1. Structured Multimodal Attentions for TextVQA
- Author
-
Qi Wu, Chenyu Gao, Yuliang Liu, Peng Wang, Anton van den Hengel, Hui Li, and Qi Zhu
- Subjects
FOS: Computer and information sciences ,Vocabulary ,Computer science ,Computer Vision and Pattern Recognition (cs.CV) ,media_common.quotation_subject ,Computer Science - Computer Vision and Pattern Recognition ,computer.software_genre ,Discriminative model ,Artificial Intelligence ,Question answering ,Humans ,media_common ,Modality (human–computer interaction) ,business.industry ,Applied Mathematics ,Optical character recognition ,Computational Theory and Mathematics ,Graph (abstract data type) ,Neural Networks, Computer ,Computer Vision and Pattern Recognition ,Artificial intelligence ,business ,computer ,Algorithms ,Software ,Natural language ,Generative grammar ,Natural language processing - Abstract
In this paper, we propose an end-to-end structured multimodal attention (SMA) neural network to mainly solve the first two issues above. SMA first uses a structural graph representation to encode the object-object, object-text and text-text relationships appearing in the image, and then designs a multimodal graph attention network to reason over it. Finally, the outputs from the above modules are processed by a global-local attentional answering module to produce an answer splicing together tokens from both OCR and general vocabulary iteratively by following M4C. Our proposed model outperforms the SoTA models on TextVQA dataset and two tasks of ST-VQA dataset among all models except pre-training based TAP. Demonstrating strong reasoning ability, it also won first place in TextVQA Challenge 2020. We extensively test different OCR methods on several reasoning models and investigate the impact of gradually increased OCR performance on TextVQA benchmark. With better OCR results, different models share dramatic improvement over the VQA accuracy, but our model benefits most blessed by strong textual-visual reasoning ability. To grant our method an upper bound and make a fair testing base available for further works, we also provide human-annotated ground-truth OCR annotations for the TextVQA dataset, which were not given in the original release. The code and ground-truth OCR annotations for the TextVQA dataset are available at https://github.com/ChenyuGAO-CS/SMA, winner of TextVQA Challenge 2020, Accepted by IEEE Transactions on Pattern Analysis and Machine Intelligence
- Published
- 2022