2 papers
cs.CV2026
Parser-Free VLM Verification for Federated Weakly Supervised Video Anomaly Detection
Sébastien Thuau, Amira Gran, Siba Haidar +1
How can vision-language models help video anomaly detection (VAD) when surveillance data remain distributed, weakly labeled, and resource-constrained? Most weakly supervised VAD me…
cs.CV2026
Federated Binary Gating with Server-Side Vision-Language Inference for Surveillance Anomaly Classification
Côme-Alexis Puech, Sébastien Thuau, Amira Gran +3
Privacy-sensitive surveillance systems could benefit from large vision-language models (VLMs), but such models typically require centralized access to raw video. In federated learn…