Audio-Visual Cross-Modal Generation with Multimodal Variational Generative Model.
Zhubin XuTianlei WangDekang LiuDinghan HuHuanqiang ZengJiuwen CaoPublished in: ISCAS (2024)
Keyphrases
- audio visual
- generative model
- cross modal
- multi modal
- visual data
- probabilistic model
- visual information
- em algorithm
- prior knowledge
- image segmentation
- semi supervised
- topic models
- high dimensional
- multimedia data
- expectation maximization
- image annotation
- multimedia databases
- data sets
- visual features
- video sequences
- machine learning