Unsupervised Improvement of Audio-Text Cross-Modal Representations.
Zhepei WangCem SubakanKrishna SubramaniJunkai WuTiago TavaresFábio AyresParis SmaragdisPublished in: WASPAA (2023)
Keyphrases
- cross modal
- semantic representations
- multi modal
- multiple modalities
- multimedia retrieval
- text retrieval
- visual data
- image retrieval
- visual recognition
- information retrieval
- multimedia databases
- text mining
- keywords
- supervised learning
- multimedia information retrieval
- semi supervised
- image features
- perceptual information
- query expansion
- image content
- text documents
- image database
- high dimensional
- object recognition
- image sequences