Audio-Visual Segmentation via Unlabeled Frame Exploitation.
Jinxiang LiuYikun LiuFei ZhangChen JuYa ZhangYanfeng WangPublished in: CoRR (2024)
Keyphrases
- audio visual
- multi modal
- multimedia
- image segmentation
- visual information
- visual data
- audio visual speech recognition
- person authentication
- temporal context
- multiscale
- multi stream
- active learning
- emotion recognition
- training data
- data sets
- image classification
- labeled data
- object recognition
- three dimensional
- computer vision
- search engine