Cross-modal generative model for visual-guided binaural stereo generation.
Zhaojian LiBin ZhaoYuan YuanPublished in: Knowl. Based Syst. (2024)
Keyphrases
- generative model
- cross modal
- multi modal
- probabilistic model
- multimedia retrieval
- image retrieval
- visual data
- em algorithm
- perceptual information
- prior knowledge
- visual similarity
- computer vision
- object categories
- multimedia databases
- semi supervised
- visual recognition
- expectation maximization
- topic models
- human body
- bayesian networks
- video analysis
- clustering algorithm
- feature space
- high dimensional
- information retrieval
- machine learning