Transforming spatio-temporal self-attention using action embedding for skeleton-based action recognition.
Tasweer AhmadSyed Tahir Hussain RizviNeel KanwalPublished in: J. Vis. Commun. Image Represent. (2023)
Keyphrases
- human actions
- action recognition
- spatio temporal
- action classification
- view invariant
- recognizing human actions
- spatial temporal
- recognition of human actions
- recognizing actions
- spatio temporal interest points
- activity recognition
- bag of words
- human detection
- action recognition in videos
- human activities
- computer vision
- human pose
- space time
- action primitives
- static images
- bag of features
- video dataset
- video sequences
- body parts
- action detection
- depth sensors
- spatial and temporal
- independent subspace analysis
- human motion
- viewpoint
- text classification
- feature space
- motion recognition
- multi view
- mid level
- visual features
- motion patterns