3 papers
cs.CV2025
Just Dance with ! A Poly-modal Inductor for Weakly-supervised Video Anomaly Detection
Snehashis Majhi, Giacomo D'Amicantonio, Antitza Dantcheva +5
Weakly-supervised methods for video anomaly detection (VAD) are conventionally based merely on RGB spatio-temporal features, which continues to limit their reliability in real-worl…
cs.CV2024
SAM-Mamba: Mamba Guided SAM Architecture for Generalized Zero-Shot Polyp Segmentation
Tapas Kumar Dutta, Snehashis Majhi, Deepak Ranjan Nayak +1
Polyp segmentation in colonoscopy is crucial for detecting colorectal cancer. However, it is challenging due to variations in the structure, color, and size of polyps, as well as t…
cs.CV2023
Human-Scene Network: A Novel Baseline with Self-rectifying Loss for Weakly supervised Video Anomaly Detection
Snehashis Majhi, Rui Dai, Quan Kong +3
Video anomaly detection in surveillance systems with only video-level labels (i.e. weakly-supervised) is challenging. This is due to, (i) the complex integration of human and scene…