Is an Image Worth More than a Thousand Words? On the Fine-Grain Semantic Differences between Visual and Linguistic Representations.
Guillem CollellMarie-Francine MoensPublished in: COLING (2016)
Keyphrases
- fine grain
- auto annotation
- coarse grain
- input image
- low level
- multiscale
- image data
- image content
- linguistic analysis
- natural language
- semantic labels
- image retrieval
- image classification
- web images
- visual concepts
- image segmentation
- semantic categories
- linguistic information
- image processing algorithms
- semantic similarity
- semantic representations
- image matching
- energy function
- visual features
- low cost