计算机科学
灵活性(工程)
特征(语言学)
动作(物理)
人工智能
网(多面体)
质量(理念)
机器学习
几何学
数学
语言学
量子力学
统计
认识论
物理
哲学
作者
Shunli Wang,Dingkang Yang,Peng Zhai,Chixiao Chen,Lihua Zhang
标识
DOI:10.1145/3474085.3475438
摘要
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.
科研通智能强力驱动
Strongly Powered by AbleSci AI