I received my M.S. from the VAI Lab at the Graduate School of AI, Kyung Hee University, where Prof. Jung Uk Kim was my advisor.
I also received a B.S. in Software Convergence from the Kyung Hee University.

My work aims to address key challenges in multimodal learning and data-centric AI.

In particular, I explore user-controllable video captions using large vision-language models (MLLMs + LLMs), and how to design robust detection systems under incomplete labels in multispectral data.

🔥 News

2025.08: 🎉🎉 Received M.S. degree from Kyung Hee University!
2025.05: 🎉🎉 One paper got accepted to IEEE TMM
2024.12: 🎉🎉 One paper got accepted to AAAI 2025

📝 Publications

International Conference

• Multispectral Pedestrian Detection with Sparsely Annotated Label
  

  Chan Lee*, Seungho Shin*, Gyeong-Moon Park, Jung Uk Kim (*Equal contribution)
  The 39th Annual AAAI Conference on Artificial Intelligence (AAAI) 2025, [paper]

• UC-DVC: A Unified Framework and Dataset for User-Controllable Dense Video Captioning
  

  Seungho Shin*, Sung Jin Um*, Gyeong-Moon Park, Jung Uk Kim (*Equal contribution)
  To be submitted to ICLR 2026

International Journal

• SSMPD: Semi-Supervised Learning for Multispectral Pedestrian Detection
  

  Seungho Shin*, Chan Lee*, Gyeong-Moon Park, Jung Uk Kim (*Equal contribution)
  IEEE Transactions on Multimedia (TMM) [IF = 9.7, JCR Top 2.7% ] (Accepted)

🏆 Honors and Awards

• 2023.12: KHUGGLE 2023 (from AI Factory, Kyung Hee University, IITP), 10-Shot Image Generation, (3rd place)

📖 Educations

• 2024.03 - 2025.08, M.S. in Artificial Intelligence, Kyung Hee University.
• 2018.03 - 2024.02, B.S. in Software Convergence, Kyung Hee University.

🧑‍🏫 Teaching

Teaching Assistant

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

🧾 Academic Activities

Reviewer for

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