Cross-Modal Attention With Semantic Consistence for Image-Text Matching.
Xing XuTan WangYang YangLin ZuoFumin ShenHeng Tao ShenPublished in: IEEE Trans. Neural Networks Learn. Syst. (2020)
Keyphrases
- cross modal
- semantic space
- image matching
- image retrieval
- visual similarity
- semantic representations
- image content
- image features
- image set
- keypoints
- multi modal
- low level
- image data
- image classification
- image regions
- web images
- visual data
- image collections
- perceptual information
- semantic information
- text retrieval
- multiscale
- information retrieval
- multimedia retrieval
- spatial relationships
- image representation
- text mining
- semantic concepts
- video sequences
- visual recognition
- semantic content
- keywords
- low level features
- feature extraction
- image sequences
- spatial information