Fusing Skeletons and Texts Based on GCN-CNN for Action Recognition.
Lijuan ZhouZhihuan LiuWeicong ZhangDi FanXiaojie QianPublished in: ICDIP (2023)
Keyphrases
- action recognition
- bag of words
- human detection
- human actions
- computer vision
- action classification
- activity recognition
- spatial temporal
- video dataset
- body parts
- recognizing human actions
- static images
- human activities
- recognition of human actions
- keywords
- human pose
- bag of features
- viewpoint
- recognizing actions
- mid level
- motion features
- motion history images
- action primitives
- three dimensional