TSA-Net: Tube Self-Attention Network for Action Quality Assessment
This addresses the problem of accurately evaluating action quality in videos for applications like sports analysis, though it appears incremental by building on existing video networks.
The paper tackles action quality assessment in videos by proposing TSA-Net, which integrates a Tube Self-Attention Module to generate spatio-temporal context efficiently, achieving state-of-the-art performance on datasets like AQA-7 and MTL-AQA.
In recent years, assessing action quality from videos has attracted growing attention in computer vision community and human computer interaction. Most existing approaches usually tackle this problem by directly migrating the model from action recognition tasks, which ignores the intrinsic differences within the feature map such as foreground and background information. To address this issue, we propose a Tube Self-Attention Network (TSA-Net) for action quality assessment (AQA). Specifically, we introduce a single object tracker into AQA and propose the Tube Self-Attention Module (TSA), which can efficiently generate rich spatio-temporal contextual information by adopting sparse feature interactions. The TSA module is embedded in existing video networks to form TSA-Net. Overall, our TSA-Net is with the following merits: 1) High computational efficiency, 2) High flexibility, and 3) The state-of-the art performance. Extensive experiments are conducted on popular action quality assessment datasets including AQA-7 and MTL-AQA. Besides, a dataset named Fall Recognition in Figure Skating (FR-FS) is proposed to explore the basic action assessment in the figure skating scene.