Deep supervised multimodal semantic autoencoder for cross-modal retrieval.
Yu TianWenjing YangQingsong LiuQiong YangPublished in: Comput. Animat. Virtual Worlds (2020)
Keyphrases
- cross modal
- multi modal
- multimedia retrieval
- visual similarity
- image retrieval
- semantic concepts
- multimedia databases
- visual recognition
- semantic similarity
- multiple modalities
- information retrieval systems
- multimedia data
- visual data
- supervised learning
- semantic content
- high level
- restricted boltzmann machine
- image classification
- information retrieval
- relevance feedback
- automatic image annotation
- high dimensional
- object recognition
- learning algorithm