Difei Gao, Luowei Zhou, Lei Ji 0001, Linchao Zhu, Yi Yang, Mike Zheng Shou. MIST : Multi-modal Iterative Spatial-Temporal Transformer for Long-form Video Question Answering. In IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023, Vancouver, BC, Canada, June 17-24, 2023. pages 14773-14783, IEEE, 2023. [doi]
@inproceedings{GaoZ0ZYS23,
title = {MIST : Multi-modal Iterative Spatial-Temporal Transformer for Long-form Video Question Answering},
author = {Difei Gao and Luowei Zhou and Lei Ji 0001 and Linchao Zhu and Yi Yang and Mike Zheng Shou},
year = {2023},
doi = {10.1109/CVPR52729.2023.01419},
url = {https://doi.org/10.1109/CVPR52729.2023.01419},
researchr = {https://researchr.org/publication/GaoZ0ZYS23},
cites = {0},
citedby = {0},
pages = {14773-14783},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023, Vancouver, BC, Canada, June 17-24, 2023},
publisher = {IEEE},
isbn = {979-8-3503-0129-8},
}