Two-Stream Gated Fusion ConvNets for Action Recognition.
Jiagang ZhuWei ZouZheng ZhuPublished in: ICPR (2018)
Keyphrases
- action recognition
- feed forward
- bag of words
- computer vision
- human actions
- data streams
- activity recognition
- action classification
- human detection
- artificial neural networks
- spatial temporal
- back propagation
- multi sensor
- bag of features
- body parts
- human pose
- recognizing human actions
- human activities
- neural network
- static images
- view invariant
- video dataset
- recognizing actions
- view invariant action recognition
- stream processing
- max margin
- action detection
- video sequences
- independent subspace analysis
- space time interest points
- machine learning