# Attention over Scene Graphs: Indoor Scene Representations Toward CSAI Classification

arXiv: https://arxiv.org/abs/2509.26457 · HTML: https://mlsanity.com/paper/2509.26457/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 32 references that are in the map.
- First posted on arXiv 30 Sep 2025.

## Builds on (most cited first, 20 of 20)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (2020)
- [MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI](https://mlsanity.com/paper/2311.16502/) (2023)
- [Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs](https://mlsanity.com/paper/2406.16860/) (2024)
- [How Attentive are Graph Attention Networks?](https://mlsanity.com/paper/2105.14491/) (2021)
- [MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark](https://mlsanity.com/paper/2409.02813/) (2024)
- [InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions](https://mlsanity.com/paper/2211.05778/) (2022)
- [Scene Graph Generation by Iterative Message Passing](https://mlsanity.com/paper/1701.02426/) (2017)
- [Learning to Compose Dynamic Tree Structures for Visual Contexts](https://mlsanity.com/paper/1812.01880/) (2018)
- [RUST: Latent Neural Scene Representations from Unposed Imagery](https://mlsanity.com/paper/2211.14306/) (2022)
- [From Pixels to Graphs: Open-Vocabulary Scene Graph Generation with Vision-Language Models](https://mlsanity.com/paper/2404.00906/) (2024)
- [Devil's on the Edges: Selective Quad Attention for Scene Graph Generation](https://mlsanity.com/paper/2304.03495/) (2023)
- [Scene Recognition with Prototype-agnostic Scene Layout](https://mlsanity.com/paper/1909.03234/) (2019)
- [SRRM: Semantic Region Relation Model for Indoor Scene Recognition](https://mlsanity.com/paper/2305.08540/) (2023)
- [Leveraging Self-Supervised Learning for Scene Classification in Child Sexual Abuse Imagery](https://mlsanity.com/paper/2403.01183/) (2024)
- [Minimizing Risk Through Minimizing Model-Data Interaction: A Protocol For Relying on Proxy Tasks When Designing Child Sexual Abuse Imagery Detection Models](https://mlsanity.com/paper/2505.06621/) (2025)
- [Explainable Scene Understanding with Qualitative Representations and Graph Neural Networks](https://mlsanity.com/paper/2504.12817/) (2025)

## Built on by (most cited first, 2 of 2)

- [CSA-Graphs: A Privacy-Preserving Structural Dataset for Child Sexual Abuse Research](https://mlsanity.com/paper/2604.07132/) (2026)
- [Classifying by Proxy: Explainable and Reproducible Ensemble of Proxy Tasks for Child Sexual Abuse Imagery Classification](https://mlsanity.com/paper/2606.15993/) (2026)

## Abstract (arXiv)

Indoor scene classification is a critical task in computer vision, with wide-ranging applications that go from robotics to sensitive content analysis, such as child sexual abuse imagery (CSAI) classification. The problem is particularly challenging due to the intricate relationships between objects and complex spatial layouts. In this work, we propose the Attention over Scene Graphs for Sensitive Content Analysis (ASGRA), a novel framework that operates on structured graph representations instead of raw pixels. By first converting images into Scene Graphs and then employing a Graph Attention Network for inference, ASGRA directly models the interactions between a scene's components. This approach offers two key benefits: (i) inherent explainability via object and relationship identification, and (ii) privacy preservation, enabling model training without direct access to sensitive images. On Places8, we achieve 81.27% balanced accuracy, surpassing image-based methods. Real-world CSAI evaluation with law enforcement yields 74.27% balanced accuracy. Our results establish structured scene representations as a robust paradigm for indoor scene classification and CSAI classification. Code is publicly available at https://github.com/tutuzeraa/ASGRA.