VideoBadminton: A Video Dataset for Badminton Action Recognition

arXiv:2403.12385v1 Announce Type: new
Abstract: In the dynamic and evolving field of computer vision, action recognition has become a key focus, especially with the advent of sophisticated methodologies like Convolutional Neural Networks (CNNs), Convolutional 3D, Transformer, and spatial-temporal feature fusion. These technologies have shown promising results on well-established benchmarks but face unique challenges in real-world applications, particularly in sports analysis, where the precise decomposition of activities and the distinction of subtly different actions are crucial. Existing datasets like UCF101, HMDB51, …

abstract action recognition arxiv become benchmarks cnns computer computer vision convolutional neural networks cs.cv dataset dynamic face feature focus fusion key networks neural networks recognition results spatial technologies temporal transformer type video vision