Cross-Modal Similarity-Based Curriculum Learning for Image Captioning.
Hongkuan ZhangSaku SugawaraAkiko AizawaLei ZhouRyohei SasanoKoichi TakedaPublished in: CoRR (2022)
Keyphrases
- cross modal
- learning algorithm
- image classification
- image retrieval
- image data
- perceptual information
- image features
- multi modal
- multiscale
- image content
- image segmentation
- low level
- image representation
- information retrieval
- image regions
- image collections
- statistical learning
- web images
- visual recognition
- automatic image annotation