返回全部动态
PhysAgent：用于可靠远程心率估计的多智能体框架
原标题：PhysAgent: A Multi-Agent Framework for Reliable Remote Heart Rate Estimation
AI 摘要
PhysAgent是一个用于远程心率估计的多智能体框架，由arXiv论文提出。该框架利用多个基础估计器生成候选心率，并通过轻量级4B多模态大语言模型Qwen3-VL-4B驱动多智能体推理，结合确定性生理验证器进行融合，以提高心率估计的稳定性和可靠性。实验表明，PhysAgent在多个公共基准上优于直接预测和传统融合方法，代码即将发布。
以上摘要由 AI 生成，可能存在误差。事实请以原文为准。
正文节选
Computer Science > Computer Vision and Pattern Recognition Title:PhysAgent: A Multi-Agent Framework for Reliable Remote Heart Rate Estimation View PDF HTML (experimental) Abstract:Remote photoplethysmography (rPPG) enables non-contact heart-rate estimation from facial videos, but its weak physiological signal is easily corrupted by motion, illumination changes, occlusion, skin-appearance variation, and device noise. Existing rPPG methods typically rely on a single model to directly p
发布时间：2026-08-04 12:00
抓取时间：2026-08-04 12:17
来源机构：arXiv