On Metric Learning for Audio-Text Cross-Modal Retrieval.
Xinhao MeiXubo LiuJianyuan SunMark D. PlumbleyWenwu WangPublished in: INTERSPEECH (2022)
Keyphrases
- cross modal
- metric learning
- multi modal
- multimedia retrieval
- distance metric
- image retrieval
- text retrieval
- multimedia databases
- visual similarity
- dimensionality reduction
- multi task
- semi supervised
- pairwise
- learning tasks
- distance function
- keywords
- visual recognition
- information retrieval
- visual data
- feature space
- multimedia documents
- multimedia
- semi supervised learning
- web images
- image database
- text mining
- metadata
- retrieval systems
- multimedia information retrieval
- multimedia data
- text documents
- transfer learning
- supervised learning
- active learning
- object recognition
- e learning