# SceneGATE: Scene-Graph based co-Attention networks for TExt visual question answering

Source: [SceneGATE: Scene-Graph based co-Attention networks for TExt visual question answering](<https://www.sota2.com/research/paper/68fa70381e209131cea49a93>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T01:36:15.259Z

Authors: Feiqi Cao, Siwen Luo, Felipe Nunez, Zean Wen, Josiah Poon, Caren Han

Published: 2022-12-16T05:10:09.000Z

## Abstract

Most TextVQA approaches focus on the integration of objects, scene texts and question words by a simple transformer encoder. But this fails to capture the semantic relations between different modalities. The paper proposes a Scene Graph based co-Attention Network (SceneGATE) for TextVQA, which reveals the semantic relations among the objects, Optical Character Recognition (OCR) tokens and the question words. It is achieved by a TextVQA-based scene graph that discovers the underlying semantics of an image. We created a guided-attention module to capture the intra-modal interplay between the language and the vision as a guidance for inter-modal interactions. To make explicit teaching of the relations between the two modalities, we proposed and integrated two attention modules, namely a scene graph-based semantic relation-aware attention and a positional relation-aware attention. We conducted extensive experiments on two benchmark datasets, Text-VQA and ST-VQA. It is shown that our SceneGATE method outperformed existing ones because of the scene graph and its attention modules.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Scene-Text Visual Question Answering on ST-VQA 1.0 (val)](<https://www.sota2.com/research/sota/scene-text-visual-question-answering-on-st-vqa-1-0-val.md>): Scene Text Visual Question Answering; ST-VQA 1.0 (val); ANLS: 52.5.

- [Scene-Text Visual Question Answering on ST-VQA 1.0 (test)](<https://www.sota2.com/research/sota/scene-text-visual-question-answering-on-st-vqa-1-0-test.md>): Scene Text Visual Question Answering; ST-VQA 1.0 (test); ANLS: 51.6.

- [Visual Question Answering on TextVQA (test)](<https://www.sota2.com/research/sota/visual-question-answering-on-textvqa-test.md>): Visual Question Answering; TextVQA (test); Accuracy: 44.

- [Visual Question Answering on TextVQA (val)](<https://www.sota2.com/research/sota/visual-question-answering-on-textvqa-val.md>): Visual Question Answering; TextVQA (val); VQA Score: 42.4.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2212.08283>)

[PDF](<https://arxiv.org/pdf/2212.08283.pdf>)