Multimodal Visual-Tactile Representation Learning through Self-Supervised Contrastive Pre-Training.
Vedant DaveFotios LygerakisElmar RueckertPublished in: CoRR (2024)
Keyphrases
- visual representation
- online learning
- supervised learning
- serious games
- high level
- unsupervised learning
- visual learning
- learning speed
- hidden markov models
- active learning
- training set
- learning stage
- learning algorithm
- perceptual information
- multimodal interaction
- skill acquisition
- structured prediction
- feedforward neural networks
- visual data
- prior knowledge
- learning process
- artificial neural networks
- training data
- e learning
- feature selection