Audio-Visual Embedding for Cross-Modal Music Video Retrieval through Supervised Deep CCA.
Donghuo ZengYi YuKeizo OyamaPublished in: ISM (2018)
Keyphrases
- audio visual
- video retrieval
- multi modal
- visual data
- visual content
- video data
- content based retrieval
- visual similarity
- retrieval systems
- visual information
- multimedia
- key frames
- video content
- semi supervised
- video streams
- multimedia databases
- high dimensional
- video sequences
- three dimensional
- image annotation
- low level
- object recognition