Haoru Chen, Tianjiao Wan, Zhimin Lin, Kele Xu, Jin Wang, Huaimin Wang. VTQAGen: BART-based Generative Model For Visual Text Question Answering. 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 9456-9461, ACM, 2023. [doi]
@inproceedings{ChenWLXWW23,
title = {VTQAGen: BART-based Generative Model For Visual Text Question Answering},
author = {Haoru Chen and Tianjiao Wan and Zhimin Lin and Kele Xu and Jin Wang and Huaimin Wang},
year = {2023},
doi = {10.1145/3581783.3612844},
url = {https://doi.org/10.1145/3581783.3612844},
researchr = {https://researchr.org/publication/ChenWLXWW23},
cites = {0},
citedby = {0},
pages = {9456-9461},
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},
}