Deep Latent Space Learning for Cross-Modal Mapping of Audio and Visual Signals.
Shah NawazMuhammad Kamran JanjuaIgnazio GalloArif MahmoodAlessandro CalefatiPublished in: DICTA (2019)
Keyphrases
- cross modal
- multi modal
- visual recognition
- latent space
- supervised learning
- learning algorithm
- low dimensional
- multimedia databases
- visual data
- multimedia retrieval
- search engine
- data sets
- pattern recognition
- image retrieval
- prior knowledge
- low level
- reinforcement learning
- distance measure
- high level
- learning tasks
- feature selection
- visual similarity