Ligong Han, Jian Ren, Hsin-Ying Lee, Francesco Barbieri, Kyle Olszewski, Shervin Minaee, Dimitris N. Metaxas, Sergey Tulyakov. Show Me What and Tell Me How: Video Synthesis via Multimodal Conditioning. In IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, New Orleans, LA, USA, June 18-24, 2022. pages 3605-3615, IEEE, 2022. [doi]
@inproceedings{HanRLBOMMT22,
title = {Show Me What and Tell Me How: Video Synthesis via Multimodal Conditioning},
author = {Ligong Han and Jian Ren and Hsin-Ying Lee and Francesco Barbieri and Kyle Olszewski and Shervin Minaee and Dimitris N. Metaxas and Sergey Tulyakov},
year = {2022},
doi = {10.1109/CVPR52688.2022.00360},
url = {https://doi.org/10.1109/CVPR52688.2022.00360},
researchr = {https://researchr.org/publication/HanRLBOMMT22},
cites = {0},
citedby = {0},
pages = {3605-3615},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, New Orleans, LA, USA, June 18-24, 2022},
publisher = {IEEE},
isbn = {978-1-6654-6946-3},
}