Multi-grained visual pivot-guided multi-modal neural machine translation with text-aware cross-modal contrastive disentangling.
Junjun GuoRui SuJunjie YePublished in: Neural Networks (2024)
Keyphrases
- cross modal
- multi modal
- machine translation
- machine translation system
- video search
- multiple modalities
- natural language processing
- semantic space
- information extraction
- target language
- text retrieval
- natural language
- image annotation
- information retrieval
- statistical machine translation
- semantic concepts
- multimedia retrieval
- text documents
- contextual information
- high dimensional
- high level