Pith. sign in

REVIEW 4 cited by

Scene Graph Reasoning for Visual Question Answering

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2007.01072 v1 pith:XVE2VAJ6 submitted 2020-07-02 cs.LG cs.CVstat.ML

Marcel Hildebrandt , Hang Li , Rajat Koner , Volker Tresp , Stephan Günnemann This is my paper
classification cs.LGcs.CVstat.ML
keywords sceneansweringgraphimageobjectsquestionfirstmethod
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

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.

Discussion (0). Sign in to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. LLM Meets Scene Graph: Can Large Language Models Understand and Generate Scene Graphs? A Benchmark and Empirical Study

    cs.CL 2025-05 conditional novelty 7.0 of 10

    TSG Bench, a new benchmark, reveals that LLMs handle scene graph understanding well but perform poorly at generating scene graphs from complex narratives, with action decomposition as the main bottleneck.

  2. SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards

    cs.CV 2025-11 conditional novelty 6.0 of 10

    Dense scene-graph-grounded rewards let a 7B multimodal LLM trained on 7K synthetic questions beat SFT and sparse-RL baselines and outscore GPT-4o on average across 12 spatial/real-world benchmarks.

  3. SG-CoT: An Ambiguity-Aware Robotic Planning Framework using Scene Graph Representations

    cs.RO 2026-03 reject novelty 5.0 of 10

    SG-CoT grounds an LLM planner's chain-of-thought in a scene graph via iterative API queries, improving ambiguity detection and clarification in simulated manipulation, though its success metric credits any clarifying ...

  4. Open World Scene Graph Generation using Vision Language Models

    cs.CV 2025-06 conditional novelty 4.0 of 10

    A zero-shot VLM pipeline can generate scene graphs with unseen objects and relations, and a new open-world evaluation setting exposes how much capacity remains untapped.

Pith tools