Exploiting Cross-Modal Prediction and Relation Consistency for Semisupervised Image Captioning.
Yang YangHongchen WeiHengshu ZhuDianhai YuHui XiongJian YangPublished in: IEEE Trans. Cybern. (2024)
Keyphrases
- cross modal
- image data
- image content
- image features
- image classification
- image representation
- low level
- image retrieval
- multi modal
- multiscale
- test images
- spatial information
- image segmentation
- semi supervised
- image regions
- image collections
- high dimensional
- computer vision
- similarity measure
- visual data
- scene classification