Reproduce “Multimodal Concert Video Editing: System Design and Exploratory Evaluation” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Lennart Schiweck, Adrian Kempf, Michelle Retig, Moritz Feucht, Tim Mangliers, Benjamin Himpel
The authors present a system that selects cut times and camera views for concert edits. It scores views using audio roles and video visibility and sharpness, then samples a camera for each interval. In one concert, three experts rated predicted-score selection less favorably than random selection: mean grades were 4.00 and 2.67, respectively. This pilot does not show random editing is generally better.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.