MEAD: A Large-Scale Audio-Visual Dataset for Emotional Talking-Face Generation.
Kaisiyuan WangQianyi WuLinsen SongZhuoqian YangWayne WuChen QianRan HeYu QiaoChen Change LoyPublished in: ECCV (21) (2020)
Keyphrases
- audio visual
- emotion recognition
- person authentication
- multi modal
- multimodal fusion
- visual information
- visual data
- video summarization
- temporal context
- affective states
- multi stream
- audio visual speech recognition
- facial images
- face images
- multimedia
- visual features
- biometric systems
- principal component analysis
- data sets