Wenliang Dai, Lu Hou, Lifeng Shang, Xin Jiang, Qun Liu, Pascale Fung. Enabling Multimodal Generation on CLIP via Vision-Language Knowledge Distillation. In Smaranda Muresan, Preslav Nakov, Aline Villavicencio, editors, Findings of the Association for Computational Linguistics: ACL 2022, Dublin, Ireland, May 22-27, 2022. pages 2383-2395, Association for Computational Linguistics, 2022. [doi]
@inproceedings{DaiHSJLF22,
title = {Enabling Multimodal Generation on CLIP via Vision-Language Knowledge Distillation},
author = {Wenliang Dai and Lu Hou and Lifeng Shang and Xin Jiang and Qun Liu and Pascale Fung},
year = {2022},
url = {https://aclanthology.org/2022.findings-acl.187},
researchr = {https://researchr.org/publication/DaiHSJLF22},
cites = {0},
citedby = {0},
pages = {2383-2395},
booktitle = {Findings of the Association for Computational Linguistics: ACL 2022, Dublin, Ireland, May 22-27, 2022},
editor = {Smaranda Muresan and Preslav Nakov and Aline Villavicencio},
publisher = {Association for Computational Linguistics},
isbn = {978-1-955917-25-4},
}