Extended Data Fig. 3: Identification of typical vs difficult frames. | Nature Machine Intelligence

Extended Data Fig. 3: Identification of typical vs difficult frames.

From: Deep-learning-based identification, tracking, pose estimation and behaviour classification of interacting primates and mice in complex environments

Extended Data Fig. 3

a) Examples of very difficult frames, which are also beyond human single-frame recognition, are excluded for the ‘typical’ frame evaluation. b) Example frames used for the ‘typical’ frame analysis. c) Identification performance is significantly higher on ‘typical’ frames than on all frames. All data is represented by mean, showing all points.

Back to article page