CV
Curriculum Vitae of Deokhyun Ahn.
Contact Information
| Name | Deokhyun Ahn |
| Professional Title | Ph.D. Candidate, Brain & Cognitive Engineering |
| ejrgus456@gmail.com | |
| Phone | +82 10 3733 3254 |
Professional Summary
Ph.D. candidate at Korea University and student researcher at KIST AI·Robotics. Research focuses on video understanding, contextual dynamics, and efficient AI systems for social good, with recent emphasis on VLM-guided video anomaly detection.
Experience
-
2023 - Present Seoul, Republic of Korea
Student Researcher
Korea Institute of Science and Technology (KIST)
Video anomaly understanding · Surveillance video · DNN
- Modeled contextual dynamics by integrating RGB appearance, motion dynamics, and scene information, enabling the model to better capture anomaly concepts through their relationships.
-
2022 - 2023 Seoul, Republic of Korea
Research Intern
Korea Institute of Science and Technology (KIST)
Video anomaly understanding in surveillance videos · DNN
-
2021 - 2021 Sejong, Republic of Korea
Researcher
The Korea Transport Institute (KOTI)
Autonomous bus development · Project coordination
Education
-
2023 - Present Seoul, Republic of Korea
Ph.D.
Korea University
Brain & Cognitive Engineering
- Video anomaly detection with a focus on modeling human-inspired contextual understanding in video.
-
2015 - 2020 Seoul, Republic of Korea
M.Eng.
Kwangwoon University
Electronic Engineering
- Thesis: A Study on Passive Target Tracking in Three-Dimensional Indoor Environment by Using Deep Neural Network.
- Completed 19 months of mandatory military service.
-
2013 - 2015 Seoul, Republic of Korea
B.Eng.
Kwangwoon University
Electronic Engineering (Transfer)
- Transferred in Mar 2013 from the National Institute for Lifelong Education (B.Eng. in Computer Engineering coursework, 2011 – 2013).
Awards
-
2025 AIR Outstanding Research Award
KIST AI·Robotics Institute
In recognition of outstanding research achievements during 2025.
-
2025 Excellent Paper Award — Graduate School
Korea University
For outstanding research performance and publication of an excellent paper during doctoral studies.
-
2024 Outstanding Oral Presentation Award
KIST Academia–Research Convergence Conference
For the presentation “Multi-Aspect Contextual Dynamics for Anomaly Detection in Surveillance Videos.”
-
2021 Division Commander's Commendation
Capital Mechanized Infantry Division
For a combat-development proposal on reconnaissance drone AI improvement and AI/big-data-based acoustic detection.
Publications
-
2026 Look Closer: Action-Guided Dense Visual Dynamics for Proficiency Estimation
CVPR 2026 Workshop on Multimodal Human Motion Analysis (Accepted — Pitch & Poster)
-
2026 Learning Robust Representations for Few-Shot Action Recognition with Frame-Level Ambiguities
BMVC 2026 (Under Review)
-
2026 BUSTER: Adaptive Sampling for VLM-Guided Unsupervised Video Anomaly Detection
BMVC 2026 (Under Review)
-
2025 Where and What — Contextual Dynamics-Aware Anomaly Detection in Surveillance Videos
IEEE Transactions on Image Processing
IF 13.7 · top 2.2% in Electrical & Electronic Engineering.
-
2025 A Foundational Research Framework for Real-World Abandoned Object Detection: Train-Free Baseline and a Standardized Benchmark
Expert Systems with Applications
-
2018 A Passive Tracking System Based on Geometric Constraints in Adaptive Wireless Sensor Networks
Sensors, 18(10), 3276
-
2016 2D Indoor Map Building Scheme Using Ultrasonic Module
J. Korean Inst. Comm. and Info. Sci., 41(8), 986–994