Show simple item record

dc.contributor.authorHatun, Kardelenen_US
dc.contributor.authorDuygulu, Pınaren_US
dc.coverage.spatialTampa, FL, USA
dc.date.accessioned2016-02-08T11:35:14Z
dc.date.available2016-02-08T11:35:14Z
dc.date.issued2008-12en_US
dc.identifier.urihttp://hdl.handle.net/11693/26769
dc.descriptionDate of Conference: 8-11 Dec. 2008
dc.descriptionConference name: 19th International Conference on Pattern Recognition, 2008
dc.description.abstractWe propose a method for recognizing human actions in videos. Inspired from the recent bag-of-words approaches, we represent actions as documents consisting of words, where a word refers to the pose in a frame. Histogram of oriented gradients (HOG) features are used to describe poses, which are then vector quantized to obtain pose-words. As an alternative to bagof- words approaches, that only represent actions as a collection of words by discarding the temporal characteristics of actions, we represent videos as ordered sequence of pose-words, that is as pose sentences. Then, string matching techniques are exploited to find the similarity of two action sequences. In the experiments, performed on data set of Blank et al., 92% performance is obtained. © 2008 IEEE.en_US
dc.language.isoEnglishen_US
dc.source.title19th International Conference on Pattern Recognition, 2008en_US
dc.relation.isversionofhttps://doi.org/10.1109/ICPR.2008.4761702
dc.subjectA-framesen_US
dc.subjectAction recognitionen_US
dc.subjectAction sequencesen_US
dc.subjectBag of wordsen_US
dc.subjectData setsen_US
dc.subjectHuman actionsen_US
dc.subjectString matchingen_US
dc.subjectTemporal characteristicsen_US
dc.subjectImage recognitionen_US
dc.titlePose sentences: a new representation for action recognition using sequence of pose wordsen_US
dc.typeConference Paperen_US
dc.departmentDepartment of Computer Engineering
dc.identifier.doi10.1109/ICPR.2008.4761702
dc.publisherIEEE


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record