Structuring and Embedding Image Captions: the V.I.F. Multi-modal System.
Cristina Nader VasconcelosAsla Medeiros SáMarcio I. SáPaulo Cezar Pinto CarvalhoPublished in: VAST (2012)
Keyphrases
- multi modal
- input image
- image data
- image features
- multi modality
- uni modal
- image analysis
- auto annotation
- audio visual
- multiscale
- image retrieval
- image classification
- fusing multiple
- image annotation
- video search
- image segmentation
- multiple modalities
- single modality
- image collections
- image content
- visual features
- contrast enhancement
- web images
- low level
- high resolution
- image representation
- affine invariant
- semantic concepts
- high dimensional
- segmentation algorithm
- image search
- object recognition
- high level