STING-BEE: Towards Vision-Language Model for Real-World X-ray Baggage Security Inspection
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916673297055744 |
|---|---|
| author | Velayudhan, Divya Ahmed, Abdelfatah Alansari, Mohamad Gour, Neha Behouch, Abderaouf Hassan, Taimur Wasim, Syed Talal Maalej, Nabil Naseer, Muzammal Gall, Juergen Bennamoun, Mohammed Damiani, Ernesto Werghi, Naoufel |
| author_facet | Velayudhan, Divya Ahmed, Abdelfatah Alansari, Mohamad Gour, Neha Behouch, Abderaouf Hassan, Taimur Wasim, Syed Talal Maalej, Nabil Naseer, Muzammal Gall, Juergen Bennamoun, Mohammed Damiani, Ernesto Werghi, Naoufel |
| contents | Advancements in Computer-Aided Screening (CAS) systems are essential for improving the detection of security threats in X-ray baggage scans. However, current datasets are limited in representing real-world, sophisticated threats and concealment tactics, and existing approaches are constrained by a closed-set paradigm with predefined labels. To address these challenges, we introduce STCray, the first multimodal X-ray baggage security dataset, comprising 46,642 image-caption paired scans across 21 threat categories, generated using an X-ray scanner for airport security. STCray is meticulously developed with our specialized protocol that ensures domain-aware, coherent captions, that lead to the multi-modal instruction following data in X-ray baggage security. This allows us to train a domain-aware visual AI assistant named STING-BEE that supports a range of vision-language tasks, including scene comprehension, referring threat localization, visual grounding, and visual question answering (VQA), establishing novel baselines for multi-modal learning in X-ray baggage security. Further, STING-BEE shows state-of-the-art generalization in cross-domain settings. Code, data, and models are available at https://divs1159.github.io/STING-BEE/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_02823 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | STING-BEE: Towards Vision-Language Model for Real-World X-ray Baggage Security Inspection Velayudhan, Divya Ahmed, Abdelfatah Alansari, Mohamad Gour, Neha Behouch, Abderaouf Hassan, Taimur Wasim, Syed Talal Maalej, Nabil Naseer, Muzammal Gall, Juergen Bennamoun, Mohammed Damiani, Ernesto Werghi, Naoufel Computer Vision and Pattern Recognition Image and Video Processing Advancements in Computer-Aided Screening (CAS) systems are essential for improving the detection of security threats in X-ray baggage scans. However, current datasets are limited in representing real-world, sophisticated threats and concealment tactics, and existing approaches are constrained by a closed-set paradigm with predefined labels. To address these challenges, we introduce STCray, the first multimodal X-ray baggage security dataset, comprising 46,642 image-caption paired scans across 21 threat categories, generated using an X-ray scanner for airport security. STCray is meticulously developed with our specialized protocol that ensures domain-aware, coherent captions, that lead to the multi-modal instruction following data in X-ray baggage security. This allows us to train a domain-aware visual AI assistant named STING-BEE that supports a range of vision-language tasks, including scene comprehension, referring threat localization, visual grounding, and visual question answering (VQA), establishing novel baselines for multi-modal learning in X-ray baggage security. Further, STING-BEE shows state-of-the-art generalization in cross-domain settings. Code, data, and models are available at https://divs1159.github.io/STING-BEE/. |
| title | STING-BEE: Towards Vision-Language Model for Real-World X-ray Baggage Security Inspection |
| topic | Computer Vision and Pattern Recognition Image and Video Processing |
| url | https://arxiv.org/abs/2504.02823 |