Hung-Ting Su, Yulei Niu, Xudong Lin 0003, Winston H. Hsu, Shih-Fu Chang. Language Models are Causal Knowledge Extractors for Zero-shot Video Question Answering. In IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023 - Workshops, Vancouver, BC, Canada, June 17-24, 2023. pages 4951-4960, IEEE, 2023. [doi]
@inproceedings{SuNLHC23,
title = {Language Models are Causal Knowledge Extractors for Zero-shot Video Question Answering},
author = {Hung-Ting Su and Yulei Niu and Xudong Lin 0003 and Winston H. Hsu and Shih-Fu Chang},
year = {2023},
doi = {10.1109/CVPRW59228.2023.00523},
url = {https://doi.org/10.1109/CVPRW59228.2023.00523},
researchr = {https://researchr.org/publication/SuNLHC23},
cites = {0},
citedby = {0},
pages = {4951-4960},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023 - Workshops, Vancouver, BC, Canada, June 17-24, 2023},
publisher = {IEEE},
isbn = {979-8-3503-0249-3},
}