Chengyang Fang, Jiangnan Li, Liang Li, Can Ma, Dayong Hu. Separate and Locate: Rethink the Text in Text-based Visual 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 4378-4388, ACM, 2023. [doi]
@inproceedings{FangLLMH23,
title = {Separate and Locate: Rethink the Text in Text-based Visual Question Answering},
author = {Chengyang Fang and Jiangnan Li and Liang Li and Can Ma and Dayong Hu},
year = {2023},
doi = {10.1145/3581783.3611753},
url = {https://doi.org/10.1145/3581783.3611753},
researchr = {https://researchr.org/publication/FangLLMH23},
cites = {0},
citedby = {0},
pages = {4378-4388},
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},
}