Zhe Li, Laurence T. Yang, Xin Nie, Bocheng Ren, Xianjun Deng. Enhancing Sentence Representation with Visually-supervised Multimodal Pre-training. In Abdulmotaleb El-Saddik, Tao Mei, Rita Cucchiara, Marco Bertini 0001, Diana Patricia Tobon Vallejo, Pradeep K. Atrey, M. Shamim Hossain, editors, Proceedings of the 31st ACM International Conference on Multimedia, MM 2023, Ottawa, ON, Canada, 29 October 2023- 3 November 2023. pages 5686-5695, ACM, 2023. [doi]
@inproceedings{LiYNRD23,
title = {Enhancing Sentence Representation with Visually-supervised Multimodal Pre-training},
author = {Zhe Li and Laurence T. Yang and Xin Nie and Bocheng Ren and Xianjun Deng},
year = {2023},
doi = {10.1145/3581783.3612254},
url = {https://doi.org/10.1145/3581783.3612254},
researchr = {https://researchr.org/publication/LiYNRD23},
cites = {0},
citedby = {0},
pages = {5686-5695},
booktitle = {Proceedings of the 31st ACM International Conference on Multimedia, MM 2023, Ottawa, ON, Canada, 29 October 2023- 3 November 2023},
editor = {Abdulmotaleb El-Saddik and Tao Mei and Rita Cucchiara and Marco Bertini 0001 and Diana Patricia Tobon Vallejo and Pradeep K. Atrey and M. Shamim Hossain},
publisher = {ACM},
}