Towards a Theoretical Framework for Learning Multi-modal Patterns for Embodied Agents

Authors:
Nicoletta Noceti;Barbara Caputo;Claudio Castellini;Luca Baldassarre;Annalisa Barla;Lorenzo Rosasco;Francesca Odone;Giulio Sandini
Affiliations:
DISI - University of Genova,;IDIAP - Martigny,;DIST - University of Genova,;DISI - University of Genova, and DIFI - University of Genova,;DISI - University of Genova,;DISI - University of Genova, and MIT, Cambridge;DISI - University of Genova,;DIST - University of Genova, and IIT, Genova
Venue:
ICIAP '09 Proceedings of the 15th International Conference on Image Analysis and Processing
Year:
2009

Citing 8
Cited 1

Scale & Affine Invariant Interest Point Detectors

International Journal of Computer Vision
Distinctive Image Features from Scale-Invariant Keypoints

International Journal of Computer Vision
Some Properties of Regularized Kernel Methods

The Journal of Machine Learning Research
A Performance Evaluation of Local Descriptors

IEEE Transactions on Pattern Analysis and Machine Intelligence
On Learning Vector-Valued Functions

Neural Computation
Simultaneous Object Recognition and Segmentation from Single or Multiple Model Views

International Journal of Computer Vision
Spectral algorithms for supervised learning

Neural Computation
An Algorithm for Transfer Learning in a Heterogeneous Environment

ECML PKDD '08 Proceedings of the 2008 European Conference on Machine Learning and Knowledge Discovery in Databases - Part I

i*Chameleon: a platform for developing multimodal application with comprehensive development cycle

Proceedings of the 28th Annual ACM Symposium on Applied Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Multi-modality is a fundamental feature that characterizes biological systems and lets them achieve high robustness in understanding skills while coping with uncertainty. Relatively recent studies showed that multi-modal learning is a potentially effective add-on to artificial systems, allowing the transfer of information from one modality to another. In this paper we propose a general architecture for jointly learning visual and motion patterns: by means of regression theory we model a mapping between the two sensorial modalities improving the performance of artificial perceptive systems. We present promising results on a case study of grasp classification in a controlled setting and discuss future developments.