Spatio-Temporal Image Representation of 3D Skeletal Movements for View-Invariant Action Recognition with Deep Convolutional Neural Networks.
Huy-Hieu PhamHoussam SalmaneLouahdi KhoudourAlain CrouzilPablo ZegersSergio A. VelastinPublished in: Sensors (2019)
Keyphrases
- image representation
- convolutional neural networks
- view invariant action recognition
- spatio temporal
- action recognition
- human motion
- multiscale
- image classification
- image content
- cross ratios
- object recognition
- image retrieval
- feature space
- visual words
- space time
- sparse coding
- bag of words
- image features
- sparse representation
- image sequences
- moving objects
- computer vision
- multiresolution
- human body
- bag of features
- cross ratio
- projective invariants
- image processing