Byoungjip Kim, Dasol Hwang, Sungjun Cho, Youngsoo Jang, Honglak Lee, Moontae Lee. Show, Think, and Tell: Thought-Augmented Fine-Tuning of Large Language Models for Video Captioning. In IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2024 - Workshops, Seattle, WA, USA, June 17-18, 2024. pages 1808-1817, IEEE, 2024. [doi]
@inproceedings{KimHCJLL22,
title = {Show, Think, and Tell: Thought-Augmented Fine-Tuning of Large Language Models for Video Captioning},
author = {Byoungjip Kim and Dasol Hwang and Sungjun Cho and Youngsoo Jang and Honglak Lee and Moontae Lee},
year = {2024},
doi = {10.1109/CVPRW63382.2024.00187},
url = {https://doi.org/10.1109/CVPRW63382.2024.00187},
researchr = {https://researchr.org/publication/KimHCJLL22},
cites = {0},
citedby = {0},
pages = {1808-1817},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2024 - Workshops, Seattle, WA, USA, June 17-18, 2024},
publisher = {IEEE},
isbn = {979-8-3503-6547-4},
}