Reproduce “State-Change Learning for Prediction of Future Events in Endoscopic Videos” 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
Saurav Sharma, Chinedu Innocent Nwoye, Didier Mutter, Nicolas Padoy
SurgFUTR predicts future surgical events by learning whether actions persist, end, begin, or remain absent. Its teacher uses current and future clips during training, while its student predicts state changes from current video alone. On CholecT50, SurgFUTR-TS reports 50.29% mAP, 43.91% F1, and 45.61% accuracy across three horizons, but results vary by task and do not establish clinical benefit.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.