. Author manuscript; available in PMC: 2022 May 11.

Published in final edited form as: Proc IEEE Int Conf Comput Vis. 2021 Oct;2021:13557–13567. doi: 10.1109/iccv48922.2021.01332

Table 4:

Quantitative analysis on Kinetics-400 dataset. The performance gain is defined as the disparity of the top-1 accuracy between VidTr network and that of I3D.

Top 5 (+)	Acc. gain	Top 5 (−)	Acc. gain

making a cake	+26.0%	shaking head	−21.7%
catching fish	+21.2%	dunking basketball	−20.8%
catching baseball	+20.8%	lunge	−19.9%
stretching arm	+19.1%	playing guitar	−19.9%
spraying	+18.0 %	tap dancing	−16.3%

(a) Top 5 classes that VidTr works better than I3D.		(b) Top 5 classes that I3D works better than VidTr.