Maximizing mutual information inside intra- and inter-modality for audio-visual event retrieval.
Ruochen LiNannan LiWenmin WangPublished in: Int. J. Multim. Inf. Retr. (2023)
Keyphrases
- audio visual
- mutual information
- multi modal
- audio visual content
- visual information
- image database
- person authentication
- image registration
- multi stream
- visual data
- similarity measure
- information retrieval
- multimedia
- temporal context
- feature selection
- multimedia databases
- event detection
- information retrieval systems
- audio visual speech recognition
- video frames
- retrieval systems
- test collection
- audio features
- image retrieval
- three dimensional
- high dimensional
- image processing