FPGA-QHAR: Throughput-Optimized for Quantized Human Action Recognition on The Edge.
Azzam AlhussainMingjie LinPublished in: CoRR (2023)
Keyphrases
- action recognition
- human movements
- static images
- human activities
- human actions
- spatio temporal interest points
- motion history images
- computer vision
- spatial temporal
- motion capture data
- bag of words
- human detection
- recognizing human actions
- recognition of human actions
- activity recognition
- body parts
- action classification
- human object interactions
- bag of features
- action detection
- recognizing actions
- independent subspace analysis
- view invariant
- video dataset
- edge information
- depth sensors
- signal processing
- view invariant action recognition
- action recognition in videos
- image processing