Content-based retrieval of human actions from realistic video databases

Jones, Simon and Shao, Ling (2013) Content-based retrieval of human actions from realistic video databases. Information Sciences, 236. pp. 56-65. ISSN 0020-0255

Full text not available from this repository.


Due to the increasing amount of video data available in various databases, on the Internet and elsewhere, new methods of managing these data are required, leading to the development of content-based video retrieval systems. We explore several recently developed action representation and information retrieval techniques in a human action retrieval system. These techniques include various means of local feature extraction; soft-assignment clustering; Bag-of-Words, vocabulary guided and spatio-temporal pyramid matches for action representation; SVMs and ABRS-SVMs for relevance feedback. Successful application of relevance feedback in particular will result in far more practical systems. We evaluate the performance of several combinations of the above techniques in three realistic action datasets: UCF Sports, UCF YouTube and HOHA2.

Item Type: Article
Uncontrolled Keywords: content-based video retrieval,relevance feedback,human action recognition
Faculty \ School: Faculty of Science > School of Computing Sciences
Depositing User: Pure Connector
Date Deposited: 07 Feb 2017 02:39
Last Modified: 22 Oct 2022 02:13
DOI: 10.1016/j.ins.2013.02.018

Actions (login required)

View Item View Item