论文标题
Autohr：通过神经搜索进行远程心率测量的强大端到端基线
AutoHR: A Strong End-to-end Baseline for Remote Heart Rate Measurement with Neural Searching
论文作者
论文摘要
远程照相学（RPPG）旨在衡量无与伦比的心脏活动，在许多应用中具有很大的潜力（例如，远程医疗保健）。面部视频中现有的端到端RPPG和心率（HR）测量方法容易受到较不受约束的情况（例如，头部运动和不良照明）。在这封信中，我们探讨了现有的端到端网络在具有挑战性的条件下的表现不佳，并通过神经体系结构搜索（NAS）建立了强大的端到端基线（AUTOHR）。提出的方法包括三个部分：1）具有新型的时间差卷积（TDC）的强大搜索主链，旨在捕获框架之间的内在RPPG感知线索； 2）考虑到时间域和频域的约束，混合损失函数； 3）为更好表示学习的时空数据加强策略。全面的实验是在三个基准数据集上进行的，以显示我们在内部和交叉数据表测试上的出色性能。
Remote photoplethysmography (rPPG), which aims at measuring heart activities without any contact, has great potential in many applications (e.g., remote healthcare). Existing end-to-end rPPG and heart rate (HR) measurement methods from facial videos are vulnerable to the less-constrained scenarios (e.g., with head movement and bad illumination). In this letter, we explore the reason why existing end-to-end networks perform poorly in challenging conditions and establish a strong end-to-end baseline (AutoHR) for remote HR measurement with neural architecture search (NAS). The proposed method includes three parts: 1) a powerful searched backbone with novel Temporal Difference Convolution (TDC), intending to capture intrinsic rPPG-aware clues between frames; 2) a hybrid loss function considering constraints from both time and frequency domains; and 3) spatio-temporal data augmentation strategies for better representation learning. Comprehensive experiments are performed on three benchmark datasets to show our superior performance on both intra- and cross-dataset testing.
