A Unified Deep Framework for Hand Pose Estimation and Dynamic Hand Action Recognition from First-Person RGB Videos.
Viet-Duc LeVan-Nam HoangTien-Thanh NguyenVan-Hung LeThanh-Hai TranHai VuThi-Lan LePublished in: MAPR (2021)
Keyphrases
- action recognition
- video dataset
- human actions
- action classification
- recognition of human actions
- recognizing human actions
- human activities
- motion features
- static images
- recognizing actions
- body parts
- human detection
- action detection
- computer vision
- unified model
- max margin
- depth sensors
- space time interest points
- spatial temporal
- bag of words
- view invariant
- motion history images
- video data
- feature vectors
- ucf sports
- video sequences