@article{rethinkingmultimodalalignmentinvideo,
  title = {Rethinking Multi-Modal Alignment in Video Question Answering from Feature and Sample Perspectives},
  author = {Shaoning Xiao and Long Chen and Kaifeng Gao and Zhao Wang and Yi Yang and Zhimeng Zhang and Jun Xiao},
  year = {2022},
  eprint = {2204.11544},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2204.11544v2},
}