The Dynamic VAD Survey is the maintained web companion to the paper “Language Models in Video Anomaly Detection: A Dynamic Survey.” It makes the survey easier to read, search, update, and cite as the field evolves.
The Survey area presents the long-form review as web pages. Explore provides structured method records, while Datasets and Benchmarks organize the evidence used across the literature. Updates records the release history and makes changes between frozen versions transparent.
The website is static and openly accessible. New material may be prepared with agentic-AI assistance, but every public release remains human-reviewed, versioned, and preserved as a frozen archive.
- Furkan MumcuUniversity of South Floridafurkan [at] usf.eduCorresponding author
Received his B.S. degree in Computer Engineering from Bilkent University, Ankara, Turkiye, in 2018, and his M.S. degree in Electrical Engineering from the University of South Florida, Tampa, FL, USA, in 2024, where he is currently pursuing a Ph.D. degree. His research interests include AI security, video anomaly detection, adversarial machine learning, and agentic AI.
- Lokman BekitUniversity of South Floridalbekit [at] usf.edu
Received his B.S. degree in Electrical Engineering from the University of South Florida, in 2025. He is currently pursuing a Ph.D. degree in Artificial Intelligence at the University of South Florida. His research interests include video anomaly detection, vision-language models and efficient inference.
- Michael J. JonesMitsubishi Electric Research Laboratories (MERL)mjones [at] merl.com
Received his bachelors degree in computer science and mathematics from Rice University in 1990 and then went to the Artificial Intelligence Lab at MIT where he received his Ph.D. in Electrical Engineering and Computer Science in 1997. After MIT, he worked at DEC's Cambridge Research Lab before moving to Mitsubishi Electric Research Laboratories (MERL) in Cambridge, Massachusetts, where he is currently a Distinguished Research Scientist in the computer vision group. His research interests include object detection and recognition, machine learning and video anomaly detection.
- Anoop CherianMitsubishi Electric Research Laboratories (MERL)cherian [at] merl.com
Received the undergraduate (honors) degree in computer science and engineering from the National Institute of Technology (NIT), Calicut, India, in 2002, and the MS and PhD degrees from the University of Minnesota, Minneapolis, Minnesota, in 2010 and 2013, respectively. He is a Senior Principal Research Scientist at Mitsubishi Electric Research Labs (MERL) Cambridge, Massachusetts, and an adjunct researcher at the Australian Centre for Robotic Vision (ACRV) at the Australian National University, Canberra, Australia. Before joining ANU, he was a postdoctoral researcher in the LEAR team at INRIA, Grenoble.
- Yasin YilmazUniversity of South Floridayasiny [at] usf.edu
Received the B.S. degree in electrical and electronics engineering from Middle East Technical University, Ankara, Turkiye, in 2008, the M.S. degree in electrical and computer engineering from Koc University, Istanbul, Turkiye, in 2010, and the Ph.D. degree in electrical engineering from Columbia University, New York City, NY, USA, in 2014. He is currently an Associate Professor with the Department of Electrical Engineering, University of South Florida, Tampa, FL, USA. His research interests include machine learning, computer vision, anomaly detection, AI security, IoT security, and their applications in environmental, biomedical, energy, transportation, and communication systems.
Routine metadata and localized prose updates may be proposed with agentic assistance. Taxonomy changes, evaluative claims, removals, and public releases require explicit human approval.