@inproceedings{compositionalvideounderstandingwith, title = {Compositional Video Understanding with Spatiotemporal Structure-based Transformers}, author = {Hoyeoung Yun and Jinwoo Ahn and Minseo Kim and Eun-Sol Kim}, year = {2024}, booktitle = {CVPR 2024 1}, url = {http://openaccess.thecvf.com//content/CVPR2024/html/Yun_Compositional_Video_Understanding_with_Spatiotemporal_Structure-based_Transformers_CVPR_2024_paper.html}, }