Cross-modal Embeddings for Video and Audio Retrieval.
Dídac SurísAmanda Cardoso DuarteAmaia SalvadorJordi TorresXavier Giró-i-NietoPublished in: CoRR (2018)
Keyphrases
- cross modal
- visual data
- multi modal
- multimedia retrieval
- multimedia
- multimedia databases
- image retrieval
- multimedia data
- video data
- multiple modalities
- video streams
- video content
- video sequences
- semantic concepts
- visual recognition
- high dimensional data
- visual similarity
- video search
- visual information
- video frames
- key frames
- multimedia information
- multimedia information retrieval
- image database
- video analysis
- visual features
- multimedia documents
- video clips
- video retrieval
- text retrieval
- information retrieval
- image data
- human motion
- query expansion
- high level