Reproduce “Dynamics are Important for the Recognition of Equine Pain in 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
Sofia Broomé, Karina Bech Gleerup, Pia Haubro Andersen, Hedvig Kjellström
The authors develop a video method for classifying equine pain by processing appearance and motion together in recurrent convolutional networks. One model uses parallel RGB and optical-flow streams, whose features are fused. Across six horses, two-stream C-LSTM-2 achieves 73.5 ± 18.3% F1 and 75.4 ± 14.1% accuracy, but labels reflect controlled pain induction, not clinical diagnosis.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.