@inproceedings{yang2021tap,
author = {Yang, Zhengyuan and Lu, Yijuan and Wang, Jianfeng and Yin, Xi and Florencio, Dinei and Wang, Lijuan and Zhang, Cha and Zhang, Lei and Luo, Jiebo},
title = {TAP: Text-Aware Pre-training for Text-VQA and Text-Caption},
booktitle = {CVPR 2021},
year = {2021},
month = {June},
abstract = {In this paper, we propose Text-Aware Pre-training (TAP) for Text-VQA and Text-Caption tasks. These two tasks aim at reading and understanding scene text in images for question answering and image caption generation, respectively. In contrast to the conventional vision-language pre-training that fails to capture scene text and its relationship with the visual and text modalities, TAP explicitly incorporates scene text (generated from OCR engines) in pre-training. With three pre-training tasks, including masked language modeling (MLM), image-text (contrastive) matching (ITM), and relative (spatial) position prediction (RPP), TAP effectively helps the model learn a better aligned representation among the three modalities: text word, visual object, and scene text. Due to this aligned representation learning, even pre-trained on the same downstream task dataset, TAP already boosts the absolute accuracy on the TextVQA dataset by +5.4%, compared with a non-TAP baseline. To further improve the performance, we build a large-scale dataset based on the Conceptual Caption dataset, named OCR-CC, which contains 1.4 million scene text-related image-text pairs. Pre-trained on this OCR-CC dataset, our approach outperforms the state of the art by large margins on multiple tasks, i.e., +8.3% accuracy on TextVQA, +8.6% accuracy on ST-VQA, and +10.2 CIDEr score on TextCaps.},
url = {http://approjects.co.za/?big=en-us/research/publication/tap-text-aware-pre-training-for-text-vqa-and-text-caption/},
}