Shopformer: Transformer-Based Framework for Detecting Shoplifting via Human Pose
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915263679561728 |
|---|---|
| author | Rashvand, Narges Noghre, Ghazal Alinezhad Pazho, Armin Danesh Ardabili, Babak Rahimi Tabkhi, Hamed |
| author_facet | Rashvand, Narges Noghre, Ghazal Alinezhad Pazho, Armin Danesh Ardabili, Babak Rahimi Tabkhi, Hamed |
| contents | Shoplifting remains a costly issue for the retail sector, but traditional surveillance systems, which are mostly based on human monitoring, are still largely ineffective, with only about 2% of shoplifters being arrested. Existing AI-based approaches rely on pixel-level video analysis which raises privacy concerns, is sensitive to environmental variations, and demands significant computational resources. To address these limitations, we introduce Shopformer, a novel transformer-based model that detects shoplifting by analyzing pose sequences rather than raw video. We propose a custom tokenization strategy that converts pose sequences into compact embeddings for efficient transformer processing. To the best of our knowledge, this is the first pose-sequence-based transformer model for shoplifting detection. Evaluated on real-world pose data, our method outperforms state-of-the-art anomaly detection models, offering a privacy-preserving, and scalable solution for real-time retail surveillance. The code base for this work is available at https://github.com/TeCSAR-UNCC/Shopformer. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_19970 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Shopformer: Transformer-Based Framework for Detecting Shoplifting via Human Pose Rashvand, Narges Noghre, Ghazal Alinezhad Pazho, Armin Danesh Ardabili, Babak Rahimi Tabkhi, Hamed Computer Vision and Pattern Recognition Shoplifting remains a costly issue for the retail sector, but traditional surveillance systems, which are mostly based on human monitoring, are still largely ineffective, with only about 2% of shoplifters being arrested. Existing AI-based approaches rely on pixel-level video analysis which raises privacy concerns, is sensitive to environmental variations, and demands significant computational resources. To address these limitations, we introduce Shopformer, a novel transformer-based model that detects shoplifting by analyzing pose sequences rather than raw video. We propose a custom tokenization strategy that converts pose sequences into compact embeddings for efficient transformer processing. To the best of our knowledge, this is the first pose-sequence-based transformer model for shoplifting detection. Evaluated on real-world pose data, our method outperforms state-of-the-art anomaly detection models, offering a privacy-preserving, and scalable solution for real-time retail surveillance. The code base for this work is available at https://github.com/TeCSAR-UNCC/Shopformer. |
| title | Shopformer: Transformer-Based Framework for Detecting Shoplifting via Human Pose |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.19970 |