SkeleMotion: A New Representation of Skeleton Joint Sequences Based on Motion Information for 3D Action Recognition.
Carlos CaetanoJessica SenaFrançois BrémondJefersson A. dos SantosWilliam Robson SchwartzPublished in: CoRR (2019)
Keyphrases
- action recognition
- recognizing human actions
- recognition of human actions
- view invariant
- action recognition in videos
- bag of features
- human actions
- bag of words
- human detection
- activity recognition
- computer vision
- body parts
- spatial temporal
- human pose
- depth sensors
- recognizing actions
- motion history images
- static images
- action classification
- human activities
- motion capture data
- spatio temporal
- hidden markov models
- machine learning
- video sequences
- depth cameras
- object detection
- image representation
- single view
- human body
- human motion