Minsun Kim

sunnykimhappy@gmail.com

I am a researcher working on video editing and content technology, having recently completed my master's at the KAIST Graduate School of Culture Technology, Visual Media Lab, advised by Prof. Junyong Noh. I'm currently interning at Adobe in San Jose, working on video repurposing with VLLMs under Dr. Joon-Young Lee.

Research Interests

  • Human-Computer Interaction, Computer Vision, Computer Graphics
  • More specifically: Content Technology, Video Editing & Generation
  • Recently exploring:

My Vision

With Sora, Veo, and the wave of generative video models, anyone can now conjure a clip from imagination. Producing footage is no longer the hard part. What I find genuinely interesting — and increasingly critical — is everything that happens after the clips exist: the cutting, the pacing, the structuring of fragments into coherent narratives that hold together and are worth someone's time.

My goal is to research the technologies — be it Human-Computer Interaction, Computer Vision, or Computer Graphics — that make this craft of editing and directing more accessible, more efficient, and ultimately better. I want to live in a world with more high-quality content in it, and I'd like to help build the tools that get us there.

News

Jan 2026 Our paper has been conditionally accepted to CHI 2026! See you in Barcelona 🇪🇸
Jan 2026 I'll be joining Adobe Research as a research intern advised by Joon-Young Lee this summer ☀️ See you in San Jose! 🌴
Apr 2025 Attending CHI 2025 in Yokohama, Japan! 🇯🇵
Jan 2025 First paper conditionally accepted to CHI 2025!

Publications

ComVi: Context-Aware Optimized Comment Display preview
HCI Video Editing Comments Visualization Video Interfaces Contextual Alignment Viewing Experience

ComVi: Context-Aware Optimized Comment Display in Video Playback

Minsun Kim, Dawon Lee*, Junyong Noh* (*Co-corresponding authors)

Proceedings of the CHI Conference on Human Factors in Computing Systems, 2026

Generating Highlight Videos preview
HCI Video Editing Highlight Generation Video Summarization Image Processing Most Replayed Data

Generating Highlight Videos of a User-specified Length using Most Replayed Data

Minsun Kim, Dawon Lee*, Junyong Noh* (*Co-corresponding authors)

Proceedings of the CHI Conference on Human Factors in Computing Systems, 2025

Video classifier with adaptive blur network preview
Computer Vision Video Classifier

Video Classifier with Adaptive Blur Network to Determine Horizontally Extrapolatable Video Content

Minsun Kim, Changwook Seo, Hyun Ho Yun, Junyong Noh

Best Paper Award Journal of the Korea Computer Graphics Society, Vol. 30, No. 3, pp. 99–107, 2024