Download Decoupling GCN with DropGraph Module for Skeleton-Based Action Recognition

Queue processing for download document In skeleton-based action recognition, graph convolutional networks (GCNs) have achieved remarkable success. Nevertheless, how to efficiently model the spatial-temporal skeleton graph without introducing extra computation burden is a challenging problem fo

You can start your download in 30 seconds

Recommend Documents
Conversational Function Module for Disaster Information with Speech Recognition

162 53 49MB

DRGCN: Deep Relation GCN for Group Activity Recognition

201 86 87MB

Human Action Recognition with Depth Cameras

166 70 3MB

XwiseNet: action recognition with Xwise separable convolutions

151 105 745KB

Temporal Distinct Representation Learning for Action Recognition

216 74 163MB

Video Action Recognition

192 90 11MB

Human Action Recognition Without Human

189 5 161MB

Few-Shot Action Recognition with Permutation-Invariant Attention

243 104 166MB

Skeleton-Based Action Recognition with Dense Spatial Temporal Graph Network

164 4 73MB

Decoupling

180 2 3MB

Skeleton-Based Human Action Recognition with Profile Hidden Markov Models

183 102 895KB

Video sketch: A middle-level representation for action recognition

203 94 5MB