Learning Semantic-Agnostic and Spatial-Aware Representation for Generalizable Visual-Audio Navigation.
Hongcheng WangYuxuan WangFangwei ZhongMingdong WuJianwei ZhangYizhou WangHao DongPublished in: IEEE Robotics Autom. Lett. (2023)
Keyphrases
- reinforcement learning
- visual representation
- learning process
- high level
- perceptual information
- semantic representation
- learning algorithm
- object recognition
- spatio temporal
- supervised learning
- learning systems
- spatial relations
- image representation
- intermediate representations
- semantic description
- cross modal
- visual words
- visual information
- neural network
- bayesian networks
- machine learning