About

Hello, I am Jeong-hun Hong, a master’s student researching multimodal learning.

Kyungpook National University
B.S. in Computer Science & Engineering
Mar. 2017 ~ Aug. 2023
Kyungpook National University
M.S. in Computer Science & Engineering
Sep. 2023 ~
Advisor: Sang-hyo Park

Multimodal Learning
- Text-Video Retrieval
- 3D Scene Graph Generation
- Captioning
Generative Model
- Diffusion-based Method
Knowledge Distillation

(First Author)

Chan Hur, Jeong-hun Hong, Dong-hun Lee, Dabin Kang, Semin Myeong, Sang-hyo Park, Hyeyoung Park, “Narrating the Video: Boosting Text-Video Retrieval via Comprehensive Utilization of Frame-Level Captions”, Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (CVPR), 2025
Semin Myeong, Dabin Kang, Chae-yeong Song, Jeong-hun Hong, Sang-hyo Park, “A study on the Use of a Text-to-image Generative Model to Generate Consistent Story Illustrations”, JOURNAL OF BROADCAST ENGINEERING, 29(6), 1043-1055, 2024
Dong-hun Lee, Jeong-hun Hong, Hui-yan Yu, Dabin Kang, Sang-hyo Park, “Exploring the interactivity of the MPEG SD data format with academic dataset”, 한국방송미디어공학회 학술발표대회 논문집, 제주, 2024
Semin Myeong, Dabin Kang, Chae-yeong Song, Jeong-hun Hong, Sang-hyo Park, “A Study on Coherent Image Generation Reflecting Story Genres Using Text-based Image Generation Models”, 한국방송미디어공학회 학술발표대회 논문집, 제주, 2024
Jeong-hun Hong, Dong-hun Lee, Han-gyul Baek, Byungjun Bae, Sang-hyo Park, “Image captioning network for disaster dataset based on transfer learning and disaster convolution block”, in The Journal of Korean Institute of Communications and Information Sciences (KICS), 2023