Multimodal sensor fusion in the latent representation space
This addresses multimodal data integration for applications like sensing and classification, but appears incremental as it builds on existing generative and fusion techniques.
The paper tackles multimodal sensor fusion by introducing a two-stage method that uses a generative model as a reconstruction prior and search manifold, demonstrating effectiveness in tasks like classification, denoising, and recovery from subsampled observations.
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.