June 14, 2020
Many visual scenes contain text that carries crucial information, and it is thus essential to understand text in images for downstream reasoning tasks. For example, a deep water label on a warning sign warns people about the danger in the scene. Recent work has explored the TextVQA task that requires reading and understanding text in images to answer a question. However, existing approaches for TextVQA are mostly based on custom pairwise fusion mechanisms between a pair of two modalities and are restricted to a single prediction step by casting TextVQA as a classification task. In this work, we propose a novel model for the TextVQA task based on a multimodal transformer architecture accompanied by a rich representation for text in images. Our model naturally fuses different modalities homogeneously by embedding them into a common semantic space where self-attention is applied to model inter- and intra- modality context. Furthermore, it enables iterative answer decoding with a dynamic pointer network, allowing the model to form an answer through multi-step prediction instead of one-step classification. Our model outperforms existing approaches on three benchmark datasets for the TextVQA task by a large margin.
Publisher
Conference on Computer Vision and Pattern Recognition (CVPR)
June 17, 2019
Yunpeng Chen, Marcus Rohrbach, Zhicheng Yan, Shuicheng Yan, Jiashi Feng, Yannis Kalantidis
June 17, 2019
June 17, 2019
Zheng Shou, Xudong Lin, Yannis Kalantidis, Laura Sevilla-Lara, Marcus Rohrbach, Shih-Fu Chang, Zhicheng Yan
June 17, 2019
June 18, 2019
Erik Wijmans, Samyak Datta, Oleksandr Maksymets, Abhishek Das, Georgia Gkioxari, Stefan Lee, Irfan Essa, Devi Parikh, Dhruv Batra
June 18, 2019
July 28, 2019
Andrew Adams, Karima Ma, Luke Anderson, Riyadh Baghdadi, Tzu-Mao Li, Michaël Gharbi, Benoit Steiner, Steven Johnson, Kayvon Fatahalian, Frédo Durand, Jonathan Ragan-Kelley
July 28, 2019
Who We Are
Our Actions
Newsletter