Please use this identifier to cite or link to this item:
Title: Exploring probabilistic localized video representation for human action recognition
Authors: Song, Y.
Tang, S.
Zheng, Y.-T.
Chua, T.-S. 
Zhang, Y.
Lin, S.
Keywords: Human action recognition
Information-theoretic video matching
Probabilistic video representation
Issue Date: 2012
Citation: Song, Y., Tang, S., Zheng, Y.-T., Chua, T.-S., Zhang, Y., Lin, S. (2012). Exploring probabilistic localized video representation for human action recognition. Multimedia Tools and Applications 58 (3) : 663-685. ScholarBank@NUS Repository.
Abstract: In recent years, the bag-of-words (BoW) video representations have achieved promising results in human action recognition in videos. By vector quantizing local spatial temporal (ST) features, the BoW video representation brings in simplicity and efficiency, but limitations too. First, the discretization of feature space in BoW inevitably results in ambiguity and information loss in video representation. Second, there exists no universal codebook for BoW representation. The codebook needs to be re-built when video corpus is changed. To tackle these issues, this paper explores a localized, continuous and probabilistic video representation. Specifically, the proposed representation encodes the visual and motion information of an ensemble of local ST features of a video into a distribution estimated by a generative probabilistic model. Furthermore, the probabilistic video representation naturally gives rise to an information-theoretic distance metric of videos. This makes the representation readily applicable to most discriminative classifiers, such as the nearest neighbor schemes and the kernel based classifiers. Experiments on two datasets, KTH and UCF sports, show that the proposed approach could deliver promising results. © 2011 Springer Science+Business Media, LLC.
Source Title: Multimedia Tools and Applications
ISSN: 15737721
DOI: 10.1007/s11042-011-0748-7
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.


checked on Mar 8, 2021


checked on Mar 8, 2021

Page view(s)

checked on Mar 1, 2021

Google ScholarTM



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.