Fast action retrieval from videos via feature disaggregation

doi:10.1016/j.cviu.2016.09.009

CORC > 北京大学 > 信息科学技术学院

	Fast action retrieval from videos via feature disaggregation
	Qin, Jie ; Liu, Li ; Yu, Mengyang ; Wang, Yunhong ; Shao, Ling
刊名	COMPUTER VISION AND IMAGE UNDERSTANDING
	2017
关键词	Similarity search Video retrieval Feature disaggregation Learning based hashing ACTION RECOGNITION QUANTIZATION SEARCH
DOI	10.1016/j.cviu.2016.09.009
英文摘要	Learning based hashing methods, which aim at learning similarity-preserving binary codes for efficient nearest neighbor search, have been actively studied recently. A majority of the approaches address hashing problems for image collections. However, due to the extra temporal information, videos are usually represented by much higher dimensional (thousands or even more) features compared with images, causing high computational complexity for conventional hashing schemes. In this paper, we propose a simple and efficient hashing scheme for high-dimensional video data. This method, called Disaggregation Hashing (DH), exploits the correlations among different feature dimensions. An intuitive feature disaggregation method is first proposed, followed by a novel hashing algorithm based on different feature clusters. Additionally, a kernelized version of DH is proposed for better performance. We demonstrate the efficiency and effectiveness of our method by theoretical analysis and exploring its application on action retrieval from video databases. Extensive experiments show the superiority of our binary coding scheme over state-of-the-art hashing methods. (C) 2016 Elsevier Inc. All rights reserved.; Hong Kong, Macao and Taiwan Science & Technology Cooperation Program of China [L2015TGA9004]; Foundation for Innovative Research Groups of the National Natural Science Foundation of China [61573045, 61421003]; National Natural Science Foundation of China [61528106]; China Scholarship Council; Northumbria University; SCI(E); ARTICLE; 104-116; 156
语种	英语
内容类型	期刊论文
源URL	[http://ir.pku.edu.cn/handle/20.500.11897/462388]
专题	信息科学技术学院
推荐引用方式 GB/T 7714	Qin, Jie,Liu, Li,Yu, Mengyang,et al. Fast action retrieval from videos via feature disaggregation[J]. COMPUTER VISION AND IMAGE UNDERSTANDING,2017.
APA	Qin, Jie,Liu, Li,Yu, Mengyang,Wang, Yunhong,&Shao, Ling.(2017).Fast action retrieval from videos via feature disaggregation.COMPUTER VISION AND IMAGE UNDERSTANDING.
MLA	Qin, Jie,et al."Fast action retrieval from videos via feature disaggregation".COMPUTER VISION AND IMAGE UNDERSTANDING (2017).