Deep Neural Networks Using Residual Fast-Slow Refined Highway and Global Atomic Spatial Attention for Action Recognition and Detection.
Manh-Hung HaOscal Tzyh-Chiang ChenPublished in: IEEE Access (2021)
Keyphrases
- action recognition
- human detection
- spatial temporal
- neural network
- bag of words
- human actions
- body parts
- computer vision
- activity recognition
- action classification
- recognition of human actions
- static images
- depth sensors
- spatial information
- object detection
- spatio temporal
- spatial and temporal
- recognizing human actions
- action primitives
- view invariant
- independent subspace analysis
- recognizing actions
- view invariant action recognition
- video dataset
- bag of features
- event detection
- temporal resolution
- human activity recognition
- human pose
- human activities
- space time