SCC: Semantic Context Cascade for Efficient Action Detection

Handle URI:
http://hdl.handle.net/10754/626983
Title:
SCC: Semantic Context Cascade for Efficient Action Detection
Authors:
Heilbron, Fabian Caba; Barrios, Wayner; Escorcia, Victor; Ghanem, Bernard ( 0000-0002-5534-587X )
Abstract:
Despite the recent advances in large-scale video analysis, action detection remains as one of the most challenging unsolved problems in computer vision. This snag is in part due to the large volume of data that needs to be analyzed to detect actions in videos. Existing approaches have mitigated the computational cost, but still, these methods lack rich high-level semantics that helps them to localize the actions quickly. In this paper, we introduce a Semantic Cascade Context (SCC) model that aims to detect action in long video sequences. By embracing semantic priors associated with human activities, SCC produces high-quality class-specific action proposals and prune unrelated activities in a cascade fashion. Experimental results in ActivityNet unveils that SCC achieves state-of-the-art performance for action detection while operating at real time.
KAUST Department:
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division; Electrical Engineering Program; Visual Computing Center (VCC)
Citation:
Heilbron FC, Barrios W, Escorcia V, Ghanem B (2017) SCC: Semantic Context Cascade for Efficient Action Detection. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Available: http://dx.doi.org/10.1109/CVPR.2017.338.
Publisher:
IEEE
Journal:
2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Conference/Event name:
30th IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Issue Date:
9-Nov-2017
DOI:
10.1109/CVPR.2017.338
Type:
Conference Paper
Sponsors:
Research in this publication was supported by the King Abdullah University of Science and Technology (KAUST) Office of Sponsored Research.
Additional Links:
http://ieeexplore.ieee.org/document/8099821/
Appears in Collections:
Conference Papers; Electrical Engineering Program; Visual Computing Center (VCC); Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division

Full metadata record

DC FieldValue Language
dc.contributor.authorHeilbron, Fabian Cabaen
dc.contributor.authorBarrios, Wayneren
dc.contributor.authorEscorcia, Victoren
dc.contributor.authorGhanem, Bernarden
dc.date.accessioned2018-02-01T07:25:01Z-
dc.date.available2018-02-01T07:25:01Z-
dc.date.issued2017-11-09en
dc.identifier.citationHeilbron FC, Barrios W, Escorcia V, Ghanem B (2017) SCC: Semantic Context Cascade for Efficient Action Detection. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Available: http://dx.doi.org/10.1109/CVPR.2017.338.en
dc.identifier.doi10.1109/CVPR.2017.338en
dc.identifier.urihttp://hdl.handle.net/10754/626983-
dc.description.abstractDespite the recent advances in large-scale video analysis, action detection remains as one of the most challenging unsolved problems in computer vision. This snag is in part due to the large volume of data that needs to be analyzed to detect actions in videos. Existing approaches have mitigated the computational cost, but still, these methods lack rich high-level semantics that helps them to localize the actions quickly. In this paper, we introduce a Semantic Cascade Context (SCC) model that aims to detect action in long video sequences. By embracing semantic priors associated with human activities, SCC produces high-quality class-specific action proposals and prune unrelated activities in a cascade fashion. Experimental results in ActivityNet unveils that SCC achieves state-of-the-art performance for action detection while operating at real time.en
dc.description.sponsorshipResearch in this publication was supported by the King Abdullah University of Science and Technology (KAUST) Office of Sponsored Research.en
dc.publisherIEEEen
dc.relation.urlhttp://ieeexplore.ieee.org/document/8099821/en
dc.titleSCC: Semantic Context Cascade for Efficient Action Detectionen
dc.typeConference Paperen
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Divisionen
dc.contributor.departmentElectrical Engineering Programen
dc.contributor.departmentVisual Computing Center (VCC)en
dc.identifier.journal2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)en
dc.conference.dateJUL 21-26, 2016en
dc.conference.name30th IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)en
dc.conference.locationHonolulu, HIen
kaust.authorHeilbron, Fabian Cabaen
kaust.authorBarrios, Wayneren
kaust.authorEscorcia, Victoren
kaust.authorGhanem, Bernarden
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.