Supervised spatio-temporal kernel descriptor for human action recognition from RGB-depth videos.
Maryam Asadi-AghbolaghiShohreh KasaeiPublished in: Multim. Tools Appl. (2018)
Keyphrases
- action recognition
- human actions
- spatio temporal interest points
- spatio temporal
- action classification
- recognition of human actions
- action detection
- action recognition in videos
- depth data
- view invariant
- video database
- human motion
- activity recognition
- human activities
- color images
- spatio temporal patterns
- computer vision
- bag of words
- space time
- space time interest points
- supervised learning
- depth information
- rgb d camera
- gray scale
- depth map
- image sequences
- spatial and temporal
- video sequences
- semi supervised
- kernel function
- video representation
- kernel methods
- content based copy detection
- background subtraction
- moving objects
- learning algorithm
- support vector
- salient points
- feature space
- color space
- object recognition
- image derivatives
- colour space
- temporal domain
- bag of features
- low level descriptors
- face recognition
- local binary pattern
- video frames
- keypoints