Modal-Dependent Retrieval Based on Mid-Level Semantic Enhancement Space.
Shunxin ZhengHuaxiang ZhangYudan QiBin ZhangPublished in: IEEE Access (2019)
Keyphrases
- mid level
- low level features
- visual concepts
- low level
- high level
- image retrieval
- semantic gap
- relevance feedback
- action recognition
- image database
- learning tasks
- visual cues
- semantic concepts
- event detection
- image content
- semantic information
- higher level
- multimedia databases
- superpixels
- perceptual grouping
- activity recognition
- levels of abstraction
- multi modal
- retrieval systems
- xml documents
- multiscale