@inproceedings{mmtfmultimodaltemporalfusionfor,
  title = {MMTF: Multi-Modal Temporal Fusion for Commonsense Video Question Answering},
  author = {Mobeen Ahmad and Geonwoo Park and Dongchan Park and Sanguk Park},
  year = {2023},
  booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops, 2023 2023 10},
  url = {https://openaccess.thecvf.com/content/ICCV2023W/VLAR/html/Ahmad_MMTF_Multi-Modal_Temporal_Fusion_for_Commonsense_Video_Question_Answering_ICCVW_2023_paper.html},
}