Visual Concept Features and Textual Expansion in a Multimodal System for Concept Annotation and Retrieval with Flickr Photos at ImageCLEF2012.
Joan BenaventÁngel CastellanosXaro BenaventEsther de VesAna García-SerranoPublished in: CLEF (Online Working Notes/Labs/Workshop) (2012)
Keyphrases
- visual concepts
- image retrieval
- image content
- image annotation
- image collections
- tagged images
- visual content
- automatic annotation
- visual information
- visual features
- visual similarity
- semantic concepts
- automatic image annotation
- multi modal
- image database
- video content
- inter related
- semantic gap
- learning tasks
- classifier training
- multi label
- image features
- positive examples
- visual data
- image search
- object categories
- relevance feedback
- information retrieval systems
- feature space
- text categorization
- video retrieval
- co occurrence
- feature vectors
- image patches
- keywords
- personal photos
- image representation
- mir flickr
- information retrieval
- metadata
- visual and textual features
- image understanding
- key frames
- visual words
- low level
- feature extraction
- high level