Show simple item record

dc.contributor.authorHeilbron, Fabian Caba
dc.contributor.authorThabet, Ali Kassem
dc.contributor.authorNiebles, Juan Carlos
dc.contributor.authorGhanem, Bernard
dc.date.accessioned2015-06-02T14:22:39Z
dc.date.available2015-06-02T14:22:39Z
dc.date.issued2015-04-17
dc.identifier.doi10.1007/978-3-319-16817-3_38
dc.identifier.urihttp://hdl.handle.net/10754/556167
dc.description.abstractThis paper describes a framework for recognizing human actions in videos by incorporating a new set of visual cues that represent the context of the action. We develop a weak foreground-background segmentation approach in order to robustly extract not only foreground features that are focused on the actors, but also global camera motion and contextual scene information. Using dense point trajectories, our approach separates and describes the foreground motion from the background, represents the appearance of the extracted static background, and encodes the global camera motion that interestingly is shown to be discriminative for certain action classes. Our experiments on four challenging benchmarks (HMDB51, Hollywood2, Olympic Sports, and UCF50) show that our contextual features enable a significant performance improvement over state-of-the-art algorithms.
dc.publisherSpringer Nature
dc.relation.urlhttp://link.springer.com/chapter/10.1007%2F978-3-319-16817-3_38
dc.relation.urlhttp://vcc.kaust.edu.sa/Documents/B.%20Ghanem/papers/action_recognition_accv2014.pdf
dc.rightsThe final publication is available at Springer via http://dx.doi.org/10.1007/978-3-319-16817-3_38
dc.subjectAction Recognition
dc.titleCamera Motion and Surrounding Scene Appearance as Context for Action Recognition
dc.typeConference Paper
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
dc.contributor.departmentElectrical Engineering Program
dc.contributor.departmentOffice of Sponsored Research
dc.identifier.journalLecture Notes in Computer Science
dc.conference.dateNov 1-5, 2014
dc.conference.nameThe 12th Asian Conference on Computer Vision (ACCV 2014)
dc.conference.locationSingapore
dc.eprint.versionPost-print
dc.contributor.institutionUniversidad del Norte, Barranquilla, Colombia
kaust.personHeilbron, Fabian Caba
kaust.personThabet, Ali Kassem
kaust.personGhanem, Bernard
refterms.dateFOA2016-04-17T00:00:00Z


Files in this item

Thumbnail
Name:
action_recognition_accv2014.pdf
Size:
11.07Mb
Format:
PDF
Description:
Accepted Manuscript

This item appears in the following Collection(s)

Show simple item record