activity
20162023
most citedLGViT: Dynamic Early Exiting for Accelerating Vision Transformer

31 citations · 57 across the 5 of their papers we have counts for

collaborators
Showing 2016 · cs.CVShow all

1 paper · 2 filters

cs.CV2016

Co-occurrence Feature Learning for Skeleton based Action Recognition using Regularized Deep LSTM Networks

Wentao Zhu, Cuiling Lan, Junliang Xing +4

Skeleton based action recognition distinguishes human actions using the trajectories of skeleton joints, which provide a very good representation for describing actions. Considerin…