Seeing the Intangible: Surveying Automatic High-Level Visual Understanding from Still Images.
Delfina Sol Martinez PandianiValentina PresuttiPublished in: CoRR (2023)
Keyphrases
- high level
- low level
- mid level
- image retrieval
- image analysis
- ground truth
- visual appearance
- fully automatic
- image database
- image data
- input image
- three dimensional
- image collections
- human visual
- automatic annotation
- spatial information
- image features
- rigid body
- web images
- image classification
- object recognition
- visual tasks
- observed scene
- image registration
- region of interest
- visual environment
- semantic gap
- low and high level
- visual cues
- image set
- segmentation method
- visual features
- feature points
- edge detection
- visual information
- visual patterns
- image regions
- manual annotation
- visual attributes
- low level image features
- d objects
- bridge the semantic gap
- similarity measure