Human-Centric Perception for Child Sexual Abuse Imagery

• URL: http://arxiv.org/abs/2603.27290v2
• Date: Thu, 02 Apr 2026 13:13:17 GMT
• Title: Human-Centric Perception for Child Sexual Abuse Imagery
• Abstract summary: Law enforcement agencies and non-gonvernmental organizations handling reports of Child Sexual Abuse Imagery (CSAI) are overwhelmed by large volumes of data.<n> CSAI classification methods often rely on black-box approaches, targeting broad and abstract concepts such as pornography.<n>We propose two methods, namely BKP-Association and YOLO-BKP, for simultaneous pose estimation and detection.
• Score: 4.0916541864237495
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• 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.

Related papers

• CSA-Graphs: A Privacy-Preserving Structural Dataset for Child Sexual Abuse Research [3.4194233177504088]
  We introduce CSA-Graphs, a privacy-preserving structural dataset.<n>Instead of releasing the original images, we provide structural representations that remove explicit visual content while preserving contextual information.<n>Experiments show that both representations retain useful information for classifying CSAI, and that combining them further improves performance.
  arXiv  Detail & Related papers  (2026-04-08T14:26:52Z)
• The Nonverbal Gap: Toward Affective Computer Vision for Safer and More Equitable Online Dating [0.29656637520758655]
  We argue that online dating platforms strip the nonverbal cues that humans rely on to signal comfort, disinterest, and consent, creating a communication gap with disproportionate safety consequences for women.<n>We propose a fairness-first research agenda organized around four capability areas: real-time discomfort detection, engagement asymmetry modeling between partners, consent-aware interaction design, and longitudinal interaction summarization.
  arXiv  Detail & Related papers  (2026-03-20T03:31:07Z)
• Evaluating Multiview Object Consistency in Humans and Image Models [68.36073530804296]
  We leverage an experimental design from the cognitive sciences which requires zero-shot visual inferences about object shape. We collect 35K trials of behavioral data from over 500 participants. We then evaluate the performance of common vision models.
  arXiv  Detail & Related papers  (2024-09-09T17:59:13Z)
• Detecting sexually explicit content in the context of the child sexual abuse materials (CSAM): end-to-end classifiers and region-based networks [0.0]
  Child sexual abuse materials (CSAM) pose a significant threat to the safety and well-being of children worldwide. This study presents methods for classifying sexually explicit content, which plays a crucial role in the automated CSAM detection system.
  arXiv  Detail & Related papers  (2024-06-20T09:21:08Z)
• Data Augmentation in Human-Centric Vision [54.97327269866757]
  This survey presents a comprehensive analysis of data augmentation techniques in human-centric vision tasks. It delves into a wide range of research areas including person ReID, human parsing, human pose estimation, and pedestrian detection. Our work categorizes data augmentation methods into two main types: data generation and data perturbation.
  arXiv  Detail & Related papers  (2024-03-13T16:05:18Z)
• Challenges in Video-Based Infant Action Recognition: A Critical Examination of the State of the Art [9.327466428403916]
  We introduce a groundbreaking dataset called InfActPrimitive'', encompassing five significant infant milestone action categories. We conduct an extensive comparative analysis employing cutting-edge skeleton-based action recognition models. Our findings reveal that, although the PoseC3D model achieves the highest accuracy at approximately 71%, the remaining models struggle to accurately capture the dynamics of infant actions.
  arXiv  Detail & Related papers  (2023-11-21T02:36:47Z)
• Deep Learning for Human Parsing: A Survey [54.812353922568995]
  We provide an analysis of state-of-the-art human parsing methods, covering a broad spectrum of pioneering works for semantic human parsing. We introduce five insightful categories: (1) structure-driven architectures exploit the relationship of different human parts and the inherent hierarchical structure of a human body, (2) graph-based networks capture the global information to achieve an efficient and complete human body analysis, (3) context-aware networks explore useful contexts across all pixel to characterize a pixel of the corresponding class, and (4) LSTM-based methods can combine short-distance and long-distance spatial dependencies to better exploit abundant local and global contexts.
  arXiv  Detail & Related papers  (2023-01-29T10:54:56Z)
• Unsupervised Human Pose Estimation through Transforming Shape Templates [2.729524133721473]
  We present a novel method for learning pose estimators for human adults and infants in an unsupervised fashion. We demonstrate the effectiveness of our approach on two different datasets including adults and infants.
  arXiv  Detail & Related papers  (2021-05-10T07:15:56Z)
• Onfocus Detection: Identifying Individual-Camera Eye Contact from Unconstrained Images [81.64699115587167]
  Onfocus detection aims at identifying whether the focus of the individual captured by a camera is on the camera or not. We build a large-scale onfocus detection dataset, named as the OnFocus Detection In the Wild (OFDIW) We propose a novel end-to-end deep model, i.e., the eye-context interaction inferring network (ECIIN) for onfocus detection.
  arXiv  Detail & Related papers  (2021-03-29T03:29:09Z)
• ConsNet: Learning Consistency Graph for Zero-Shot Human-Object Interaction Detection [101.56529337489417]
  We consider the problem of Human-Object Interaction (HOI) Detection, which aims to locate and recognize HOI instances in the form of human, action, object> in images. We argue that multi-level consistencies among objects, actions and interactions are strong cues for generating semantic representations of rare or previously unseen HOIs. Our model takes visual features of candidate human-object pairs and word embeddings of HOI labels as inputs, maps them into visual-semantic joint embedding space and obtains detection results by measuring their similarities.
  arXiv  Detail & Related papers  (2020-08-14T09:11:18Z)
• Large image datasets: A pyrrhic win for computer vision? [2.627046865670577]
  We investigate problematic practices and consequences of large scale vision datasets. We examine broad issues such as the question of consent and justice as well as specific concerns such as the inclusion of verifiably pornographic images in datasets.
  arXiv  Detail & Related papers  (2020-06-24T06:41:32Z)
• Gradient-Induced Co-Saliency Detection [81.54194063218216]
  Co-saliency detection (Co-SOD) aims to segment the common salient foreground in a group of relevant images. In this paper, inspired by human behavior, we propose a gradient-induced co-saliency detection method.
  arXiv  Detail & Related papers  (2020-04-28T08:40:55Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.