mlsanityData to 14 Oct 2026

CSA-Graphs: A Privacy-Preserving Structural Dataset for Child Sexual Abuse Research

arXiv 2604.07132 ↗First posted 8 Apr 2026cs.CV cs.AI cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Child Sexual Abuse Imagery (CSAI) classification is an important yet challenging problem for computer vision research due to the strict legal and ethical restrictions that prevent the public sharing of CSAI datasets. This limitation hinders reproducibility and slows progress in developing automated methods. In this work, we introduce CSA-Graphs, a privacy-preserving structural dataset. Instead of releasing the original images, we provide structural representations that remove explicit visual content while preserving contextual information. CSA-Graphs includes two complementary graph-based modalities: scene graphs describing object relationships and skeleton graphs encoding human pose. Experiments show that both representations retain useful information for classifying CSAI, and that combining them further improves performance. This dataset enables broader research on computer vision methods for child safety while respecting legal and ethical constraints.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 19 of its 51 references that are in the map. First posted on arXiv 8 Apr 2026.

Builds on

19 of 51 references.

References · 19

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  2. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,166
  3. 2016Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotationscited by 2,656
  4. 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,064
  5. 2021How Attentive are Graph Attention Networks?cited by 835
  6. 2020Deep Learning-Based Human Pose Estimation: A Surveycited by 207
  7. 2025YOLO26: Key Architectural Enhancements and Performance Benchmarking for Real-Time Object Detectioncited by 79
  8. 2022Scene Graph Generation: A Comprehensive Surveycited by 73
  9. 2023Action Scene Graphs for Long-Form Understanding of Egocentric Videoscited by 51
  10. 2024From Pixels to Graphs: Open-Vocabulary Scene Graph Generation with Vision-Language Modelscited by 43
  11. 2021Exploiting Scene Graphs for Human-Object Interaction Detectioncited by 22
  12. 2021Pose2Room: Understanding 3D Scenes from Human Activitiescited by 22
7 more
  1. 2022Seeing without Looking: Analysis Pipeline for Child Sexual Abuse Datasetscited by 10
  2. 2023Adaptive Visual Scene Understanding: Incremental Scene Graph Generationcited by 8
  3. 2024Two-Person Interaction Augmentation with Skeleton Priorscited by 5
  4. 2024Leveraging Self-Supervised Learning for Scene Classification in Child Sexual Abuse Imagerycited by 4
  5. 2025Minimizing Risk Through Minimizing Model-Data Interaction: A Protocol For Relying on Proxy Tasks When Designing Child Sexual Abuse Imagery Detection Modelscited by 4
  6. 2025Attention over Scene Graphs: Indoor Scene Representations Toward CSAI Classificationcited by 2
  7. 2026Human-Centric Perception for Child Sexual Abuse Imagerycited by 1

Built on by

Not cited yet.