Deep Triplet Neural Networks with Cluster-CCA for Audio-Visual Cross-Modal Retrieval.
Donghuo ZengYi YuKeizo OyamaPublished in: ACM Trans. Multim. Comput. Commun. Appl. (2020)
Keyphrases
- cross modal
- audio visual
- multi modal
- visual data
- multimedia retrieval
- high dimensional
- multimedia
- multimedia databases
- visual information
- information retrieval
- high dimensional data
- image sequences
- image retrieval
- text classification
- retrieval systems
- information retrieval systems
- multimedia data
- image database
- image data
- visual similarity
- similarity measure