MSST-RT: Multi-Stream Spatial-Temporal Relative Transformer for Skeleton-Based Action Recognition.
Yan SunYixin ShenLiyan MaPublished in: Sensors (2021)
Keyphrases
- spatial temporal
- action recognition
- multi stream
- human actions
- audio visual
- bag of words
- computer vision
- activity recognition
- hidden markov models
- human activities
- bag of features
- visual information
- spatio temporal
- space time interest points
- facial expressions
- search engine
- event detection
- video database
- multiscale
- image sequences