Reproduce “Markerless tracking of user-defined features with deep 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
Alexander Mathis, Pranav Mamidanna, Taiga Abe, Kevin M. Cury, Venkatesh N. Murthy, Mackenzie W. Mathis, Matthias Bethge
DeepLabCut adapts an ImageNet-pretrained vision network to predict user-selected body points from manually labeled video frames. In mouse odor-trail videos, about 100 labeled frames yielded average test root-mean-square error below 5 pixels for the snout and tail base. On tested random splits, an 80% training set reached same-annotator repeat-label variability; results do not establish performance in other settings.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.