Cross-modal Generative Model for Visual-Guided Binaural Stereo Generation.
Zhaojian LiBin ZhaoYuan YuanPublished in: CoRR (2023)
Keyphrases
- generative model
- cross modal
- multi modal
- probabilistic model
- multimedia retrieval
- image retrieval
- semi supervised
- visual data
- perceptual information
- visual similarity
- prior knowledge
- em algorithm
- multimedia databases
- visual recognition
- topic models
- computer vision
- object categories
- visual information
- training data
- expectation maximization
- active learning
- semantic concepts
- visual features