These challenges can cause large variations between instances of the same class. Third, the datasets are usually small, with only a few actors performing few repetitions of each action. Hence training complex classifiers risks over-fitting the data. We address this task by mining a set of key-pose-motifs for each action class. A key-pose-motif contains a set of ordered poses, which are required to be close but not necessarily adjacent in the action sequences. The representation is robust to style variations. The key-pose-motifs are represented in terms of a dictionary using soft-quantization to deal with inaccuracies caused by quantization. We propose an efficient algorithm to mine key-pose-motifs taking into account of these probabilities. We classify a sequence by matching it to the motifs of each class and selecting the class that maximizes the matching score. This simple classifier obtains state-of-the-art performance on two benchmark datasets.; ONR [N00014-15-1-2356]; NSF Expedition NSF [CCF-1317376]; [973-2015CB351800]; [NSFC-61272027]; [NSFC-61231010]; [NSFC-61527804]; [NSFC-61210005]; CPCI-S(ISTP); 2639-2647
语种	英语
出处	29th IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
DOI标识	10.1109/CVPR.2016.289
内容类型	其他
源URL	[http://ir.pku.edu.cn/handle/20.500.11897/470252]
专题	信息科学技术学院
推荐引用方式 GB/T 7714	Wang, Chunyu,Wang, Yizhou,Yuille, Alan L.. Mining 3D Key-Pose-Motifs for Action Recognition. 2016-01-01.

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。