Recognizing a Sequence of Events from Tennis Video Clips: Addressing Timestep Identification and Subtle Class Differences

Zhaoyu Liu, Jingyu Guo, Mo Wang, Ruicong Wang, Kan Jiang, Jin Song Dong

Abstract: Detecting temporally precise and fine-grained events from tennis videos is important in automatic video annotation. This paper addresses the challenges of recognizing a sequence of events from tennis video clips, focusing on accurate timestep identification and distinguishing subtle class differences. We propose a novel but simple end-to-end event detection network to accurately detect and identify the key events, which can be trained on a single GPU. We demonstrate that our model outperforms the existing baselines on our fine-grained tennis event dataset. The research contributes to the development of tennis video analytics and has broader implications in other sports domains.