Boosting Entity-aware Image Captioning with Multi-modal Knowledge Graph.
Wentian ZhaoYao HuHeda WangXinxiao WuJiebo LuoPublished in: CoRR (2021)
Keyphrases
- multi modal
- image data
- image features
- input image
- uni modal
- multiscale
- image content
- image segmentation
- auto annotation
- low level
- image classification
- image retrieval
- image representation
- single modality
- image collections
- image analysis
- segmentation method
- image annotation
- audio visual
- cross modal
- multi modality
- multiple modalities
- higher level
- fusing multiple
- image regions
- x ray
- high resolution
- semantic concepts
- video search
- high dimensional
- high level