Semi-supervised cross-modal learning for cross modal retrieval and image annotation.
Fuhao ZouXingqiang BaiChaoyang LuanKai LiYunfei WangHefei LingPublished in: World Wide Web (2019)
Keyphrases
- cross modal
- multi modal
- image annotation
- visual similarity
- image retrieval
- semi supervised
- multimedia retrieval
- multimedia databases
- automatic image annotation
- semantic concepts
- image content
- image database
- image understanding
- image search
- web images
- image collections
- visual data
- supervised learning
- pairwise
- multi label
- visual features
- information retrieval
- labeled data
- language model
- nearest neighbor
- object recognition
- multiscale