Prompt-guided Representation Disentanglement for Action Recognition
This work addresses a domain-specific problem in video understanding for multi-action scenarios, offering an incremental improvement over existing methods.
The paper tackles the challenge of modeling interactions between different objects in multi-action video scenes by proposing ProDA, a framework that disentangles specified actions using prompt-guided representations, achieving state-of-the-art results in video action recognition.
Action recognition is a fundamental task in video understanding. Existing methods typically extract unified features to process all actions in one video, which makes it challenging to model the interactions between different objects in multi-action scenarios. To alleviate this issue, we explore disentangling any specified actions from complex scenes as an effective solution. In this paper, we propose Prompt-guided Disentangled Representation for Action Recognition (ProDA), a novel framework that disentangles any specified actions from a multi-action scene. ProDA leverages Spatio-temporal Scene Graphs (SSGs) and introduces Dynamic Prompt Module (DPM) to guide a Graph Parsing Neural Network (GPNN) in generating action-specific representations. Furthermore, we design a video-adapted GPNN that aggregates information using dynamic weights. Experiments in video action recognition demonstrate the effectiveness of our approach when compared with the state-of-the-art methods. Our code can be found in https://github.com/iamsnaping/ProDA.git