Jointing Cross-Modality Retrieval to Reweight Attributes for Image Caption Generation.
Yuxuan DingWei WangMengmeng JiangHeng LiuDonghu DengWei WeiChunna TianPublished in: PRCV (3) (2019)
Keyphrases
- image retrieval
- input image
- multiscale
- image classification
- single image
- image description
- image data
- image database
- image features
- image content
- image analysis
- segmentation algorithm
- image representation
- similarity matching
- low level
- segmentation method
- image pixels
- image segmentation
- visual features
- object retrieval
- information retrieval
- image regions
- visual information
- test images
- image collections
- feature extraction
- relevant images
- feature points
- pixel values
- relevance feedback
- bounding box
- image similarity
- text queries