Structured Multimodal Attentions for TextVQA

By Chenyu Gao, Qi Zhu, Peng Wang, Yuliang Liu, Anton van den Hengel, Qi Wu. 2020

69 citations recorded by the source corpus.

Text based Visual Question Answering (TextVQA) is a recently raised challenge requiring models to read text in images and answer natural language questions by jointly reasoning over the question, textual information and visual content. Introduction of this new modality - Optical Character Recognition (OCR) tokens ushers in demanding reasoning requirements. Most of the state-of-the-art (SoTA) VQA methods fail when answer these questions because of three reasons: (1) poor text reading ability; (2) lack of textual-visual reasoning capacity; and (3) choosing discriminative answering mechanism over generative couterpart (although this has been further addressed by M4C). 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.

Subfields: Multimodal Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Multimodal Learning

1. Zhe Gan
2. Lijuan Wang
3. Zicheng Liu
4. Jianfeng Wang
5. Xiaowei Hu
6. Linjie Li
7. Zhengyuan Yang
8. Ce Liu

Citations in the corpus

• TAP: Text-Aware Pre-training for Text-VQA and Text-Caption (2020, methodology): “First, “TAP” outperforms the state of the art [20, 25, 16, 36, 19] by large margins, and significantly improves the non-TAP baseline “M4C†.”
• GIT: A Generative Image-to-text Transformer for Vision and Language (2022, background): “[29] Chenyu Gao, Qi Zhu, Peng Wang, Hui Li, Yuliang Liu, Anton van den Hengel, and Qi Wu.”
• Finding the Evidence: Localization-aware Answer Prediction for Text Visual Question Answering (2020, methodology): “We compare our result on TextVQA to the newest SOTA method SMA (Gao et al., 2020) and other existing works like LoRRA (Singh et al., 2019), MSFT VTI (MSFTVTI, 2019), and M4C (Hu et al., 2020).”
• TextOCR: Towards large-scale end-to-end reasoning for arbitrary-shaped scene text (2021, background): “Multiple models have been introduced recently which ablate various components of M4C for better accuracy [22, 13, 16, 20].”
• LaTr: Layout-Aware Transformer for Scene-Text VQA (2021, background): “Instead of having separate graphs for each modality, SMA [15] introduces a single graph that encodes all modalities.”
• Universal Multimodal Representation for Language Understanding (2023, background): “The major focus is to bridge the gap between text and images through building visualsemantic embeddings [39], [40], [41], [42], [43].”