Integrating vertex and edge features with Graph Convolutional Networks for skeleton-based action recognition.
Kai LiuLei GaoNaimul Mefraz KhanLin QiLing GuanPublished in: Neurocomputing (2021)
Keyphrases
- action recognition
- average degree
- edge weights
- betweenness centrality
- human actions
- directed graph
- undirected graph
- bag of words
- computer vision
- complex networks
- human detection
- activity recognition
- action classification
- body parts
- recognizing human actions
- weighted graph
- spatial temporal
- network structure
- static images
- recognizing actions
- recognition of human actions
- space time interest points
- view invariant
- independent subspace analysis
- depth sensors
- action primitives
- view invariant action recognition
- action detection
- human pose
- bag of features
- graph databases
- human activities
- object detection