Cross-modal supervised learning for better acoustic representations.
Shaoyong JiaXin ShuYang YangDawei LiangQiyue LiuJunhui LiuPublished in: CoRR (2019)
Keyphrases
- cross modal
- supervised learning
- multi modal
- multimedia retrieval
- visual recognition
- image retrieval
- semi supervised
- multimedia databases
- visual data
- training data
- learning tasks
- training set
- machine learning
- active learning
- higher level
- statistical learning
- class labels
- visual similarity
- learning algorithm
- perceptual information
- similarity search
- training examples
- high dimensional