Skip to main content
. 2023 Mar 22;18(9):1665–1672. doi: 10.1007/s11548-023-02864-8

Fig. 1.

Fig. 1

Pictographical representation of TRandAugment. A video is segmented into T clips, and a random augmentation ti, sampled from a list of transforms τ, is applied to clip i. The augmented clips are merged back to form a new video which is passed as input while training an end-to-end CNN+TCN network that predicts phases or steps