Attention over Scene Graphs: Indoor Scene Representations Toward CSAI Classification
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914068367933440 |
|---|---|
| author | Barros, Artur Caetano, Carlos Macedo, João Santos, Jefersson A. dos Avila, Sandra |
| author_facet | Barros, Artur Caetano, Carlos Macedo, João Santos, Jefersson A. dos Avila, Sandra |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_26457 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Attention over Scene Graphs: Indoor Scene Representations Toward CSAI Classification Barros, Artur Caetano, Carlos Macedo, João Santos, Jefersson A. dos Avila, Sandra Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning 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. |
| title | Attention over Scene Graphs: Indoor Scene Representations Toward CSAI Classification |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2509.26457 |