DC Field | Value | Language |
---|---|---|
dc.contributor.author | Woo, Sungpil | ko |
dc.contributor.author | Zubair, Muhammad | ko |
dc.contributor.author | Lim, Sunhwan | ko |
dc.contributor.author | Kim, Daeyoung | ko |
dc.date.accessioned | 2023-11-27T03:02:06Z | - |
dc.date.available | 2023-11-27T03:02:06Z | - |
dc.date.created | 2023-11-24 | - |
dc.date.issued | 2023-08-07 | - |
dc.identifier.citation | KDD Data Science for Social Good 2023 | - |
dc.identifier.uri | http://hdl.handle.net/10203/315221 | - |
dc.description.abstract | In pre-clinical health monitoring, estimating physiological signals from video is a low-cost and convenient tool. Remote photoplethysmography (rPPG) involves placing a camera in a remote area to estimate a person’s heart rate or Blood Volume Pulse (BVP). In this paper, we propose an attention based deep architecture for rPPG estimation that assimilate temporal relationship across a sequence of frames while focusing on the relevant features and regions by exploiting the inter-pixel relationship of feature maps. Also, we design a dynamic supervision strategy using frequency and time domain losses to mitigate overfitting for efficient estimation of rPPG signals. The proposed method was evaluated on two publicly available rPPG datasets (UBFC-rPPG and PURE). The findings of this study demonstrate that promising results can be achieved by enforcing an adequate balance between time-frequency supervision. | - |
dc.language | English | - |
dc.publisher | ACM SIGKDD | - |
dc.title | Attention based Remote Photoplethysmography Estimation from Facial Video with Equilibrium in Time-Frequency Supervision | - |
dc.type | Conference | - |
dc.type.rims | CONF | - |
dc.citation.publicationname | KDD Data Science for Social Good 2023 | - |
dc.identifier.conferencecountry | US | - |
dc.identifier.conferencelocation | Long Beach, CA | - |
dc.contributor.localauthor | Kim, Daeyoung | - |
dc.contributor.nonIdAuthor | Woo, Sungpil | - |
dc.contributor.nonIdAuthor | Zubair, Muhammad | - |
dc.contributor.nonIdAuthor | Lim, Sunhwan | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.