People Watching: Human Actions as a Cue for Single View Geometry.
David F. FouheyVincent DelaitreAbhinav GuptaAlexei A. EfrosIvan LaptevJosef SivicPublished in: ECCV (5) (2012)
Keyphrases
- single view
- human actions
- view invariant
- multi view
- action recognition
- perspective projection
- multiple views
- spatio temporal
- space time
- video sequences
- surface reconstruction
- human motion
- human activities
- activity recognition
- three dimensional
- recognition of human actions
- recognizing actions
- visual features
- action sequences
- data sets
- recognizing human actions
- d objects
- feature extraction
- image sequences
- action recognition in videos