Extended Data Fig. 8: Comparison with R3D.
From: Unsupervised behaviour analysis and magnification (uBAM) using deep learning
Besides JAABA and DLC we also compare our method with R3D which is another non-parametric model, very popular for video classification. We extract R3D features and evaluate the representation using the same protocol as our method. Our model is more suited to behaviour analysis. More information regarding the evaluation protocol can be found in the Methods section of the main manuscript. (Details in Supplementary).
