Image-Assisted Transformer in Zero-Resource Multi-Modal Translation.
Ping HuangShiliang SunHao YangPublished in: ICASSP (2021)
Keyphrases
- multi modal
- uni modal
- image data
- input image
- image content
- multi modality
- image representation
- fusing multiple
- multiscale
- image regions
- image segmentation
- image features
- image retrieval
- single modality
- audio visual
- image collections
- image classification
- segmentation method
- auto annotation
- image annotation
- cross modal
- low level
- high resolution
- visual cues
- web images
- video search
- image analysis
- vector field
- image search
- mean shift
- multiple modalities