About Me
Chan Hur received his Ph.D. in Computer Science and Engineering from Kyungpook National University (advised by Prof. Hyeyoung Park). He is currently a researcher in the Digital Convergence Research Department at ETRI (Electronics and Telecommunications Research Institute), where he works on VLMs, multimodal retrieval, and GUI agents. His research focuses on multimodal learning and multimodal applications with LLMs/LMMs, particularly in text–video retrieval, GUI agents, compositional image retrieval, video question answering, and large language/multimodal models. He also works on domain-specific AI for medical applications. He is interested in bridging semantic gaps between heterogeneous modalities and advancing multimodal representation learning.
Current
- 2026.02–Present: Researcher, ETRI Digital Convergence Research Department.
Latest News
- 2026.02~: Joined ETRI Digital Convergence Research Department as a researcher.
- 2026: Awarded the CSE Award from Kyungpook National University Computer Science and Engineering.
- 2026: Semantic Hardness Is Not Visual Hardness paper accepted at ACL 2026 (main conference).
- 2026: ReFineVQA paper accepted at WACV 2026.
- 2025: Narrating the Video accepted at CVPR 2025 and Local Feature Aggregation accepted at ICAIIC 2025.
Research Interests and Skills
- Multimodal Learning: Vision-Language Model, Text-Video Retrieval, GUI Agent, Composed Image Retrieval
- Representation Learning: Cross-modal alignment, Generative Caption Utilization
- Deep Learning Frameworks: PyTorch, TensorFlow
- Language Skills: Korean (native), English (fluent), Japanese (intermediate)
Education
-
Ph.D. in Computer Science and Engineering
Kyungpook National University, Daegu, South Korea
2021.03 – 2026.02
Dissertation: Advancing Text-Video Retrieval with Frame-Wise Generative Information
Advisor: Prof. Hyeyoung Park
-
M.S. in Computer Science and Engineering
Kyungpook National University, Daegu, South Korea
2019.03 – 2021.02
Thesis: Zero-Shot Image Recognition Model Using Image Description
Advisor: Prof. Hyeyoung Park
-
B.S. in Mechanical Engineering
Kyungpook National University, Daegu, South Korea
2014 – 2019
Publications
International Conferences
-
Semantic Hardness Is Not Visual Hardness: Sign-Aware Hard Negative Mining for Sign Language Retrieval
Junmyeong Lee, Chan Hur, ChangSu Choi, Sukmin Cho, Fitsum Gaim, Eui Jun Hwang, Hoyun Song, KyungTae Lim, ACL 2026
-
ReFineVQA: Iterative Refinement of Video Description via Feedback Generation for Video Question Answering”
Jeongwan Shin, Chan Hur, Seongmin Cho, Jae-Ho Choi, Hyeyoung Park WACV 2026
-
Narrating the Video:Boosting Text-Video Retrieval via Comprehensive Utilization of Frame-Level Captions
Chan Hur, Jeong-hun Hong, Dong-hun Lee, Dabin Kang, Semin Myeong, Sang-hyo Park, Hyeyoung Park, CVPR 2025 – arXiv
-
Local Feature Aggregation with Attribute Anchors for Text-guided Image-Text Retrieval
Chan Hur, Hyeyoung Park, ICAIIC 2025 – IEEE
-
Automatic Image Recommendation for Economic Topics using Visual and Semantic Information
Chan Hur, Changhun Hyun, Hyeyoung Park, ICSC 2020 – IEEE
International Journals
-
EENet:Embedding Enhancement Network for Compositional Image-Text Retrieval using Generated Text
Chan Hur, Hyeyoung Park, Multimedia Tools and Applications, 2023 – SCIE (Q1)
-
Zero-shot Image Classification using Captioning-based Rectified Embedding Vector
Chan Hur, Hyeyoung Park, Applied Sciences, 2023 – SCIE (Q2)
-
An Image Selection Framework for Automatic Report Generation
Changhun Hyun, Chan Hur, Hyeyoung Park, Multimedia Tools and Applications, 2022 – SCIE (Q1)
Domestic Publications
-
Improving text-video retrieval performance using video features combined with generation-based caption information
Chan Hur, Dong-hun Lee, Sang-hyo Park, Hyeyoung Park, KIISE Transactions on Computing Practices (KCI journal), 2024
-
Feature Vector Combination on Joint Embedding Space using Captions for Text Video Retrieval (Best paper award)
Chan Hur, Dong-hun Lee, Sang-hyo Park, Hyeyoung Park, Korea Computer Congress 2023 (KCC 2023)
-
Deep learning-based Lightweight Model for Carbon-Reduction Activity Image Classification
Hojun Song, Yunhee Koo, Sehyun Park, Jeoungwon Cha, Youngjae Lee, Chan Hur, Hyeyoung Park, Journal of Embedded Systems and Applications (KCI journal), 2022
-
A Study on the Alternative Method of Video Characteristics Using Captioning in Text-Video Retrieval Model
Dong-hun Lee, Chan Hur, Hyeyoung Park, Sang-hyo Park, Journal of Embedded Systems and Applications (KCI journal), 2022
-
A study on Video-text Retrieval model using Caption Information
Dong-hun Lee, Chan Hur, Hyeyoung Park, Sang-hyo Park, Korea Artificial Intelligence Conference 2022
Patents
- (등록) 전자 장치 및 그의 이미지를 추천하는 방법 – (2025.05)
- (출원) 언어 생성모델을 이용한 대화형 이미지 추천 시스템 – (2023.06)
- (출원) 텍스트 기반 비디오 검색 장치 및 그 비디오 검색 방법 – (2025.05)
Awards
- Best graduate Ph.D Student Award – Kyungpook National University Computer Science and Engineering, 2026
- Best Paper Award LSTM 기반 온실 환경 예측 및 제어 시스템 최적화 – ICT 대학생 논문 경진대회, 2024
- Best Paper Award Feature Vector Combination on Joint Embedding Space using Captions for Text Video Retrieval – Korea Computer Congress, 2023
Lectures
- Deep Learning and Machine Learning with Python – Kyungpook National University IT Education Center (경북대학교 IT 교육센터) (2023–2025)
- Introduction of Generative AI and Applications – Kyungpook National University IT Education Center (경북대학교 IT 교육센터) (2024–2025)
- Machine Learning – Korea National Open University (한국방송통신대학교) (2023–2025)
Powered by Jekyll and Minimal Light theme.