Incomplete Cross-modal Retrieval with Dual-Aligned Variational Autoencoders.
Mengmeng JingJingjing LiLei ZhuKe LuYang YangZi HuangPublished in: ACM Multimedia (2020)
Keyphrases
- cross modal
- multi modal
- multimedia retrieval
- image retrieval
- multimedia databases
- visual similarity
- denoising
- perceptual information
- multimedia
- image segmentation
- text retrieval
- information retrieval
- content based retrieval
- visual content
- visual data
- information retrieval systems
- retrieval model
- graph cuts
- semantic concepts
- image sequences