CTI-GAN: Cross-Text-Image Generative Adversarial Network for Bidirectional Cross-modal Generation.
Changhong JingBing XueJunren PanPublished in: CSSE (2022)
Keyphrases
- cross modal
- input image
- image data
- image content
- multiscale
- image classification
- image retrieval
- image features
- multi modal
- image representation
- image collections
- image segmentation
- image regions
- visual similarity
- generative model
- spatial information
- visual data
- multimedia retrieval
- low level
- object recognition
- multimedia databases