CM-AVAE: Cross-Modal Adversarial Variational Autoencoder for Visual-to-Tactile Data Generation.
Qiyuan XiFei WangLiangze TaoHanjing ZhangXun JiangJuan WuPublished in: IEEE Robotics Autom. Lett. (2024)
Keyphrases
- cross modal
- data generation
- multi modal
- perceptual information
- multimedia retrieval
- visual similarity
- image retrieval
- data streams
- active learning
- image segmentation
- visual recognition
- high throughput
- visual data
- streaming data
- multimedia databases
- object recognition
- concept drift
- semantic similarity
- visual features
- feature extraction
- decision trees