Multi-stage Factorized Spatio-Temporal Representation for RGB-D Action and Gesture Recognition.
Yujun MaBenjia ZhouRuili WangPichao WangPublished in: ACM Multimedia (2023)
Keyphrases
- multistage
- gesture recognition
- view invariant
- spatio temporal
- human computer interaction
- kinect sensor
- depth data
- depth cameras
- single stage
- sign language recognition
- stochastic optimization
- dynamic programming
- hidden markov models
- human actions
- hand gestures
- stochastic programming
- production system
- lot sizing
- hand gesture recognition
- hand motion
- human machine interface
- human robot interaction
- skin detection
- attack detection
- sign language
- assembly systems
- machine learning
- lot streaming
- hand tracking
- action recognition
- image sequences
- artificial intelligence
- representation scheme
- pose estimation
- software engineering
- knowledge base