Multimodal sensor fusion in the latent representation space

Autor:	Piechocki, Robert J., Wang, Xiaoyang, Bocus, Mohammud J.
Rok vydání:	2022
Předmět:	Computer Science - Artificial Intelligence Computer Science - Human-Computer Interaction Computer Science - Machine Learning Electrical Engineering and Systems Science - Signal Processing 68Txx I.2.4 H.1.2 I.2.6
Druh dokumentu:	Working Paper
Popis:	A new method for multimodal sensor fusion is introduced. The technique relies on a two-stage process. In the first stage, a multimodal generative model is constructed from unlabelled training data. In the second stage, the generative model serves as a reconstruction prior and the search manifold for the sensor fusion tasks. The method also handles cases where observations are accessed only via subsampling i.e. compressed sensing. We demonstrate the effectiveness and excellent performance on a range of multimodal fusion experiments such as multisensory classification, denoising, and recovery from subsampled observations. Comment: Under review for Nature Scientific Reports
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2208.02183 Zobrazit plný text záznamu View this record from Arxiv