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. My work focuses on anomaly detection, out-of-distribution detection, AI robustness, safety, and learning under unknown conditions.
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
The complete archive remains available on the News page.
Will give an invited talk on trustworthy AI at the AI International Cooperation Forum during Keimyung University AI Week 2026 at Keimyung University in Daegu, Republic of Korea, on 28 October 2026.
Serving as an Area Chair for ICLR 2027.
CRANE accepted at BMVC 2026.