SCC: Semantic Context Cascade for Efficient Action Detection

Fabian Caba Heilbron, Wayner Barrios, Victor Escorcia, Bernard Ghanem

Research output: Chapter in Book/Report/Conference proceedingConference contribution

83 Scopus citations


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.
Original languageEnglish (US)
Title of host publication2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Number of pages10
ISBN (Print)9781538604571
StatePublished - Nov 9 2017


Dive into the research topics of 'SCC: Semantic Context Cascade for Efficient Action Detection'. Together they form a unique fingerprint.

Cite this