Hi there π
I am a third year Ph.D. student at the
Human-Computer Interaction Institute
in the School of Computer Science
at Carnegie Mellon University,
where I am advised by Professor Nik Martelaro.
I completed my Bachelor's degree in Computer Science with First Class Honors and
a full scholarship from HKUST, where I was advised
by Professor Xiaojuan Ma and
Professor Kwang-Ting Cheng.
I also spent two wonderful internships at Adobe Research,
where I was mentored by Fabian Caba Heilbron,
Oliver Wang, and
Joon-Young Lee, and
Runway, where I was mentored by
Anastasis Germanidis and
CristΓ³bal Valenzuela.
During my free time, I enjoy filming travel videos and listening to Avicii music.
Research Interests
My research interest is in building AI-assisted design tools to
augment human creativity. Specifically, I am passionate about exploring how we can
harness the knowledge within Large Language Models (LLMs) to support creative tasks.
Currently, I am building a variety of LLM-infused video editing tools to support video
editors in various editing tasks, such as adding sounds to video, uncovering highlight
moments, organizing video assets, and more.
Publications
VideoMap: Video Editing in Latent Space
NeurIPS 2022 Workshop on Machine Learning for Creativity and Design
David Chuan-En Lin, Fabian Caba Heilbron, Joon-Young Lee, Oliver Wang, and Nikolas Martelaro
VideoMap is a proof-of-concept interface for video editing in the latent space.
π Preliminary websiteπ Preprint
Videogenic: Video Highlights via Photogenic Moments
NeurIPS 2022 Workshop on Machine Learning for Creativity and Design
David Chuan-En Lin, Fabian Caba Heilbron, Joon-Young Lee, Oliver Wang, and Nikolas Martelaro
Videogenic is a system for uncovering highlight moments within videos.
π Preliminary websiteπ Preprint
Soundify: Matching Sound Effects to Video
NeurIPS 2021 Workshop on Machine Learning for Creativity and Design (Oral top 6%)
David Chuan-En Lin, Anastasis Germanidis, CristΓ³bal Valenzuela, Yining Shi, and Nikolas Martelaro
Soundify is a system for matching spatial sound effects to video.
π Websiteπ Paperπ¬ Visualizationπ¬ Resultsπ¬ Demoπ Talk
Learning Personal Style from Few Examples
DIS 2021
David Chuan-En Lin and Nikolas Martelaro
PseudoClient is a system for modeling personal graphic design style based on a handful of examples.
π Websiteπ Paperπ¬ Videoπ Talk
SeqDynamics: Visual Analytics for Evaluating Online Problem-solving Dynamics
EuroVis 2020
Meng Xia, Min Xu, Chuan-En Lin, Ta Ying Cheng, Huamin Qu, and Xiaojuan Ma
SeqDynamics is a visualization tool for analyzing student problem-solving with multi-scale views.
π Paper
ARchitect: Building Interactive Virtual Experiences from Physical Affordances by Bringing Human-in-the-Loop
CHI 2020
Chuan-En Lin*, Ta Ying Cheng*, and Xiaojuan Ma
ARchitect is a workflow for mapping physical objects to virtual proxies with matching interaction affordances.
π Websiteπ Paperπ¬ Video
* equal contribution
Learning to Film from Professional Human Motion Videos
CVPR 2019
Chong Huang, Chuan-En Lin, Zhenyu Yang, Yan Kong, Peng Chen, Xin Yang, and Kwang-Ting Cheng
An imitation learning system for autonomous drone filming.
π Paperπ¬ Video