Event Detection in Table Tennis Videos using 2D Keypoints

Key points

• To overcome this limitation, we propose EventNet, a two-stage pipeline to detect key events: (1) 2d keypoints are extracted of the upper-body poses for both players, table corners and ball center.1
• (2) The temporal sequences of these frame-based representations are processed by a transformer encoder that predicts two time-to-event values for each frame, indicating how close the current frame is to the next and previous ball-racket contact.1
• Furthermore, we introduce viewpoint augmentation via 3D reprojection and frame-rate augmentation to improve robustness and generalization.1
• Overall, our work demonstrates that 2d keypoint-based temporal modeling with our EventNet architecture is a promising and practical approach for automatic event detection in table tennis videos.1

Sources (1)

• [1]Event Detection in Table Tennis Videos using 2D Keypoints
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 6, 12:55 PM

  This paper addresses the challenge of automatic, frame-accurate event detection in table tennis videos.

  To overcome this limitation, we propose EventNet, a two-stage pipeline to detect key events: (1) 2d keypoints are extracted of the upper-body poses for both players, table corners and ball center.

Extractive summary: sentences quoted from the sources.