Recognizing human actions using key poses

Simple item page
dc.citation.epage1730en_US
dc.citation.spage1727en_US
dc.contributor.authorBaysal, Sermetcanen_US
dc.contributor.authorKurt, Mehmet Canen_US
dc.contributor.authorDuygulu, Pınaren_US
dc.coverage.spatialIstanbul, Turkeyen_US
dc.date.accessioned2016-02-08T12:22:41Z
dc.date.available2016-02-08T12:22:41Z
dc.date.issued2010en_US
dc.departmentDepartment of Computer Engineeringen_US
dc.descriptionDate of Conference: 23-26 Aug. 2010en_US
dc.description.abstractIn this paper, we explore the idea of using only pose, without utilizing any temporal information, for human action recognition. In contrast to the other studies using complex action representations, we propose a simple method, which relies on extracting "key poses" from action sequences. Our contribution is two-fold. Firstly, representing the pose in a frame as a collection of line-pairs, we propose a matching scheme between two frames to compute their similarity. Secondly, to extract "key poses" for each action, we present an algorithm, which selects the most representative and discriminative poses from a set of candidates. Our experimental results on KTH and Weizmann datasets have shown that pose information by itself is quite effective in grasping the nature of an action and sufficient to distinguish one from others. © 2010 IEEE.en_US
dc.description.provenanceMade available in DSpace on 2016-02-08T12:22:41Z (GMT). No. of bitstreams: 1 bilkent-research-paper.pdf: 70227 bytes, checksum: 26e812c6f5156f83f0e77b261a471b5a (MD5) Previous issue date: 2010en
dc.identifier.doi10.1109/ICPR.2010.427en_US
dc.identifier.issn1051-4651
dc.identifier.urihttp://hdl.handle.net/11693/28516
dc.language.isoEnglishen_US
dc.publisherIEEEen_US
dc.relation.isversionofhttp://dx.doi.org/10.1109/ICPR.2010.427en_US
dc.source.title2010 20th International Conference on Pattern Recognitionen_US
dc.subjectA-framesen_US
dc.subjectAction sequencesen_US
dc.subjectComplex actionsen_US
dc.subjectData setsen_US
dc.subjectHuman actionsen_US
dc.subjectHuman-action recognitionen_US
dc.subjectKey poseen_US
dc.subjectMatching schemeen_US
dc.subjectPose informationen_US
dc.subjectSIMPLE methoden_US
dc.subjectTemporal informationen_US
dc.subjectGesture recognitionen_US
dc.titleRecognizing human actions using key posesen_US
dc.typeConference Paperen_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Recognizing human actions using key poses.pdf
Size:
718.89 KB
Format:
Adobe Portable Document Format
Description:
Full printable version
Download

Collections

Department of Computer Engineering