CN-Celeb-AV: A Multi-Genre Audio-Visual Dataset for Person Recognition.
Lantian LiXiaolou LiHaoyu JiangChen ChenRuihai HouDong WangPublished in: INTERSPEECH (2023)
Keyphrases
- audio visual
- multi modal
- visual information
- visual data
- multimedia
- video summarization
- multi stream
- person authentication
- object recognition
- audio visual speech recognition
- action recognition
- visual content
- pattern recognition
- feature extraction
- activity recognition
- human computer interaction
- visual features
- data sources
- video sequences
- face recognition