Please use this identifier to cite or link to this item: https://doi.org/10.1109/ICME.2010.5582550
DC FieldValue
dc.titleA distribution based video representation for human action recognition
dc.contributor.authorSong, Y.
dc.contributor.authorTang, S.
dc.contributor.authorZheng, Y.-T.
dc.contributor.authorChua, T.-S.
dc.contributor.authorZhang, Y.
dc.contributor.authorLin, S.
dc.date.accessioned2013-07-04T07:59:02Z
dc.date.available2013-07-04T07:59:02Z
dc.date.issued2010
dc.identifier.citationSong, Y., Tang, S., Zheng, Y.-T., Chua, T.-S., Zhang, Y., Lin, S. (2010). A distribution based video representation for human action recognition. 2010 IEEE International Conference on Multimedia and Expo, ICME 2010 : 772-777. ScholarBank@NUS Repository. https://doi.org/10.1109/ICME.2010.5582550
dc.identifier.isbn9781424474912
dc.identifier.urihttp://scholarbank.nus.edu.sg/handle/10635/40206
dc.description.abstractMost current research on human action recognition in videos uses the bag-of-words (BoW) representations based on vector quantization on local spatial temporal features, due to the simplicity and good performance of such representations. In contrast to the BoW schemes, 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 spatial temporal (ST) features of a video into a distribution estimated by a generative probabilistic model such as the Gaussian Mixture Model. Furthermore, this probabilistic video representation naturally gives rise to an information-theoretic distance metric of videos. This makes the representation readily applicable as input to most discriminative classifiers, such as the nearest neighbor schemes and the kernel methods. The experiments on two datasets, KTH and UCF sports, show that the proposed approach could deliver promising results. © 2010 IEEE.
dc.description.urihttp://libproxy1.nus.edu.sg/login?url=http://dx.doi.org/10.1109/ICME.2010.5582550
dc.sourceScopus
dc.subjectHuman action recognition
dc.subjectInformation-theoretic video matching
dc.subjectProbabilistic video representation
dc.typeConference Paper
dc.contributor.departmentCOMPUTER SCIENCE
dc.description.doi10.1109/ICME.2010.5582550
dc.description.sourcetitle2010 IEEE International Conference on Multimedia and Expo, ICME 2010
dc.description.page772-777
dc.identifier.isiut000287977700137
Appears in Collections:Staff Publications

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

SCOPUSTM   
Citations

3
checked on Oct 18, 2019

WEB OF SCIENCETM
Citations

2
checked on Oct 11, 2019

Page view(s)

82
checked on Oct 14, 2019

Google ScholarTM

Check

Altmetric


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