Figure 4.
Accurate frame-wise categorizations of various user-defined behaviors by different Categorizers
(A–C) Bars showing the test metrics (overall accuracy, precisions, recalls, and F1 scores) for LarvaN (A), RatA (B), and MouseH (C) in video analysis. Seven videos for larvae (10 larvae per video), 10 videos for rats (one rat per video), and two videos for mice (one mouse per video) that were not used for generating the training datasets were used to generate the testing data (animations and their paired pattern images). A total of 2,162 pairs (for larvae), 4,828 pairs (rats), and 12,653 pairs (mice) of data were randomly selected and then were sorted by experimenters into different folders under user-defined behavioral names (building ground truth testing datasets).