Revamping Cross-Modal Recipe Retrieval with Hierarchical Transformers and Self-supervised Learning.
Amaia SalvadorErhan GundogduLoris BazzaniMichael DonoserPublished in: CoRR (2021)
Keyphrases
- cross modal
- learning algorithm
- multi modal
- visual recognition
- perceptual information
- information retrieval systems
- learning tasks
- multimedia retrieval
- information retrieval
- statistical learning
- video sequences
- active learning
- relevance feedback
- image database
- image understanding
- multimedia databases
- feature extraction