"Sports video captioning by attentive motion representation based hierarchical recurrent neural networks", in MMSports' 18
We provide the dataset of Sports Video Captioning Dataset-Volleyball (Due to the confidental limit, the code and dataset currently are not available).
If you use this dataset for your research, please cite:
Sports video captioning by attentive motion representation based hierarchical recurrent neural networks, https://dl.acm.org/citation.cfm?id=3265851, Mengshi Qi, Yunhong Wang, Annan Li, and Jiebo Luo; 1st International Workshop on Multimedia Content Analysis in Sports (MMSports'18).
Sports Video Captioning via Attentive Motion Representation and Group Relationship Modeling, https://ieeexplore.ieee.org/abstract/document/8733019, Mengshi Qi, Yunhong Wang, Annan Li, and Jiebo Luo; IEEE Transactions on Circuits and Systems fo Video Technology (TCSVT), 2019.
The demo of sports video captioning can be found in:
https://www.youtube.com/watch?v=AUHGMF-kvDc.