Spatio-temporal deformable 3D ConvNets with attention for action recognition.
Jun LiXianglong LiuMingyuan ZhangDeqing WangPublished in: Pattern Recognit. (2020)
Keyphrases
- action recognition
- human actions
- spatio temporal
- feed forward
- spatial temporal
- action recognition in videos
- spatio temporal interest points
- view invariant
- deformable part models
- bag of words
- recognition of human actions
- action classification
- activity recognition
- computer vision
- human detection
- spatial and temporal
- body parts
- human activities
- independent subspace analysis
- action primitives
- action detection
- viewpoint
- motion features
- bag of features
- neural network
- recognizing actions
- motion recognition
- machine learning
- human pose
- motion patterns
- human motion
- artificial neural networks
- image sequences
- depth cameras
- static images
- depth sensors
- motion history images
- back propagation
- fuzzy logic
- view invariant action recognition