Combining Visual and Textual Features for Semantic Segmentation of Historical Newspapers.
Raphaël BarmanMaud EhrmannSimon ClematideSofia Ares OliveiraFrédéric KaplanPublished in: J. Data Min. Digit. Humanit. (2021)
Keyphrases
- semantic segmentation
- superpixels
- conditional random fields
- weakly supervised
- scene classification
- object categories
- object class
- visual features
- image understanding
- visual and textual features
- machine learning
- object classes
- image search
- visual words
- segmentation method
- natural images
- multi modal
- semi supervised
- training set
- web pages