mlsanityData to 7 Oct 2026

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

arXiv 2104.10283 ↗First posted 20 Apr 2021cs.CL cs.CVcited by 16

Not on the map. Why?

Abstract (arXiv)

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 for 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 model by a large margin (88.43% vs. 94.78%).

Key facts. Cited by 16 papers in the map (data through 7 Oct 2026). Builds on 20 of its 24 references that are in the map. First posted on arXiv 20 Apr 2021.

Builds on

20 of 24 references.

References · 20

  1. 2017Graph Attention Networkscited by 8,854
  2. 2018How Powerful are Graph Neural Networks?cited by 4,355
  3. 2016Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotationscited by 2,646
  4. 2019Strategies for Pre-training Graph Neural Networkscited by 964
  5. 2016SPICE: Semantic Propositional Image Caption Evaluationcited by 820
  6. 2017A simple neural network module for relational reasoningcited by 345
  7. 2018Image Generation from Scene Graphscited by 324
  8. 2016Analyzing the Behavior of Visual Question Answering Modelscited by 119
  9. 2019Relation-Aware Graph Attention Network for Visual Question Answeringcited by 119
  10. 2019Learning by Abstraction: The Neural State Machinecited by 113
  11. 2016Human Attention in Visual Question Answering: Do Humans and Deep Networks Look at the Same Regions?cited by 111
  12. 2018Did the Model Understand the Question?cited by 60
8 more
  1. 2019Language-Conditioned Graph Networks for Relational Reasoningcited by 55
  2. 2020ALICE: Active Learning with Contrastive Natural Language Explanationscited by 36
  3. 2020Neuro-Symbolic Visual Reasoning: Disentangling "Visual" from "Reasoning"cited by 35
  4. 2017Situation Recognition with Graph Neural Networkscited by 34
  5. 2020Beyond User Self-Reported Likert Scale Ratings: A Comparison Model for Automatic Dialog Evaluationcited by 22
  6. 2019MOSS: End-to-End Dialog System Framework with Modular Supervisioncited by 19
  7. 2020LRTA: A Transparent Neural-Symbolic Reasoning Framework with Modular Supervision for Visual Question Answeringcited by 12
  8. 2020Neural Group Testing to Accelerate Deep Learningcited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 3; 2023: 3; 2024: 4; 2025: 2; 2026: 2.

16 papers.

Sort:

By area:

  1. 2024Towards Semantic Equivalence of Tokenization in Multimodal LLMcited by 45
  2. 2022VQA-GNN: Reasoning with Multimodal Knowledge via Graph Neural Networks for Visual Question Answeringcited by 22
  3. 2023Multimodal Graph Transformer for Multimodal Question Answeringcited by 10
  4. 2021HERALD: An Annotation Efficient Method to Detect User Disengagement in Social Conversationscited by 9
  5. 2025DSPNet: Dual-vision Scene Perception for Robust 3D Question Answeringcited by 9
  6. 2022Symbolic image detection using scene and knowledge graphscited by 3
  7. 2022Visually Grounded VQA by Lattice-based Retrievalcited by 3
  8. 2024REACT: Real-time Efficiency and Accuracy Compromise for Tradeoffs in Scene Graph Generationcited by 3
  9. 2024Goal-Oriented Semantic Communication for Wireless Visual Question Answeringcited by 3
  10. 2023SelfGraphVQA: A Self-Supervised Graph Neural Network for Scene-based Question Answeringcited by 2
  11. 2024Intrinsic Subgraph Generation for Interpretable Graph based Visual Question Answeringcited by 1
  12. 2025Bridging the Gap Between Multimodal Foundation Models and World Modelscited by 1
4 more
  1. 2026REACT++: Efficient Cross-Attention for Real-Time Scene Graph Generationcited by 1
  2. 2021Adventurer's Treasure Hunt: A Transparent System for Visually Grounded Compositional Visual Question Answering based on Scene Graphscited by 0
  3. 2023Unified Lattice Graph Fusion for Chinese Named Entity Recognitioncited by 0
  4. 2026DSFlash: Comprehensive Panoptic Scene Graph Generation in Realtimecited by 0