Person instance graphs for mono-, cross- and multi-modal person recognition in multimedia data: application to speaker identification in TV broadcast.
Hervé BredinAnindya RoyViet Bac LeClaude BarrasPublished in: Int. J. Multim. Inf. Retr. (2014)
Keyphrases
- multi modal
- multimedia data
- semantic concepts
- speaker identification
- multimedia
- audio visual
- multimedia information retrieval
- multimedia databases
- multimedia content
- tv broadcast
- feature extraction
- data processing
- high dimensional
- pattern recognition
- high level
- gaussian mixture model
- visual information
- data analysis
- face recognition
- multiple modalities
- data sets