Noise-robust Cross-modal Interactive Learning with Text2Image Mask for Multi-modal Neural Machine Translation.
Junjie YeJunjun GuoYan XiangKaiwen TanZhengtao YuPublished in: COLING (2022)
Keyphrases
- multi modal
- cross modal
- machine translation
- multiple modalities
- interactive learning
- image retrieval
- video search
- image data
- visual similarity
- image features
- image content
- web images
- visual data
- information extraction
- image representation
- semantic concepts
- image annotation
- image regions
- natural language processing
- image analysis
- high dimensional
- image classification
- low level
- similarity measure
- statistical machine translation
- image segmentation
- information retrieval
- text mining
- low level features
- image collections
- imaging modalities