Semantic Cues Enhanced Multimodality Multistream CNN for Action Recognition.
Zhigang TuWei XieJustin DauwelsBaoxin LiJunsong YuanPublished in: IEEE Trans. Circuits Syst. Video Technol. (2019)
Keyphrases
- action recognition
- mid level
- activity recognition
- bag of words
- human actions
- action classification
- computer vision
- spatial temporal
- body parts
- recognition of human actions
- human detection
- human activities
- recognizing human actions
- high level
- bag of features
- static images
- semantic content
- semantic information
- independent subspace analysis
- semantic similarity
- video dataset
- recognizing actions
- depth cameras
- view invariant action recognition
- visual words
- action detection
- view invariant
- three dimensional
- depth map
- low level features
- machine learning
- multi view