Agent-Environment Network for Temporal Action Proposal Generation
This addresses the problem of localizing human actions in videos for applications like video analysis, offering a novel approach but likely incremental as it builds on existing methods with attention mechanisms.
The paper tackles temporal action proposal generation in untrimmed videos by proposing a contextual Agent-Environment Network that models agent-environment interactions, achieving state-of-the-art performance on THUMOS-14 and ActivityNet-1.3 datasets with robust results across different backbone networks.
Temporal action proposal generation is an essential and challenging task that aims at localizing temporal intervals containing human actions in untrimmed videos. Most of existing approaches are unable to follow the human cognitive process of understanding the video context due to lack of attention mechanism to express the concept of an action or an agent who performs the action or the interaction between the agent and the environment. Based on the action definition that a human, known as an agent, interacts with the environment and performs an action that affects the environment, we propose a contextual Agent-Environment Network. Our proposed contextual AEN involves (i) agent pathway, operating at a local level to tell about which humans/agents are acting and (ii) environment pathway operating at a global level to tell about how the agents interact with the environment. Comprehensive evaluations on 20-action THUMOS-14 and 200-action ActivityNet-1.3 datasets with different backbone networks, i.e C3D and SlowFast, show that our method robustly exhibits outperformance against state-of-the-art methods regardless of the employed backbone network.