Visual-Tactile Cross-Modal Data Generation Using Residue-Fusion GAN With Feature-Matching and Perceptual Losses.
Shaoyu CaiKening ZhuYuki BanTakuji NarumiPublished in: IEEE Robotics Autom. Lett. (2021)
Keyphrases
- cross modal
- feature matching
- data generation
- multi modal
- perceptual information
- image pairs
- object recognition
- image matching
- matching algorithm
- multimedia retrieval
- feature points
- visual data
- visual similarity
- visual recognition
- image registration
- graph matching
- data streams
- active learning
- image retrieval
- multimedia databases
- visual information
- geometric constraints
- visual features
- streaming data
- learning algorithm
- text mining
- pattern recognition
- image processing