Action recognition from videos using sparse trajectories.
Alexandros DoumanoglouNicholas VretosPetros DarasPublished in: ICDP (2016)
Keyphrases
- action recognition
- view invariant
- human actions
- video dataset
- action classification
- recognition of human actions
- recognizing human actions
- ucf sports
- human activities
- static images
- spatio temporal interest points
- bag of words
- recognizing actions
- human detection
- action recognition in videos
- space time interest points
- motion features
- spatial temporal
- computer vision
- activity recognition
- human object interactions
- body parts
- multi view
- sparse representation
- single view
- mid level features
- action detection
- action primitives
- motion history images
- human pose
- moving objects
- motion recognition
- max margin
- depth sensors
- video frames
- low level descriptors
- dynamic scenes
- motion capture data
- machine learning
- motion trajectories