A generative framework for multimodal learning of spatial concepts and object categories: An unsupervised part-of-speech tagging and 3D visual perception based approach.
Amir AlyAkira TaniguchiTadahiro TaniguchiPublished in: ICDL-EPIROB (2017)
Keyphrases
- visual perception
- object categories
- object categorization
- unsupervised learning
- object detectors
- discriminative learning
- learning algorithm
- object detection
- supervised learning
- generative model
- object recognition
- reinforcement learning
- prior knowledge
- higher level
- object classes
- multi modal
- image features
- learning process