Reproduce “Disentangling Spatial and Temporal Learning for Efficient Image-to-Video Transfer Learning” 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
Zhiwu Qing, Shiwei Zhang, Ziyuan Huang, Yingya Zhang, Changxin Gao, Deli Zhao, Nong Sang
DiST combines frozen CLIP image features with motion features from a lightweight temporal encoder and an integration branch that exchanges information between them. It trains without back-propagating through the image backbone. On Something-Something V2, its CLIP ViT-B/16 setup reaches 70.9% top-1, versus EVL’s 62.4%, on that benchmark and setup. This supports the design in tested settings, not every video task.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.