Jenhao Hsiao, Yikang Li, Chiuman Ho. Language-guided Multi-Modal Fusion for Video Action Recognition. In IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2021, Montreal, BC, Canada, October 11-17, 2021. pages 3151-3155, IEEE, 2021. [doi]
@inproceedings{HsiaoLH21,
title = {Language-guided Multi-Modal Fusion for Video Action Recognition},
author = {Jenhao Hsiao and Yikang Li and Chiuman Ho},
year = {2021},
doi = {10.1109/ICCVW54120.2021.00354},
url = {https://doi.org/10.1109/ICCVW54120.2021.00354},
researchr = {https://researchr.org/publication/HsiaoLH21},
cites = {0},
citedby = {0},
pages = {3151-3155},
booktitle = {IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2021, Montreal, BC, Canada, October 11-17, 2021},
publisher = {IEEE},
isbn = {978-1-6654-0191-3},
}