Data to 7 Oct 2026

Scene Graph Reasoning for Visual Question Answering

arXiv 2007.01072 ↗First posted 2 Jul 2020cs.LG cs.CV stat.MLcited by 49

Not on the map. Why?

Abstract (arXiv)

Visual question answering is concerned with answering free-form questions about an image. Since it requires a deep linguistic understanding of the question and the ability to associate it with various objects that are present in the image, it is an ambitious task and requires techniques from both computer vision and natural language processing. We propose a novel method that approaches the task by performing context-driven, sequential reasoning based on the objects and their semantic and spatial relationships present in the scene. As a first step, we derive a scene graph which describes the objects in the image, as well as their attributes and their mutual relationships. A reinforcement agent then learns to autonomously navigate over the extracted scene graph to generate paths, which are then the basis for deriving answers. We conduct a first experimental study on the challenging GQA dataset with manually curated scene graphs, where our method almost reaches the level of human performance.

Key facts. Cited by 49 papers in the map (data through 7 Oct 2026). First posted on arXiv 2 Jul 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 5; 2022: 15; 2023: 7; 2024: 11; 2025: 10; 2026: 1.

49 papers.

Sort:

By area:

2024SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilitiescited by 679
2021Bipartite Graph Network with Adaptive Message Passing for Unbiased Scene Graph Generationcited by 137
2022Panoptic Scene Graph Generationcited by 114
2021SGTR: End-to-end Scene Graph Generation with Transformercited by 102
2022Stacked Hybrid-Attention and Group Collaborative Learning for Unbiased Scene Graph Generationcited by 67
2022Relationformer: A Unified Framework for Image-to-Graph Generationcited by 67
2024RoboEXP: Action-Conditioned Scene Graph via Interactive Exploration for Robotic Manipulationcited by 48
2024From Pixels to Graphs: Open-Vocabulary Scene Graph Generation with Vision-Language Modelscited by 43
2021OODformer: Out-Of-Distribution Detection Transformercited by 27
2022Fine-Grained Predicates Learning for Scene Graph Generationcited by 27
2022Iterative Scene Graph Generation with Generative Transformerscited by 22
2023HiLo: Exploiting High Low Frequency Relations for Unbiased Panoptic Scene Graph Generationcited by 19

37 more

2025InSpire: Vision-Language-Action Models with Intrinsic Spatial Reasoningcited by 19
2024Look Before You Decide: Prompting Active Deduction of MLLMs for Assumptive Reasoningcited by 17
2024OpenPSG: Open-set Panoptic Scene Graph Generation via Large Multimodal Modelscited by 15
2022Adaptive Fine-Grained Predicates Learning for Scene Graph Generationcited by 14
2022VQA and Visual Reasoning: An Overview of Recent Datasets, Methods and Challengescited by 14
2025SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewardscited by 14
2022Joint learning of object graph and relation graph for visual question answeringcited by 13
2023VLPrompt: Vision-Language Prompting for Panoptic Scene Graph Generationcited by 12
2024Groupwise Query Specialization and Quality-Aware Multi-Assignment for Transformer-based Visual Relationship Detectioncited by 11
2023Towards Complex-query Referring Image Segmentation: A Novel Benchmarkcited by 10
2025AerialVG: A Challenging Benchmark for Aerial Visual Grounding by Exploring Positional Relationscited by 10
2025LLM Meets Scene Graph: Can Large Language Models Understand and Generate Scene Graphs? A Benchmark and Empirical Studycited by 9
2021Learning through structure: towards deep neuromorphic knowledge graph embeddingscited by 7
2025Open World Scene Graph Generation using Vision Language Modelscited by 7
2022Incremental Object Grounding Using Scene Graphscited by 6
2024ROOT: VLM based System for Indoor Scene Understanding and Beyondcited by 6
2024RA-SGG: Retrieval-Augmented Scene Graph Generation Framework via Multi-Prototype Learningcited by 6
2021Scenes and Surroundings: Scene Graph Generation using Relation Transformercited by 5
2022Is it all a cluster game? -- Exploring Out-of-Distribution Detection based on Clustering in the Embedding Spacecited by 5
2022Box Supervised Video Segmentation Proposal Networkcited by 4
2022Relational representation learning with spike trainscited by 4
2022Visual Semantic Parsing: From Images to Abstract Meaning Representationcited by 4
2023Improving Scene Graph Generation with Superpixel-Based Interaction Learningcited by 4
2024Situational Scene Graph for Structured Human-centric Situation Understandingcited by 4
2025Enhancing Spatial Reasoning through Visual and Textual Thinkingcited by 4
2025ESCA: Contextualizing Embodied Agents via Scene-Graph Generationcited by 4
2023SPAN: Learning Similarity between Scene Graphs and Images with Transformerscited by 3
2022Learning Two-Step Hybrid Policy for Graph-Based Interpretable Reinforcement Learningcited by 1
2024SGTR+: End-to-end Scene Graph Generation with Transformercited by 1
2025CoPa-SG: Dense Scene Graphs with Parametric and Proto-Relationscited by 1
2025MARS2 2025 Challenge on Multimodal Reasoning: Datasets, Methods, Results, Discussion, and Outlookcited by 1
2022SGDraw: Scene Graph Drawing Interface Using Object-Oriented Representationcited by 0
2023Towards Unseen Triples: Effective Text-Image-joint Learning for Scene Graph Generationcited by 0
2023STDG: Semi-Teacher-Student Training Paradigram for Depth-guided One-stage Scene Graph Generationcited by 0
2024Discrete Subgraph Sampling for Interpretable Graph based Visual Question Answeringcited by 0
2025HOIverse: A Synthetic Scene Graph Dataset With Human Object Interactionscited by 0
2026Spatial Atlas: Compute-Grounded Reasoning for Spatial-Aware Research Agent Benchmarkscited by 0