Multi-View and Multi-Modal Action Recognition with Learned Fusion.
Sandy ArdiantoHsueh-Ming HangPublished in: APSIPA (2018)
Keyphrases
- multi modal
- multi view
- action recognition
- view invariant
- single view
- activity recognition
- multiple views
- human actions
- bag of words
- depth map
- three dimensional
- computer vision
- d objects
- body parts
- view synthesis
- semi supervised
- range images
- surface reconstruction
- high dimensional
- human activities
- motion capture
- multiple viewpoints
- spatio temporal
- humanoid robot
- object recognition
- video search