T-VLAD: Temporal vector of locally aggregated descriptor for multiview human action recognition.
Hajra Binte NaeemFiza MurtazaMuhammad Haroon YousafSergio A. VelastinPublished in: Pattern Recognit. Lett. (2021)
Keyphrases
- action recognition
- motion history images
- spatio temporal interest points
- spatial temporal
- static images
- human activities
- bag of words
- human movements
- activity recognition
- action classification
- human actions
- human detection
- computer vision
- body parts
- bag of features
- recognition of human actions
- recognizing actions
- recognizing human actions
- human object interactions
- motion capture data
- action primitives
- image search
- action detection
- human pose
- view invariant
- temporal information
- multi view
- feature vectors
- depth sensors
- temporal relations
- spatio temporal
- atomic actions
- multiple views
- low level