Semi-supervised Cross-domain Visual Feature Learning for Audio-Visual Broadcast Speech Transcription.
Rongfeng SuXunying LiuLan WangPublished in: INTERSPEECH (2018)
Keyphrases
- visual features
- audio visual
- cross domain
- semi supervised
- knowledge transfer
- learning algorithm
- visual data
- visual information
- active learning
- supervised learning
- learning process
- machine learning
- text categorization
- multi modal
- computer vision
- image classification
- decision trees
- data mining
- image data
- image retrieval
- keywords
- reinforcement learning