Aligning Images and Text with Semantic Role Labels for Fine-Grained Cross-Modal Understanding.
Abhidip BhattacharyyaCecilia MauceriMartha PalmerChristoffer HeckmanPublished in: LREC (2022)
Keyphrases
- fine grained
- cross modal
- visual similarity
- access control
- image retrieval
- semantic roles
- web images
- object recognition
- image features
- semantic role labeling
- similarity measure
- image collections
- multi modal
- image classification
- text mining
- keywords
- machine learning
- semantic information
- multi label
- image annotation
- n gram
- visual data