Skip to main content
. 2021 May 19;16(7):1111–1119. doi: 10.1007/s11548-021-02388-z

Fig. 7.

Fig. 7

Step recognition on complete videos in Bypass40 for quality assessment. The figure shows best (top) and worst (bottom) performance of our model. The 44 distinct steps are mapped to the same 20 categorical colormap