Ph.D. in Brain & Cognitive Engineering
2023-03 – Present
- Expected graduation: March 2027.
- Study contextual video understanding inspired by human cognitive processes.
Curriculum vitae
Download PDFDeokhyun Ahn
Ph.D. Candidate, Brain & Cognitive Engineering
Expected graduation: March 2027 · Available from March 2027
Reliable and efficient video understanding for social good.
Research for social good has always been my first priority, and it will continue to guide my work. I am a Ph.D. candidate in Brain & Cognitive Engineering at Korea University and a student researcher at KIST AI·Robotics.
My early work on sensing applications, including an ultrasonic SLAM helmet for firefighters and indoor drone tracking, shaped my commitment to dependable systems for real-world needs. I now study reliable and efficient video understanding: identifying anomalous behavior, understanding its temporal context, and explaining it with visual evidence.
My work connects video anomaly detection and understanding, adaptive video sampling, action recognition, and vision-language models (VLMs). Through public-safety research at KIST, I work on contextual anomaly detection and behavior analysis for real-world surveillance video.
Recent work includes BUSTER for VLM-guided anomaly detection with adaptive sampling, Where and What for contextual anomaly detection, and Look Closer for action-guided proficiency estimation.
Current focus: why vision-language models hallucinate in video anomaly understanding, and how selective visual verification can make their explanations more faithful.
Research keywords
- Video understanding
- Video anomaly detection & understanding
- Adaptive video sampling
- Efficient vision-language models
- VLM hallucination & reliability
- Temporal & contextual reasoning
- Action recognition & human motion analysis
- Video surveillance & public safety
- Seoul, Republic of Korea
- ejrgus456@gmail.com
- +82 10 3733 3254
- GitHub
Education
M.Eng. in Electronic Engineering
2015-08 – 2020-02
Kwangwoon University
- Thesis: A Study on Passive Target Tracking in Three-Dimensional Indoor Environment by Using Deep Neural Network.
- Completed 19 months of mandatory military service.
B.Eng. in Electronic Engineering (Transfer)
2013-03 – 2015-08
Kwangwoon University
- Transferred in March 2013 from the National Institute for Lifelong Education after completing B.Eng. coursework in Computer Engineering from March 2011 to February 2013.
Experience
Student Researcher
2023-01 – Present
Korea Institute of Science and Technology (KIST)
KIST AI·Robotics Institute · Vision Intelligence Group
- Develop public safety video systems spanning action recognition, contextual anomaly detection, and vision language models that explain anomalous behavior.
Research Intern
2022-01 – 2023-02
Korea Institute of Science and Technology (KIST)
KIST AI·Robotics Institute · Vision Intelligence Group · Began surveillance video research through urban public safety projects and national research programs.
Researcher
2021-10 – 2021-12
The Korea Transport Institute (KOTI)
Contributed to autonomous bus development through SLAM, control center systems, policy research, and coordination.
Research Grants & Projects
National R&D · video anomaly detection that uses context
Real-Time Intelligent Surveillance for Public Safety
MSIT & MOTIE · with Yonsei University and the Korean National Police Agency
- Analyzes about 1,000 cameras from city scale CCTV control centers for crime related anomalies and was validated in Anyang City, Korea.
Government R&D · safety services using mobile platforms
Mobile Platform for Active Safety Services
Korean National Police Agency & MOTIE
New initiative
Anomaly Detection in Correctional Facilities
Detecting inmate anomalous behavior in custodial environments.
Awards
AIR Outstanding Research Award
December 2025
KIST AI·Robotics Institute
In recognition of outstanding research achievements during 2025.
Excellent Paper Award, Graduate School
February 2025
Korea University
For outstanding research performance and publication of an excellent paper during doctoral studies.
Outstanding Oral Presentation Award
November 2024
KIST Academia and Research Convergence Conference
For the presentation "Multi-Aspect Contextual Dynamics for Anomaly Detection in Surveillance Videos."
Division Commander's Commendation
July 2021
Capital Mechanized Infantry Division
For a combat development proposal on reconnaissance drone AI improvement and acoustic detection using AI and big data.
Publications
Look Closer: Action-Guided Dense Visual Dynamics for Proficiency Estimation
2026
CVPRW 2026, Multimodal Human Motion Analysis (Accepted, Pitch and Poster Presentation)
BUSTER: Adaptive Sampling for VLM-Guided Unsupervised Video Anomaly Detection
2026
British Machine Vision Conference (BMVC), Accepted
Learning Robust Representations for Few-Shot Action Recognition with Frame-Level Ambiguities
2026
IEEE Access (Submitted)
Where and What: Contextual Dynamics-Aware Anomaly Detection in Surveillance Videos
2025
IEEE Transactions on Image Processing
IF 13.7 · Top 2.2% in Electrical & Electronic Engineering.
A Foundational Research Framework for Real-World Abandoned Object Detection: Train-Free Baseline and a Standardized Benchmark
2025
Expert Systems with Applications
A Passive Tracking System Based on Geometric Constraints in Adaptive Wireless Sensor Networks
2018
Sensors, 18(10), 3276
2D Indoor Map Building Scheme Using Ultrasonic Module
2016
J. Korean Inst. Comm. and Info. Sci., 41(8), 986–994
Teaching
Teaching Assistant, Senior Capstone Project
2018-09 – 2018-12
Kwangwoon University
Instructor: Prof. Youngok Kim
- Assisted in managing and supporting the Capstone Design Project as a TA for 50+ students.
Teaching Assistant, Computer Architecture
2017-03 – 2017-06
Kwangwoon University
Instructor: Prof. Youngok Kim
- Graded assignments and provided feedback for 30+ students with Q&A sessions.
Skills
Programming
- Python
- C
- Java
- Git
- Linux
Machine Learning
- PyTorch
- TensorFlow
- Keras
- NumPy
- Pandas
- Matplotlib
Sensing
- Ultrasonic
- Beacon
- RF
- Wi-Fi
- 3-axis Accelerometer
Embedded & IoT
- Raspberry Pi
- Arduino
Languages
Korean
Native speaker
English
Professional working proficiency
Interests
Video Intelligence
- Video understanding
- Video anomaly detection & understanding
- Adaptive video sampling
- Efficient vision-language models
- VLM hallucination & reliability
- Temporal & contextual reasoning
- Action recognition & human motion analysis
- Video surveillance & public safety