Multimodal Object Recognition Using Deep Learning Representations Extracted from Images and Smartphone Sensors.
Javier Ortega BastidaAntonio-Javier GallegoAntonio PertusaPublished in: CIARP (2018)
Keyphrases
- computer vision
- deep learning
- extracted from images
- unsupervised feature learning
- deep belief networks
- machine learning
- unsupervised learning
- d objects
- weakly supervised
- deep architectures
- higher order
- object model
- supervised learning
- mental models
- viewpoint
- semi supervised
- restricted boltzmann machine
- moving objects