Minsun (Sunny) Kim

I am a second-year master’s student at KAIST Graduate School of Culture Technology, specializing in Human-Computer Interaction and Computer Vision, advised by Prof. Junyong Noh at the Visual Media Lab.

📚 Research Interests

Human-Computer Interaction, Computer Vision, Computer Grapics
Keywords: Content Technology, Video Editing & Generation

🌟 My Vision

The emergence of AI video generation tools like Sora and Veo has made it possible for anyone to create any video clip they envision. Visualizing ideas is no longer the bottleneck in creation.

I believe what becomes critical in this era is how we edit and direct these clips to craft a cohesive story. My research focuses on developing advanced video editing technologies that enable creators to express their narratives more seamlessly and effectively in this new creative environment.

News

Jan 15, 2026	📄 Our paper has been conditionally accepted to CHI 2026! See you in Barcelona, Spain 🇪🇸
Jan 02, 2026	I’ll be joining Adobe Research as a research intern advised by Joon-Young Lee this summer ☀️ See you in San Jose! 🌴
Apr 25, 2025	📢🌸 Attending CHI 2025 in Yokohama, Japan! 🇯🇵✨ Excited to meet everyone and share our research! 🎉
Jan 16, 2025	📄 My first international conference paper has been conditionally accepted to CHI 2025!

Selected publications

HCI

ComVi: Context-Aware Optimized Comment Display in Video Playback

Minsun Kim, Dawon Lee*, and Junyong Noh^*

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

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

Minsun Kim, Dawon Lee*, and Junyong Noh^*

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

Abs DOI PDF Video Website

A highlight is a short edit of the original video that includes the most engaging moments. Given the rigid timing of TV commercial slots and length limits of social media uploads, generating highlights of specific lengths is crucial. Previous research on automatic highlight generation often overlooked the control over the duration of the final video, producing highlights of arbitrary lengths. We propose a novel system that automatically generates highlights of any user-specified length. Our system leverages Most Replayed Data (MRD), which identifies how frequently a video has been watched over time, to gauge the most engaging parts. It then optimizes the final editing path by adjusting internal shot durations. We evaluated the quality of our system’s outputs through two user studies, including a comparison with highlights created by human editors. Results show that our system can automatically produce highlights that are indistinguishable from those created by humans in viewing experience.