GraghVQA: Language-Guided Graph Neural Networks for Graph-based Visual Question Answering

Weixin Liang, Yanhao Jiang, Zixuan Liu


Abstract
Images are more than a collection of objects or attributes — they represent a web of relationships among interconnected objects. Scene Graph has emerged as a new modality as a structured graphical representation of images. Scene Graph encodes objects as nodes connected via pairwise relations as edges. To support question answering on scene graphs, we propose GraphVQA, a language-guided graph neural network framework that translates and executes a natural language question as multiple iterations of message passing among graph nodes. We explore the design space of GraphVQA framework, and discuss the trade-off of different design choices. Our experiments on GQA dataset show that GraphVQA outperforms the state-of-the-art accuracy by a large margin (88.43% vs. 94.78%).
Anthology ID:
2021.maiworkshop-1.12
Volume:
Proceedings of the Third Workshop on Multimodal Artificial Intelligence
Month:
June
Year:
2021
Address:
Mexico City, Mexico
Editors:
Amir Zadeh, Louis-Philippe Morency, Paul Pu Liang, Candace Ross, Ruslan Salakhutdinov, Soujanya Poria, Erik Cambria, Kelly Shi
Venue:
maiworkshop
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
79–86
Language:
URL:
https://aclanthology.org/2021.maiworkshop-1.12
DOI:
10.18653/v1/2021.maiworkshop-1.12
Bibkey:
Cite (ACL):
Weixin Liang, Yanhao Jiang, and Zixuan Liu. 2021. GraghVQA: Language-Guided Graph Neural Networks for Graph-based Visual Question Answering. In Proceedings of the Third Workshop on Multimodal Artificial Intelligence, pages 79–86, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
GraghVQA: Language-Guided Graph Neural Networks for Graph-based Visual Question Answering (Liang et al., maiworkshop 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.maiworkshop-1.12.pdf
Optional supplementary material:
 2021.maiworkshop-1.12.OptionalSupplementaryMaterial.zip
Code
 codexxxl/GraphVQA
Data
GQA