Camera Motion and Surrounding Scene Appearance as Context for Action Recognition

Handle URI:
http://hdl.handle.net/10754/556167
Title:
Camera Motion and Surrounding Scene Appearance as Context for Action Recognition
Authors:
Heilbron, Fabian Caba; Thabet, Ali Kassem ( 0000-0001-7513-0748 ) ; Niebles, Juan Carlos; Ghanem, Bernard ( 0000-0002-5534-587X )
Abstract:
This 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.
KAUST Department:
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
Publisher:
Springer Science + Business Media
Journal:
Lecture Notes in Computer Science
Conference/Event name:
The 12th Asian Conference on Computer Vision (ACCV 2014)
Issue Date:
17-Apr-2015
DOI:
10.1007/978-3-319-16817-3_38
Type:
Conference Paper
Additional Links:
http://link.springer.com/chapter/10.1007%2F978-3-319-16817-3_38; http://vcc.kaust.edu.sa/Documents/B.%20Ghanem/papers/action_recognition_accv2014.pdf
Appears in Collections:
Conference Papers; Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division

Full metadata record

DC FieldValue Language
dc.contributor.authorHeilbron, Fabian Cabaen
dc.contributor.authorThabet, Ali Kassemen
dc.contributor.authorNiebles, Juan Carlosen
dc.contributor.authorGhanem, Bernarden
dc.date.accessioned2015-06-02T14:22:39Zen
dc.date.available2015-06-02T14:22:39Zen
dc.date.issued2015-04-17en
dc.identifier.doi10.1007/978-3-319-16817-3_38en
dc.identifier.urihttp://hdl.handle.net/10754/556167en
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.en
dc.publisherSpringer Science + Business Mediaen
dc.relation.urlhttp://link.springer.com/chapter/10.1007%2F978-3-319-16817-3_38en
dc.relation.urlhttp://vcc.kaust.edu.sa/Documents/B.%20Ghanem/papers/action_recognition_accv2014.pdfen
dc.rightsThe final publication is available at Springer via http://dx.doi.org/10.1007/978-3-319-16817-3_38en
dc.subjectAction Recognitionen
dc.titleCamera Motion and Surrounding Scene Appearance as Context for Action Recognitionen
dc.typeConference Paperen
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Divisionen
dc.identifier.journalLecture Notes in Computer Scienceen
dc.conference.dateNov 1-5, 2014en
dc.conference.nameThe 12th Asian Conference on Computer Vision (ACCV 2014)en
dc.conference.locationSingaporeen
dc.eprint.versionPost-printen
dc.contributor.institutionUniversidad del Norte, Barranquilla, Colombiaen
kaust.authorHeilbron, Fabian Cabaen
kaust.authorThabet, Ali Kassemen
kaust.authorGhanem, Bernarden
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.