SCaTNet: A Novel Self-supervised Contrastive Framework with Spatial-Channel Attention and Temporal Transformer for Few-Shot Action Recognition.
Zanxi RuanYingmei WeiYanming GuoYuxiang XieYifei YuanPublished in: ACAI (2023)
Keyphrases
- action recognition
- spatial temporal
- spatio temporal
- video dataset
- bag of words
- action classification
- spatial and temporal
- computer vision
- human actions
- three dimensional
- static images
- human detection
- activity recognition
- spatial information
- video sequences
- body parts
- bag of features
- human pose
- space time
- motion history images