Yen-Chun Chen 0001, Linjie Li, Licheng Yu, Ahmed El Kholy, Faisal Ahmed 0001, Zhe Gan, Yu Cheng 0001, Jingjing Liu 0001. UNITER: UNiversal Image-TExt Representation Learning. In Andrea Vedaldi, Horst Bischof, Thomas Brox, Jan-Michael Frahm, editors, Computer Vision - ECCV 2020 - 16th European Conference, Glasgow, UK, August 23-28, 2020, Proceedings, Part XXX. Volume 12375 of Lecture Notes in Computer Science, pages 104-120, Springer, 2020. [doi]
@inproceedings{ChenLYK0G0020,
title = {UNITER: UNiversal Image-TExt Representation Learning},
author = {Yen-Chun Chen 0001 and Linjie Li and Licheng Yu and Ahmed El Kholy and Faisal Ahmed 0001 and Zhe Gan and Yu Cheng 0001 and Jingjing Liu 0001},
year = {2020},
doi = {10.1007/978-3-030-58577-8_7},
url = {https://doi.org/10.1007/978-3-030-58577-8_7},
researchr = {https://researchr.org/publication/ChenLYK0G0020},
cites = {0},
citedby = {0},
pages = {104-120},
booktitle = {Computer Vision - ECCV 2020 - 16th European Conference, Glasgow, UK, August 23-28, 2020, Proceedings, Part XXX},
editor = {Andrea Vedaldi and Horst Bischof and Thomas Brox and Jan-Michael Frahm},
volume = {12375},
series = {Lecture Notes in Computer Science},
publisher = {Springer},
isbn = {978-3-030-58577-8},
}