Semi-Coupled Two-Stream Fusion ConvNets for Action Recognition at Extremely Low Resolutions.
Jiawei ChenJonathan WuJanusz KonradPrakash IshwarPublished in: WACV (2017)
Keyphrases
- action recognition
- feed forward
- human actions
- computer vision
- bag of words
- human detection
- activity recognition
- action classification
- data streams
- spatial temporal
- recognition of human actions
- bag of features
- back propagation
- recognizing human actions
- body parts
- video dataset
- independent subspace analysis
- static images
- artificial neural networks
- multi sensor
- human activities
- depth cameras
- view invariant
- action detection
- depth sensors
- neural network
- human pose
- multi view
- text classification
- high resolution