| CARVIEW |
Senior Research Scientist
Adobe Research
One Broadway, Cambridge MA 02142
vshin [at] adobe [dot] com
I am a senior research scientist at
Adobe Research.
I build systems that combine algorithms with novel user interactions made possible by those algorithms.
My primary focus is audiovisual media—especially video. I'm passionate about helping people create compelling video stories, communicate more effectively through video, and engage with video content in smarter, more meaningful ways.
I received my PhD in Computer Science from MIT, where I was advised by
Fredo Durand in the
Computer Graphics Lab.
Before joining MIT, I completed my B.S. in Computer Science at Princeton University,
working with Thomas Funkhouser.
Publications
2025
|
VideoDiff: Human-AI Video Co-Creation with Alternatives
M. Huh, D. Li, K. Pimmel, V. Shin, A. Pavel, M. Dontcheva
CHI 2025
|
|
Compositional Structures as Substrates for Human-AI Co-creation Environment: A Design Approach and A Case Study
Y. Cao, Y. Huang, A. Truong, V. Shin, H. Xia
CHI 2025
|
2023
|
SoundToons: Exemplar-Based Authoring of Interactive Audio-Driven Animation Sprites.
T. Chong, D. Aneja, T. Igarashi, V.Shin
ACM IUI 2023
|
|
Automated Conversion of Music Videos into Lyric Videos.
J. Ma, A. Rao, L. Wei, R. Kazi, V.Shin, M. Agrawala
UIST 2023
|
2022
|
Beyond Subtitles Captioning and Visualizing Non-Speech Sounds in User Generated Videos.
O. Alonzo, V.Shin, D. Li
ASSETS 2022
|
|
CatchLive: Real-time Summarization of Live Streams with Stream Content and Interaction Data
S. Yang, J. Yim, J. Kim, V.Shin
CHI 2022
|
2021
|
Multi-level Correspondence via Graph Kernels for Editing Vector Graphics Designs
|
|
Beyond Show of Hands: Engaging Viewers via Expressive and Scalable Visual Communication in Live Streaming
[paper]
J. Chung, V.Shin, H. Xia, L. Wei, R. Kazi
CHI 2021
|
2020
|
Snapstream: Snapshot-based Interactions in Live Streaming for Visual Art
S. Yang, C. Kim V. Shin, J. Kim
Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems (CHI 2020)
|
|
Temporal Segmentation of Creative Live Streams
[pdf]
C. Fraser, J. Kim, V. Shin , J. Brandt, M. Dontcheva
Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems (CHI 2020)
|
|
Generating Audio-Visual Slideshows from Text Articles Using Word Concreteness
M. Leake, V. Shin , J. Kim, M. Agrawala
Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems (CHI 2020)
|
|
Pose2Pose: Pose Selection and Transfer for 2D Character Animation
|
2019
|
B-Script: Transcript-based B-roll Video Editing with Recommendations
B. Huber, V. Shin, B. Russel, O. Wang, G. Mysore
Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems (CHI 2019)
|
2018
|
DynamicSlide: Exploring the Design Space of Reference-based Interaction Techniques for Slide-based Lecture Videos
H. Jung, V. Shin, J. Kim
Proceedings of the 2018 Workshop on Multimedia for Accessible Human Computer Interface
|
|
On Learning Associations of Faces and Voices
[pdf]
C. Kim, V. Shin , T. Oh, A. Kaspar, M. Elgharib, W. Matusik
In Proceedings of Asian Conference on Computer Vision (ACCV 2018)
|
Past Projects
|
Project Blink: Creating the Future of AI-Powered Video Editing
[blog post][video]
Project Blink is an AI-powered, web-based video editing app that transforms video editing. By leveraging the AI's media understanding capabilities, Project Blink allows users to edit by content rather than frame-by-frame. Users can search for words, images, people, and moments in a video, then cut and paste just as they would in a text document, streamlining the video editing workflow. |
Past Intern Collaborators
Adobe Research offers an exceptional internship program for graduate students. Here are a few research interns I have been fortunate to work with.
If you are a PhD student and interested in a research internship, please send me an email with your CV and a summary of your research interests.
- Oliver Alonzo - DePaul University
- Saelyne Yang - KAIST
- John Joon Young Chung - Midjourney
- Ailie Fraser - Adobe Research
- Nora Willett - CLO Virtual Fashion