Bi-Directional Modality Fusion Network For Audio-Visual Event Localization.
Shuo LiuWeize QuanYuan LiuDong-Ming YanPublished in: ICASSP (2022)
Keyphrases
- audio visual
- bi directional
- multi modal
- person authentication
- multimodal fusion
- multi stream
- visual information
- audio visual speech recognition
- event detection
- temporal context
- visual data
- associative memory
- multimedia
- feature extraction
- feature selection
- neural network
- data processing
- data points
- high level
- search engine