LAVSS: Location-Guided Audio-Visual Spatial Audio Separation.
Yuxin YeWenming YangYapeng TianPublished in: WACV (2024)
Keyphrases
- audio visual
- multi modal
- visual information
- visual data
- sound source
- multi stream
- multimedia
- audio features
- emotion recognition
- audio visual speech recognition
- person authentication
- multimodal fusion
- spatio temporal
- spatial and temporal
- spatial data
- spatial information
- audio visual content
- bag of words
- image classification
- domain knowledge