Rethinking Motion Representation: Residual Frames with 3D ConvNets for Better Action Recognition.
Li TaoXueting WangToshihiko YamasakiPublished in: CoRR (2020)
Keyphrases
- action recognition
- recognizing human actions
- recognition of human actions
- action recognition in videos
- motion features
- view invariant
- human actions
- feed forward
- static images
- human detection
- activity recognition
- human movements
- bag of words
- action classification
- computer vision
- bag of features
- spatio temporal
- motion capture data
- moving objects
- object recognition
- body parts
- human pose
- motion analysis
- camera motion
- human motion
- mid level
- human activities
- space time
- depth sensors
- recognizing actions
- neural network