@article{learningfinegrainedvisualunderstanding,
  title = {Learning Fine-Grained Visual Understanding for Video Question Answering via Decoupling Spatial-Temporal Modeling},
  author = {Hsin-Ying Lee and Hung-Ting Su and Bing-Chen Tsai and Tsung-Han Wu and Jia-Fong Yeh and Winston H. Hsu},
  year = {2022},
  eprint = {2210.03941},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2210.03941v1},
}