2025/05/06 by Yiping Xie, Bo Zhao, Xie, Yiping +15 · 3 citations
Computer Science · Engineering · Medicine · #Adaptation (eye) #Benchmark (surveying) #Bridge (graph theory) #Bridging (networking) #Computer Vision and Pattern Recognition (cs.CV) #Context-Aware Activity Recognition Systems #Domain (mathematical analysis) #Domain adaptation #ECG Monitoring and Analysis #FOS: Computer and information sciences #Feature (linguistics) #Generalization #Motion (physics) #Non-Invasive Vital Sign Monitoring #Task (project management)
paper · pdf · doi:10.48550/arxiv.2505.03621
published in arXiv (Cornell University) (Cornell University)
openalex publication_date 2025/05/06 · openalex created_date 2025/10/16 · openalex updated_date 2026/08/05
Remote photoplethysmography (rPPG) enables non-contact physiological measurement but remains highly susceptible to illumination changes, motion artifacts, and limited temporal modeling. Large Language Models (LLMs) excel at capturing long-range dependencies, offering a potential solution but struggle with the continuous, noise-sensitive nature of rPPG signals due to their text-centric design. To bridge this gap, we introduce the PhysLLM, a collaborative optimization framework that synergizes LLMs with domain-specific rPPG components. Specifically, the Text Prototype Guidance (TPG) strategy is proposed to establish cross-modal alignment by projecting hemodynamic features into LLM-interpretable semantic space, effectively bridging the representational gap between physiological signals and linguistic tokens. Besides, a novel Dual-Domain Stationary (DDS) Algorithm is proposed for resolving signal instability through adaptive time-frequency domain feature re-weighting. Finally, rPPG task-specific cues systematically inject physiological priors through physiological statistics, environmental contextual answering, and task description, leveraging cross-modal learning to integrate both visual and textual information, enabling dynamic adaptation to challenging scenarios like variable illumination and subject movements. Evaluation on four benchmark datasets, PhysLLM achieves state-of-the-art accuracy and robustness, demonstrating superior generalization across lighting variations and motion scenarios. The source code is available at https://github.com/Alex036225/PhysLLM.