Human Action Recognition Based on Multi-scale Feature Maps from Depth Video Sequences.
Chang LiQian HuangXing LiQianhan WuPublished in: CoRR (2021)
Keyphrases
- action recognition
- human actions
- feature maps
- multiscale
- motion capture data
- video sequences
- depth sensors
- body parts
- human activities
- space time interest points
- activity recognition
- computer vision
- action classification
- human object interactions
- motion history images
- recognizing human actions
- image processing
- human motion
- self organizing maps
- saliency map
- video frames
- kernel function
- image sequences
- three dimensional
- visual features
- image representation
- depth information
- depth data
- feature space