TY - GEN
T1 - STING-BEE: Towards Vision-Language Model for Real-World X-ray Baggage Security Inspection
AU - Velayudhan, Divya
AU - Ahmed, Abdelfatah
AU - Alansari, Mohamad
AU - Gour, Neha
AU - Behouch, Abderaouf
AU - Hassan, Taimur
AU - Wasim, Syed Talal
AU - Maalej, Nabil
AU - Naseer, Muzammal
AU - Gall, Juergen
AU - Bennamoun, Mohammed
AU - Damiani, Ernesto
AU - Werghi, Naoufel
PY - 2025/8/13
Y1 - 2025/8/13
N2 - 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/.
AB - 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/.
KW - multi-modal
KW - threat classification
KW - threat localization
KW - visual grounding
KW - visual question answering
KW - x-ray baggage security
UR - https://ieeexplore.ieee.org/document/11094781
UR - https://www.scopus.com/pages/publications/105045566900
U2 - 10.1109/CVPR52734.2025.01934
DO - 10.1109/CVPR52734.2025.01934
M3 - Conference publication
AN - SCOPUS:105045566900
T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR)
SP - 20767
EP - 20777
BT - 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
PB - IEEE
T2 - 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2025
Y2 - 11 June 2025 through 15 June 2025
ER -