Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Human-Centric Perception for Child Sexual Abuse Imagery

Camila Laranjeira, João Macedo, Sandra Avila, Fabrício Benevenuto, Jefersson A. dos Santos

Abstract

Law enforcement agencies and non-gonvernmental organizations handling reports of Child Sexual Abuse Imagery (CSAI) are overwhelmed by large volumes of data, requiring the aid of automation tools. However, defining sexual abuse in images of children is inherently challenging, encompassing sexually explicit activities and hints of sexuality conveyed by the individual's pose, or their attire. CSAI classification methods often rely on black-box approaches, targeting broad and abstract concepts such as pornography. Thus, our work is an in-depth exploration of tasks from the literature on Human-Centric Perception, across the domains of safe images, adult pornography, and CSAI, focusing on targets that enable more objective and explainable pipelines for CSAI classification in the future. We introduce the Body-Keypoint-Part Dataset (BKPD), gathering images of people from varying age groups and sexual explicitness to approximate the domain of CSAI, along with manually curated hierarchically structured labels for skeletal keypoints and bounding boxes for person and body parts, including head, chest, hip, and hands. We propose two methods, namely BKP-Association and YOLO-BKP, for simultaneous pose estimation and detection, with targets associated per individual for a comprehensive decomposed representation of each person. Our methods are benchmarked on COCO-Keypoints and COCO-HumanParts, as well as our human-centric dataset, achieving competitive results with models that jointly perform all tasks. Cross-domain ablation studies on BKPD and a case study on RCPD highlight the challenges posed by sexually explicit domains. Our study addresses previously unexplored targets in the CSAI domain, paving the way for novel research opportunities.

Human-Centric Perception for Child Sexual Abuse Imagery

Abstract

Law enforcement agencies and non-gonvernmental organizations handling reports of Child Sexual Abuse Imagery (CSAI) are overwhelmed by large volumes of data, requiring the aid of automation tools. However, defining sexual abuse in images of children is inherently challenging, encompassing sexually explicit activities and hints of sexuality conveyed by the individual's pose, or their attire. CSAI classification methods often rely on black-box approaches, targeting broad and abstract concepts such as pornography. Thus, our work is an in-depth exploration of tasks from the literature on Human-Centric Perception, across the domains of safe images, adult pornography, and CSAI, focusing on targets that enable more objective and explainable pipelines for CSAI classification in the future. We introduce the Body-Keypoint-Part Dataset (BKPD), gathering images of people from varying age groups and sexual explicitness to approximate the domain of CSAI, along with manually curated hierarchically structured labels for skeletal keypoints and bounding boxes for person and body parts, including head, chest, hip, and hands. We propose two methods, namely BKP-Association and YOLO-BKP, for simultaneous pose estimation and detection, with targets associated per individual for a comprehensive decomposed representation of each person. Our methods are benchmarked on COCO-Keypoints and COCO-HumanParts, as well as our human-centric dataset, achieving competitive results with models that jointly perform all tasks. Cross-domain ablation studies on BKPD and a case study on RCPD highlight the challenges posed by sexually explicit domains. Our study addresses previously unexplored targets in the CSAI domain, paving the way for novel research opportunities.

Paper Structure

This paper contains 21 sections, 6 equations, 8 figures, 14 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Related Work
  3. CSAI Classification
  4. Human-Centric Perception
  5. BKP-Dataset
  6. Methodologies
  7. BKP Association
  8. YOLO-BKP
  9. Experiments
  10. Datasets
  11. COCO
  12. RCPD
  13. Metrics
  14. Results
  15. COCO
  16. ...and 6 more sections

Figures (8)

  • Figure 1: Examples of labeled samples from BKPD. Top row: sourced from SOD, bottom row: sourced from Open Images. Boxes are color-coded per associated individual.
  • Figure 2: YOLO-BKP architecture.
  • Figure 3: Samples with annotations from COCO-Keypoints (left) and COCO-HumanParts (right).
  • Figure 4: Qualitative results for pose estimation for small and tiny persons. Original images and zoom-ins side-by-side.
  • Figure 5: Qualitative results on COCO2017 val set. Left: BKP-Association, right: YOLO-BKP. Bounding box colors indicate association to the same individual.
  • ...and 3 more figures