P2ANet: A Large-Scale Benchmark for Dense Action Detection from Table Tennis Match Broadcasting Videos
ACM Trans. Multim. Comput. Commun. Appl.(2024)
摘要
While deep learning has been widely used for video analytics, such as video classification and action detection, dense action detection with fast-moving subjects from sports videos is still challenging. In this work, we release yet another sports video benchmark P(2)ANet for Ping Pong-Action detection, which consists of 2,721 video clips collected from the broadcasting videos of professional table tennis matches in World Table Tennis Championships and Olympiads. We work with a crew of table tennis professionals and referees on a specially designed annotation toolbox to obtain fine-grained action labels (in 14 classes) for every ping-pong action that appeared in the dataset, and formulate two sets of action detection problems-action localization and action recognition. We evaluate a number of commonly seen action recognition (e.g., TSM, TSN, Video SwinTransformer, and Slowfast) and action localization models (e.g., BSN, BSN++, BMN, TCANet), using P(2)ANet for both problems, under various settings. These models can only achieve 48% area under the AR-AN curve for localization and 82% top-one accuracy for recognition since the ping-pong actions are dense with fast-moving subjects but broadcasting videos are with only 25 FPS. The results confirm that P(2)ANet is still a challenging task and can be used as a special benchmark for dense action detection from videos. We invite readers to examine our dataset by visiting the following link: https://github.com/Fred1991/P2ANET.
更多查看译文
关键词
Datasets,annotation toolbox,video analysis,action recognition and localization,table tennis
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要