Fusing mixed visual features for human action recognition.
Chao TangChangle ZhouWei PanLidong XieHuosheng HuPublished in: Int. J. Model. Identif. Control. (2013)
Keyphrases
- visual features
- human actions
- image classification
- visual information
- visual content
- image retrieval
- image search
- low level features
- image annotation
- semantic gap
- semantic concepts
- visual appearance
- keywords
- semantic features
- image collections
- bridge the semantic gap
- low level
- action recognition
- web images
- bag of features
- key frames
- visual data
- automatic image annotation
- image sequences
- visual properties
- information retrieval
- video shots
- feature extraction
- global features
- visual similarity