用隐空间融合多模态生理信号，让低资源设备高效分析生物数据。
Latent Sensor Fusion: Multimedia Learning of Physiological Signals for Resource-Constrained Devices
- 通过隐空间融合实现跨模态统一编码，不依赖具体传感器类型。
- 在低资源设备上速度更快、体积更小，且保持与专用模型相当的精度。
- 适合边缘计算场景下的可穿戴健康监测系统使用。
隐空间能高效总结数据并隐式保留关系信息。我们利用这种元嵌入构建了无需特定模态的统一编码器，采用传感器-隐空间融合方法分析和关联多模态生理信号。通过基于自编码器的隐空间压缩感知融合策略，解决了资源受限设备上生物信号分析的计算难题。实验表明，该统一编码器显著比特定模态的替代方案更快、更轻量、更具可扩展性，同时不牺牲表征准确性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。