Reproduce “Video2GIF: Automatic Generation of Animated GIFs from Video” 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
Michael Gygli, Yale Song, Liangliang Cao
Video2GIF ranks candidate video segments by GIF suitability, not finished GIFs. It aligns user-created GIFs with source videos, labels overlapping segments as positives, and trains a shared neural ranker to compare segments within each video. On 357 held-out videos, its adaptive-Huber-plus-context model reaches 44.19% nMSD and 16.18% mAP, outperforming rankSVM on nMSD but only slightly on mAP.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.