10 papers
Are Multimodal LLMs Ready for Surveillance? A Reality Check on Zero-Shot Anomaly Detection in the Wild
Shanle Yao, Armin Danesh Pazho, Narges Rashvand +1
Multimodal large language models (MLLMs) have demonstrated impressive general competence in video understanding, yet their reliability for real-world Video Anomaly Detection (VAD)…
From Frames to Events: Rethinking Evaluation in Human-Centric Video Anomaly Detection
Narges Rashvand, Shanle Yao, Armin Danesh Pazho +2
Pose-based Video Anomaly Detection (VAD) has gained significant attention for its privacy-preserving nature and robustness to environmental variations. However, traditional frame-l…
Adversarially-Refined VQ-GAN with Dense Motion Tokenization for Spatio-Temporal Heatmaps
Gabriel Maldonado, Narges Rashvand, Armin Danesh Pazho +3
Continuous human motion understanding remains a core challenge in computer vision due to its high dimensionality and inherent redundancy. Efficient compression and representation a…
A Survey on Video Anomaly Detection via Deep Learning: Human, Vehicle, and Environment
Ghazal Alinezhad Noghre, Armin Danesh Pazho, Hamed Tabkhi
Video Anomaly Detection (VAD) has emerged as a pivotal task in computer vision, with broad relevance across multiple fields. Recent advances in deep learning have driven significan…
ALFred: An Active Learning Framework for Real-world Semi-supervised Anomaly Detection with Adaptive Thresholds
Shanle Yao, Ghazal Alinezhad Noghre, Armin Danesh Pazho +1
Video Anomaly Detection (VAD) can play a key role in spotting unusual activities in video footage. VAD is difficult to use in real-world settings due to the dynamic nature of human…
From Lab to Field: Real-World Evaluation of an AI-Driven Smart Video Solution to Enhance Community Safety
Shanle Yao, Babak Rahimi Ardabili, Armin Danesh Pazho +4
This article adopts and evaluates an AI-enabled Smart Video Solution (SVS) designed to enhance safety in the real world. The system integrates with existing infrastructure camera n…