@article{videolanguagealignmentpretrainingvia,
  title = {Video-Language Alignment via Spatio-Temporal Graph Transformer},
  author = {Shi-Xue Zhang and Hongfa Wang and Xiaobin Zhu and Weibo Gu and Tianjin Zhang and Chun Yang and Wei Liu and Xu-Cheng Yin},
  year = {2024},
  eprint = {2407.11677},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2407.11677v2},
}