Fine-Grained Action Recognition on a Novel Basketball Dataset

Abstract

Currently most works on action recognition focus on the coarsely-grained actions, while the fine-grained action recognition is seldom addressed which is of vital importance in many applications such as video retrieval. To tackle this issue, in this paper, we release a challenging dataset by annotating the fine-grained actions in basketball game videos. A benchmark evaluation of the state-of-the-art approaches for action recognition is also provided on our dataset. Furthermore, we propose an approach by integrating the NTS-Net into two-stream network so as to locate the most informative regions and extract more discriminative features for fine-grained action recognition. Our experiments show that the proposed approach significantly outperforms the existing approaches.