UC2: Universal Cross-Lingual Cross-Modal Vision-and-Language Pre-Training.
Mingyang ZhouLuowei ZhouShuohang WangYu ChengLinjie LiZhou YuJingjing LiuPublished in: CVPR (2021)
Keyphrases
- cross lingual
- cross modal
- parallel corpus
- multi modal
- machine translation
- language modeling
- natural language
- news articles
- text classification
- image retrieval
- training set
- visual similarity
- multimedia retrieval
- target language
- supervised learning
- multimedia databases
- document clustering
- transfer learning
- machine learning
- language model
- knowledge representation
- learning algorithm