Video intelligence
Deep-Cascade
A fast cascade of 3D neural networks for detecting and localizing anomalies in crowded video.
Trustworthy artificial intelligence
Reliable AI beyond the benchmark.
I am an Associate Professor at New Uzbekistan University and a Visiting Researcher at OIST, Japan. I study how AI behaves when inputs are unfamiliar, shifted, or adversarial, and advise industry teams on reliable evaluation and computer vision.
Associate ProfessorNew Uzbekistan University
Visiting ResearcherOIST, Japan
Principal InvestigatorJSPS-funded AI research
Area ChairICLR · NeurIPS · BMVC
Selected research
Contributions spanning video intelligence, self-supervised learning, and trustworthy open-world AI.
Learning foundations
Neighborhood-Relational Encoding
Self-supervised representations that preserve relationships between neighboring samples without intensive annotation.
Trustworthy AI
Unified Anomaly & OOD Survey
A cross-domain framework connecting anomaly, novelty, open-set, and out-of-distribution detection.
AI consulting for industry
Independent technical advice, robustness audits, computer vision and anomaly-detection strategy, due diligence, workshops, and focused proofs of concept.
Latest updates
Top Area Chair — NeurIPS 2026 Main Track
Invited Talk — Keimyung University AI Week 2026, Daegu (28 October)
Area Chair — ICLR 2027