Audio-visual domain adaptation using conditional semi-supervised Generative Adversarial Networks.
Christos AthanasiadisEnrique HortalStylianos AsteriadisPublished in: Neurocomputing (2020)
Keyphrases
- domain adaptation
- audio visual
- semi supervised
- labeled data
- semi supervised learning
- multi modal
- unsupervised learning
- unlabeled data
- co training
- pairwise
- visual information
- active learning
- supervised learning
- visual data
- multimedia
- transfer learning
- multi view
- multiple sources
- cross domain
- text classification
- sentiment classification
- information retrieval
- object recognition
- low dimensional
- three dimensional
- low level