Deconstruct Complexity (DeComplex): A Novel Perspective on Tackling Dense Action Detection

원문 초록

Dense action detection involves detecting multiple co-occurring actions in an untrimmed video while action classes are often ambiguous and represent overlapping concepts. To address this challenge task, we introduce a novel perspective inspired by how humans tackle complex tasks by breaking them into manageable sub-tasks. Instead of relying on a single network to address the entire problem, as in current approaches, we propose decomposing the problem into detecting key concepts present in action classes, specifically, detecting dense static concepts and detecting dense dynamic concepts, and assigning them to distinct, specialized networks. Furthermore, simultaneous actions in a video often exhibit interrelationships, and exploiting these relationships can improve performance. However, we argue that current networks fail to effectively learn these relationships due to their reliance on binary cross-entropy optimization, which treats each class independently. To address this limitation, we propose providing explicit supervision on co-occurring concepts during network optimization through a novel language-guided contrastive learning loss. Our extensive experiments demonstrate the superiority of our approach over state-of-the-art methods, achieving substantial relative improvements of 23.4% and 2.5% mAP on the challenging benchmark datasets, Charades and MultiTHUMOS.