公开(公告)号：US11971956B1

公开(公告)日：2024-04-30

申请号：US17393150

申请日：2021-08-03

Applicant: Amazon Technologies, Inc.

Inventor： Fanyi Xiao ,  Joseph P. Tighe ,  Davide Modolo

IPC: G06F18/214 ,  G06F18/21 ,  G06N3/08 ,  G06T5/00 ,  G06T5/50 ,  G06V20/40

CPC classification number: G06F18/2148 ,  G06F18/2193 ,  G06N3/08 ,  G06T5/002 ,  G06T5/50 ,  G06V20/41 ,  G06T2207/10016 ,  G06T2207/20084

Abstract: Techniques for training a visual neural network are described. In particular, the training of the visual neural network may be performed using one or more contrastive learning loss functions including one or more of a visual-to-visual contrastive learning function using the visual neural network on positive and negative video clips according to a first loss function, a secondary-to-secondary contrastive learning a secondary neural network on secondary positive and negative information generated from the positive and negative video clips, and a secondary-to-visual contrastive learning according to a third loss function using the visual neural network on positive and negative video clips and using the secondary neural network secondary positive and negative information generated from the positive and negative video clips.