SCC: Semantic Context Cascade for Efficient Action Detection

Citations Over TimeTop 10% of 2017 papers

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.

Related Papers

• → Study of a Nonstationary Separation Method with Gas Centrifuge Cascade(2004)9 cited
• → Further optimization of Q-cascades(2015)10 cited
• → Structural issues in cascade-form adaptive IIR filters(2002)4 cited
• → Design of a 160% pitch passage for cascade experiments using optimization methods(2010)2 cited
• → One-pitch passage designed inversely with a single blade for cascade experiments(2010)1 cited