Diverse Image Captioning via Conditional Variational Autoencoder and Dual Contrastive Learning.
Jing XuBing LiuYong ZhouMingming LiuRui YaoZhiwen ShaoPublished in: ACM Trans. Multim. Comput. Commun. Appl. (2024)
Keyphrases
- image segmentation
- learning process
- image data
- single image
- multiscale
- image pixels
- image retrieval
- template matching
- energy function
- image features
- supervised learning
- learning algorithm
- input image
- image classification
- spatial information
- image matching
- region of interest
- image analysis
- image collections
- image representation
- multiresolution
- object recognition
- latent variable models