Cross-view Action Recognition via Transductive Transfer Learning

CASIA OpenIR > 智能感知与计算研究中心

	Cross-view Action Recognition via Transductive Transfer Learning
	Jie Qin; Zhaoxiang Zhang; Yunhong Wang
	2013-09-15
会议名称	International Conference on Image Processing
会议录名称	ICIP 2013
会议日期	15-18 September 2013
会议地点	Melbourne, Australia
摘要	Human action recognition is a hot topic in computer vision field. Various applicable approaches have been proposed to recognize different types of actions. However, the recognition performance deteriorates rapidly when the viewpoint changes. Traditional approaches aim to address the problem by inductive transfer learning, in which target-view samples are manually labeled. In this paper, we present a novel approach for cross-view action recognition based on transductive transfer learning. We address the problem by transferring instances across views. In our settings, both labels of examples from the target view and the corresponding relation between examples from pairwise views are dispensable. Experimental results on the IXMAS multi-view data set demonstrate the effectiveness of our approach, and are comparable to the state of the art.
关键词	Transductive Svm Action Recognition Transfer Learning
文献类型	会议论文
条目标识符	http://ir.ia.ac.cn/handle/173211/13286
专题	智能感知与计算研究中心
通讯作者	Zhaoxiang Zhang
推荐引用方式 GB/T 7714	Jie Qin,Zhaoxiang Zhang,Yunhong Wang. Cross-view Action Recognition via Transductive Transfer Learning[C],2013.