@ARTICLE{10130340,
  author={Wu, Bofeng and Liu, Buyu and Huang, Peng and Bao, Jun and Xi, Peng and Yu, Jun},
  journal={IEEE Transactions on Circuits and Systems for Video Technology}, 
  title={Concept Parser With Multimodal Graph Learning for Video Captioning}, 
  year={2023},
  volume={33},
  number={9},
  pages={4484-4495},
  keywords={Transformers;Visualization;Feature extraction;Task analysis;Syntactics;Natural languages;Computer architecture;Video captioning;transformer;multi-modal learning;graph learning},
  doi={10.1109/TCSVT.2023.3277827}}