Chained Multi-stream Networks Exploiting Pose, Motion, and Appearance for Action Classification and Detection.
Mohammadreza ZolfaghariGabriel L. OliveiraNima SedaghatThomas BroxPublished in: ICCV (2017)
Keyphrases
- action classification
- static images
- multi stream
- loop closure
- human pose
- action recognition
- human detection
- human actions
- human motion
- pose estimation
- object detection
- hidden markov models
- human body
- image sequences
- audio visual
- partial occlusion
- appearance model
- object segmentation
- video frames
- temporal resolution
- bag of words
- visual data
- global features
- max margin