Two-Stream RNN/CNN for Action Recognition in 3D Videos.
Rui ZhaoHaider AliPatrick van der SmagtPublished in: CoRR (2017)
Keyphrases
- action recognition
- human actions
- action classification
- video dataset
- recognition of human actions
- ucf sports
- recognizing human actions
- human activities
- spatio temporal interest points
- recurrent neural networks
- motion features
- view invariant
- recognizing actions
- static images
- space time interest points
- action recognition in videos
- bag of words
- activity recognition
- action detection
- data streams
- computer vision
- human detection
- mid level features
- spatial temporal
- motion history images
- human object interactions
- human pose
- video sequences
- bag of features
- body parts
- visual words
- depth sensors
- atomic actions
- mid level
- spatio temporal
- video frames
- image retrieval
- view invariant action recognition