Changsheng Xu, Zhenlong Xu, Yifan He, Shuigeng Zhou, Jihong Guan. Multi-Modal Learning with Text Merging for TEXTVQA. In IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2022, Virtual and Singapore, 23-27 May 2022. pages 1985-1989, IEEE, 2022. [doi]
@inproceedings{XuXHZG22,
title = {Multi-Modal Learning with Text Merging for TEXTVQA},
author = {Changsheng Xu and Zhenlong Xu and Yifan He and Shuigeng Zhou and Jihong Guan},
year = {2022},
doi = {10.1109/ICASSP43922.2022.9746969},
url = {https://doi.org/10.1109/ICASSP43922.2022.9746969},
researchr = {https://researchr.org/publication/XuXHZG22},
cites = {0},
citedby = {0},
pages = {1985-1989},
booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2022, Virtual and Singapore, 23-27 May 2022},
publisher = {IEEE},
isbn = {978-1-6654-0540-9},
}