Ali Furkan Biten, Ron Litman, Yusheng Xie, Srikar Appalaraju, R. Manmatha. LaTr: Layout-Aware Transformer for Scene-Text VQA. In IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, New Orleans, LA, USA, June 18-24, 2022. pages 16527-16537, IEEE, 2022. [doi]
@inproceedings{BitenLXAM22,
title = {LaTr: Layout-Aware Transformer for Scene-Text VQA},
author = {Ali Furkan Biten and Ron Litman and Yusheng Xie and Srikar Appalaraju and R. Manmatha},
year = {2022},
doi = {10.1109/CVPR52688.2022.01605},
url = {https://doi.org/10.1109/CVPR52688.2022.01605},
researchr = {https://researchr.org/publication/BitenLXAM22},
cites = {0},
citedby = {0},
pages = {16527-16537},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, New Orleans, LA, USA, June 18-24, 2022},
publisher = {IEEE},
isbn = {978-1-6654-6946-3},
}