File Download
  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Action-Gons: Action recognition with a discriminative dictionary of structured elements with varying granularity

TitleAction-Gons: Action recognition with a discriminative dictionary of structured elements with varying granularity
Authors
Issue Date2015
PublisherSpringer Verlag. The Journal's web site is located at http://springerlink.com/content/105633/
Citation
The 12th Asian Conference on Computer Vision (ACCV 2014), Singapore, 1-5 November 2014. In Lecture Notes in Computer Science, 2015, v. 9007, p. 259-274 How to Cite?
AbstractThis paper presents “Action-Gons”, a middle level representation for action recognition in videos. Actions in videos exhibit a reasonable level of regularity seen in human behavior, as well as a large degree of variation. One key property of action, compared with image scene, might be the amount of interaction among body parts, although scenes also observe structured patterns in 2D images. Here, we study highorder statistics of the interaction among regions of interest in actions and propose a mid-level representation for action recognition, inspired by the Julesz school of n-gon statistics. We propose a systematic learning process to build an over-complete dictionary of “Action-Gons”. We first extract motion clusters, named as action units, then sequentially learn a pool of action-gons with different granularities modeling different degree of interactions among action units. We validate the discriminative power of our learned action-gons on three challenging video datasets and show evident advantages over the existing methods. © Springer International Publishing Switzerland 2015.
DescriptionLNCS v. 9007 entitled: Computer Vision -- ACCV 2014: 12th Asian Conference on Computer ..., Part 5
Persistent Identifierhttp://hdl.handle.net/10722/214076
ISBN
ISSN
2023 SCImago Journal Rankings: 0.606
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorWang, Y-
dc.contributor.authorWang, B-
dc.contributor.authorYu, Y-
dc.contributor.authorDai, Q-
dc.contributor.authorTu, Z-
dc.date.accessioned2015-08-20T01:42:47Z-
dc.date.available2015-08-20T01:42:47Z-
dc.date.issued2015-
dc.identifier.citationThe 12th Asian Conference on Computer Vision (ACCV 2014), Singapore, 1-5 November 2014. In Lecture Notes in Computer Science, 2015, v. 9007, p. 259-274-
dc.identifier.isbn978-3-319-16813-5-
dc.identifier.issn0302-9743-
dc.identifier.urihttp://hdl.handle.net/10722/214076-
dc.descriptionLNCS v. 9007 entitled: Computer Vision -- ACCV 2014: 12th Asian Conference on Computer ..., Part 5-
dc.description.abstractThis paper presents “Action-Gons”, a middle level representation for action recognition in videos. Actions in videos exhibit a reasonable level of regularity seen in human behavior, as well as a large degree of variation. One key property of action, compared with image scene, might be the amount of interaction among body parts, although scenes also observe structured patterns in 2D images. Here, we study highorder statistics of the interaction among regions of interest in actions and propose a mid-level representation for action recognition, inspired by the Julesz school of n-gon statistics. We propose a systematic learning process to build an over-complete dictionary of “Action-Gons”. We first extract motion clusters, named as action units, then sequentially learn a pool of action-gons with different granularities modeling different degree of interactions among action units. We validate the discriminative power of our learned action-gons on three challenging video datasets and show evident advantages over the existing methods. © Springer International Publishing Switzerland 2015.-
dc.languageeng-
dc.publisherSpringer Verlag. The Journal's web site is located at http://springerlink.com/content/105633/-
dc.relation.ispartofLecture Notes in Computer Science-
dc.rightsThe final publication is available at Springer via http://dx.doi.org/10.1007/978-3-319-16814-2_17-
dc.titleAction-Gons: Action recognition with a discriminative dictionary of structured elements with varying granularity-
dc.typeConference_Paper-
dc.identifier.emailYu, Y: yzyu@cs.hku.hk-
dc.identifier.authorityYu, Y=rp01415-
dc.description.naturepostprint-
dc.identifier.doi10.1007/978-3-319-16814-2_17-
dc.identifier.scopuseid_2-s2.0-84929617785-
dc.identifier.hkuros249496-
dc.identifier.volume9007-
dc.identifier.spage259-
dc.identifier.epage274-
dc.identifier.isiWOS:000362446300017-
dc.publisher.placeGermany-
dc.customcontrol.immutablesml 150820 ; 160419-
dc.identifier.issnl0302-9743-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats