Seungho Shin

Currently, I am a research intern and an incoming Ph.D. student at the Machine Learning and Intelligence Lab (MLILAB) at KAIST. Before joining KAIST, I received my Master’s degree from the Visual Artificial Intelligence Lab (VAILAB) at Kyung Hee University in 2025, advised by Prof. Jung Uk Kim. I also worked with Prof. Gyeong-Moon Park through collaborative research. I received my B.S. in Software Convergence from Kyung Hee University in 2024.

My work aims to address key challenges in multimodal learning and data-centric AI. Specifically, I focus on building user-friendly and real-world applicable multimodal systems.

If you are interested in my research or collaboration, feel free to reach out :)

Seungho Shin

News

🎉 Admitted to the Ph.D. program at KAIST, joining MLILAB!

🎉 Received my M.S. degree from Kyung Hee University!

🎉 One paper accepted to IEEE TMM.

🎉 One paper accepted to AAAI 2025.

Publications

*Equal contribution  Corresponding author

International Conference

Multispectral Pedestrian Detection with Sparsely Annotated Label

Multispectral Pedestrian Detection with Sparsely Annotated Label

AAAI 2025

Chan Lee*, Seungho Shin*, Gyeong-Moon Park†, Jung Uk Kim†

*Equal contribution, †Corresponding author

International Journal

SSMPD: Semi-Supervised Learning for Multispectral Pedestrian Detection

SSMPD: Semi-Supervised Learning for Multispectral Pedestrian Detection

IEEE TMM

Seungho Shin*, Chan Lee*, Gyeong-Moon Park†, Jung Uk Kim†

*Equal contribution, †Corresponding author

IEEE Transactions on Multimedia, Vol. 28, pp. 1806–1819, 2026 (IF 9.7, JCR Top 2.7%)

Preprint

User-Controllable Dense Video Captioning: A Large-Scale Benchmark and Framework

User-Controllable Dense Video Captioning: A Large-Scale Benchmark and Framework

Preprint

Seungho Shin*, Sung Jin Um*, Gyeong-Moon Park†, Jung Uk Kim†

*Equal contribution, †Corresponding author

CollabVR: Collaborative Video Reasoning with Vision-Language and Video Generation Models

CollabVR: Collaborative Video Reasoning with Vision-Language and Video Generation Models

Preprint

Joowon Kim*, Seungho Shin*, Joonhyung Park, Eunho Yang†

*Equal contribution, †Corresponding author

Education

Kyung Hee University | M.S. in Artificial Intelligence

Visual Artificial Intelligence Lab (VAILAB), advised by Prof. Jung Uk Kim

Kyung Hee University | B.S. in Software Convergence

Honors & Awards

KHUGGLE 2023 (AI Factory, Kyung Hee University, IITP), 10-Shot Image Generation — 3rd place

Teaching

Teaching Assistant

  • Software Engineering (Spring 2025)
  • Web/Python Programming (Fall 2024)
  • Artificial Intelligence and Ethics (Spring 2024)

Academic Services

Conference Reviewer

  • NeurIPS 2026

Journal Reviewer

  • IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)