Injecting Semantic Concepts into End-to-End Image Captioning.
Zhiyuan FangJianfeng WangXiaowei HuLin LiangZhe GanLijuan WangYezhou YangZicheng LiuPublished in: CVPR (2022)
Keyphrases
- end to end
- semantic concepts
- image collections
- image regions
- input image
- semantic gap
- low level
- image features
- visual concepts
- image retrieval
- multiscale
- image representation
- image data
- image classification
- image content
- congestion control
- visual features
- computer vision
- multi modal
- image matching
- low level features
- image analysis
- keypoints
- topic models
- data processing
- high resolution
- metadata