JAMSNet: A Remote Pulse Extraction Network Based on Joint Attention and Multi-Scale Fusion

• Published in: IEEE transactions on circuits and systems for video technology Vol. 33; no. 6; pp. 2783 - 2797
• Main Authors: Zhao, Changchen, Wang, Hongsheng, Chen, Huiling, Shi, Weiwei, Feng, Yuanjing
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.06.2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Convolution; Data mining; Datasets; Feature extraction; Heart rate; joint attention; layer-wise attention; Modules; Motion artifacts; multi-scale fusion; Multiscale analysis; Neural networks; Remote photoplethysmography (rPPG); Signal strength; Skin; Source separation

Remote photoplethysmography (rPPG) has been an active research topic in recent years. While most existing methods are focusing on eliminating motion artifacts in the raw traces obtained from single-scale region-of-interest (ROI), it is worth noting that there are some noise signals that cannot be ef...