Spatiotemporal Pyramid Pooling in 3D Convolutional Neural Networks for Action Recognition.
Cheng ChengPin LvBing SuPublished in: ICIP (2018)
Keyphrases
- action recognition
- convolutional neural networks
- convolutional network
- bag of words
- human actions
- activity recognition
- multiresolution
- human detection
- computer vision
- space time
- spatial and temporal
- spatial temporal
- body parts
- image representation
- action classification
- recognizing human actions
- coarse to fine
- multiscale
- histogram of oriented gradients
- depth sensors
- scale space
- human activities
- spatio temporal
- moving objects
- human pose
- static images
- independent subspace analysis
- recognition of human actions
- recognizing actions
- input image
- action detection
- video dataset
- action primitives
- bag of features
- multi view
- low level
- action recognition in videos
- optical flow
- face recognition