mlsanityData to 14 Oct 2026

Relation-Aware Graph Attention Network for Visual Question Answering

arXiv 1903.12314 ↗First posted 29 Mar 2019cs.CV cs.AIcited by 119

Not on the map. Why?

Abstract (arXiv)

In order to answer semantically-complicated questions about an image, a Visual Question Answering (VQA) model needs to fully understand the visual scene in the image, especially the interactive dynamics between different objects. We propose a Relation-aware Graph Attention Network (ReGAT), which encodes each image into a graph and models multi-type inter-object relations via a graph attention mechanism, to learn question-adaptive relation representations. Two types of visual object relations are explored: (i) Explicit Relations that represent geometric positions and semantic interactions between objects; and (ii) Implicit Relations that capture the hidden dynamics between image regions. Experiments demonstrate that ReGAT outperforms prior state-of-the-art approaches on both VQA 2.0 and VQA-CP v2 datasets. We further show that ReGAT is compatible to existing VQA architectures, and can be used as a generic relation encoder to boost the model performance for VQA.

Key facts. Cited by 119 papers in the map (data through 14 Oct 2026). First posted on arXiv 29 Mar 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 38; 2022: 25; 2023: 30; 2024: 14; 2025: 10; 2026: 2.

119 papers.

Sort:

By area:

  1. 2021Scaling Local Self-Attention for Parameter Efficient Visual Backbonescited by 220
  2. 2022Vision-Language Pre-training: Basics, Recent Advances, and Future Trendscited by 117
  3. 2022Super-CLEVR: A Virtual Benchmark to Diagnose Domain Robustness in Visual Reasoningcited by 92
  4. 2024Natural Language Understanding and Inference with MLLM in Visual Question Answering: A Surveycited by 76
  5. 2021Adversarial VQA: A New Benchmark for Evaluating the Robustness of VQA Modelscited by 75
  6. 2022Scene Graph Generation: A Comprehensive Surveycited by 73
  7. 2021Video as Conditional Graph Hierarchy for Multi-Granular Question Answeringcited by 68
  8. 2023Beyond One-to-One: Rethinking the Referring Image Segmentationcited by 68
  9. 2022A Survey on Graph Neural Networks and Graph Transformers in Computer Vision: A Task-Oriented Perspectivecited by 56
  10. 2021Attention, please! A survey of Neural Attention Models in Deep Learningcited by 51
  11. 2024EGTR: Extracting Graph from Transformer for Scene Graph Generationcited by 47
  12. 2023Act As You Wish: Fine-Grained Control of Motion Diffusion Model with Hierarchical Semantic Graphscited by 45
38 more
  1. 2023Expert Knowledge-Aware Image Difference Graph Representation Learning for Difference-Aware Medical Visual Question Answeringcited by 41
  2. 2021DualVGR: A Dual-Visual Graph Reasoning Unit for Video Question Answeringcited by 35
  3. 2021Multimodal Dialogue Response Generationcited by 32
  4. 2021ROSITA: Enhancing Vision-and-Language Semantic Alignments via Cross- and Intra-modal Knowledge Integrationcited by 31
  5. 2024STAR: A First-Ever Dataset and A Large-Scale Benchmark for Scene Graph Generation in Large-Size Satellite Imagerycited by 31
  6. 2022(2.5+1)D Spatio-Temporal Scene Graphs for Video Question Answeringcited by 30
  7. 2024Reefknot: A Comprehensive Benchmark for Relation Hallucination Evaluation, Analysis and Mitigation in Multimodal Large Language Modelscited by 30
  8. 2022A Review on Methods and Applications in Multimodal Deep Learningcited by 29
  9. 2021Recent Advances and Trends in Multimodal Deep Learning: A Reviewcited by 26
  10. 2021Coarse-to-Fine Reasoning for Visual Question Answeringcited by 25
  11. 2022Toward 3D Spatial Reasoning for Human-like Text-based Visual Question Answeringcited by 25
  12. 2023Robust Visual Question Answering: Datasets, Methods, and Future Challengescited by 23
  13. 2023SPA: A Graph Spectral Alignment Perspective for Domain Adaptationcited by 22
  14. 2023Prophet: Prompting Large Language Models with Complementary Answer Heuristics for Knowledge-based Visual Question Answeringcited by 21
  15. 2022GSRFormer: Grounded Situation Recognition Transformer with Alternate Semantic Attention Refinementcited by 20
  16. 2022Visual Perturbation-aware Collaborative Learning for Overcoming the Language Prior Problemcited by 18
  17. 2021Efficient Graph Deep Learning in TensorFlow with tf_geometriccited by 17
  18. 2021Structured Co-reference Graph Attention for Video-grounded Dialoguecited by 17
  19. 2021Comprehensive Visual Question Answering on Point Clouds through Compositional Scene Manipulationcited by 17
  20. 2023Interpretable Medical Image Visual Question Answering via Multi-Modal Relationship Graph Learningcited by 17
  21. 2021Learning from Pixel-Level Label Noise: A New Perspective for Semi-Supervised Semantic Segmentationcited by 16
  22. 2021GraghVQA: Language-Guided Graph Neural Networks for Graph-based Visual Question Answeringcited by 16
  23. 2021Auto-Parsing Network for Image Captioning and Visual Question Answeringcited by 16
  24. 2021Multi-Modal Interaction Graph Convolutional Network for Temporal Language Localization in Videoscited by 16
  25. 2023Learning Situation Hyper-Graphs for Video Question Answeringcited by 16
  26. 20233D-Aware Visual Question Answering about Parts, Poses and Occlusionscited by 16
  27. 2022VQA and Visual Reasoning: An Overview of Recent Datasets, Methods and Challengescited by 14
  28. 2021GoG: Relation-aware Graph-over-Graph Network for Visual Dialogcited by 13
  29. 2022Joint learning of object graph and relation graph for visual question answeringcited by 13
  30. 2024Layout Agnostic Human Activity Recognition in Smart Homes through Textual Descriptions Of Sensor Triggers (TDOST)cited by 13
  31. 2025Question-Aware Gaussian Experts for Audio-Visual Question Answeringcited by 12
  32. 2021Learning Reasoning Paths over Semantic Graphs for Video-grounded Dialoguescited by 11
  33. 2021X-GGM: Graph Generative Modeling for Out-of-Distribution Generalization in Visual Question Answeringcited by 10
  34. 2021Learning to Ground Visual Objects for Visual Dialogcited by 10
  35. 2021Incomplete Multi-view Clustering via Cross-view Relation Transfercited by 10
  36. 2021SkipNode: On Alleviating Performance Degradation for Deep Graph Convolutional Networkscited by 10
  37. 2023Graph Neural Networks in Vision-Language Image Understanding: A Surveycited by 10
  38. 2023Plug-and-Play Regulators for Image-Text Matchingcited by 10

50 most cited of 119 All 119 (JSON)