ViSTec: Video Modeling for Sports Technique Recognition and Tactical Analysis
This addresses the demand for automated tactical analysis in racket sports, reducing laborious manual annotation, though it appears incremental as it builds on existing video perception and action segmentation models.
The paper tackled the problem of recognizing stroke techniques and tactical strategies in racket sports videos, where existing methods fail due to occlusions and blurring, and demonstrated that their ViSTec model outperforms existing models significantly, with validation from experts in the Chinese national table tennis team.
The immense popularity of racket sports has fueled substantial demand in tactical analysis with broadcast videos. However, existing manual methods require laborious annotation, and recent attempts leveraging video perception models are limited to low-level annotations like ball trajectories, overlooking tactics that necessitate an understanding of stroke techniques. State-of-the-art action segmentation models also struggle with technique recognition due to frequent occlusions and motion-induced blurring in racket sports videos. To address these challenges, We propose ViSTec, a Video-based Sports Technique recognition model inspired by human cognition that synergizes sparse visual data with rich contextual insights. Our approach integrates a graph to explicitly model strategic knowledge in stroke sequences and enhance technique recognition with contextual inductive bias. A two-stage action perception model is jointly trained to align with the contextual knowledge in the graph. Experiments demonstrate that our method outperforms existing models by a significant margin. Case studies with experts from the Chinese national table tennis team validate our model's capacity to automate analysis for technical actions and tactical strategies. More details are available at: https://ViSTec2024.github.io/.