Improving Audio-Visual Segmentation with Bidirectional Generation.
Dawei HaoYuxin MaoBowen HeXiaodong HanYuchao DaiYiran ZhongPublished in: AAAI (2024)
Keyphrases
- audio visual
- multi modal
- temporal segmentation
- visual information
- image segmentation
- video summarization
- audio visual speech recognition
- temporal context
- visual data
- multiscale
- person authentication
- hidden markov models
- multimedia
- multi stream
- computer vision
- co occurrence
- pattern recognition
- keywords
- image processing