Timezone: »

 
Videogenic: Video Highlights via Photogenic Moments
David Chuan-En Lin · Fabian Caba · Joon-Young Lee · Oliver Wang · Nikolas Martelaro

@
in Workshop on Machine Learning for Creativity and Design »

This paper investigates the challenge of extracting highlight moments from videos. To perform this task, a system needs to understand what constitutes a highlight for arbitrary video domains while at the same time being able to scale across different domains. Our key insight is that photographs taken by photographers tend to capture the most remarkable or photogenic moments of an activity. Drawing on this insight, we present Videogenic, a system capable of creating domain-specific highlight videos for a wide range of domains. In a human evaluation study (N=50), we show that a high-quality photograph collection combined with CLIP-based retrieval (which uses a neural network with semantic knowledge of images) can serve as an excellent prior for finding video highlights. In a within-subjects expert study (N=12), we demonstrate the usefulness of Videogenic in helping video editors create highlight videos with lighter workload, shorter task completion time, and better usability.

[ Poster] 

Author Information

David Chuan-En Lin (Carnegie Mellon University)

David's research focus is in Designer-AI Interaction. He supports designers by (1) building novel ML-infused design tools and (2) investigating how such tools augment design processes.

Fabian Caba (Adobe Research)
Joon-Young Lee (Adobe Research)
Oliver Wang (Adobe Research)
Nikolas Martelaro (Carnegie Mellon University)

More from the Same Authors