Latent Sensor Fusion: Multimedia Learning of Physiological Signals for Resource-Constrained Devices
arXiv:2507.14185 · doi:10.1145/3731715.3733482
Abstract
Latent spaces offer an efficient and effective means of summarizing data while implicitly preserving meta-information through relational encoding. We leverage these meta-embeddings to develop a modality-agnostic, unified encoder. Our method employs sensor-latent fusion to analyze and correlate multimodal physiological signals. Using a compressed sensing approach with autoencoder-based latent space fusion, we address the computational challenges of biosignal analysis on resource-constrained devices. Experimental results show that our unified encoder is significantly faster, lighter, and more scalable than modality-specific alternatives, without compromising representational accuracy.
References in corpus (7)
- A Survey on Deep Learning in Medical Image Analysis
- Deep Residual Learning for Image Recognition
- Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
- Neural Discrete Representation Learning
- Multimodal Generative Models for Scalable Weakly-Supervised Learning
- BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation
- Efficient Multitask Learning on Resource-Constrained Systems