What have we learned from deep representations for action recognition?
Christoph FeichtenhoferAxel PinzRichard P. WildesAndrew ZissermanPublished in: CoRR (2018)
Keyphrases
- action recognition
- mid level
- human actions
- bag of words
- activity recognition
- human detection
- spatial temporal
- computer vision
- action classification
- static images
- recognizing human actions
- recognizing actions
- view invariant
- motion features
- bag of features
- depth cameras
- video dataset
- action detection
- depth sensors
- action primitives
- human activities
- recognition of human actions
- action recognition in videos