Cross2StrA: Unpaired Cross-lingual Image Captioning with Cross-lingual Cross-modal Structure-pivoted Alignment.
Shengqiong WuHao FeiWei JiTat-Seng ChuaPublished in: CoRR (2023)
Keyphrases
- cross lingual
- cross modal
- machine translation
- language modeling
- image retrieval
- low level
- text classification
- image content
- image features
- image classification
- multi modal
- transfer learning
- visual similarity
- image representation
- image collections
- query expansion
- information retrieval
- probabilistic model
- active learning
- data analysis