Leveraging image captions for selective whole slide image annotation.
Jingna QiuMarc AubrevilleFrauke WilmMathias ÖttlJonas UtzMaja SchlerethKatharina BreiningerPublished in: CoRR (2024)
Keyphrases
- image annotation
- image content
- image retrieval
- image collections
- web images
- image dataset
- visual features
- image search
- automatic image annotation
- semantic gap
- image data
- image classification
- web image search
- image understanding
- visual content
- annotated images
- image annotation and retrieval
- automatic annotation
- image database
- multi label
- visual similarity
- image features
- image representation
- classifier training
- visual concepts
- semantic concepts
- multiscale
- low level
- image analysis
- low level visual features
- visual and textual information
- multi modal
- image segmentation
- image regions
- higher order
- text mining
- ground truth
- object recognition
- video sequences
- machine learning