Self-Adaptive Matrix Completion for Heart Rate Estimation from Face Videos under Realistic Conditions

By Sergey Tulyakov, Xavier Alameda-Pineda, Elisa Ricci, Lijun Yin, Jeffrey F. Cohn, Nicu Sebe. Computer Vision and Pattern Recognition, 2016

329 citations recorded by the source corpus.

Subfields: Biomedical Engineering, Cardiology and Cardiovascular Medicine, Cognitive Neuroscience

View Paper: https://www.semanticscholar.org/paper/ff0e397159b9eb3f98df7ed49b5d66433075c745

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biomedical Engineering

In Cardiology and Cardiovascular Medicine

In Cognitive Neuroscience

Citations in the corpus

PhysFormer: Facial Video-based Physiological Measurement with Temporal Difference Transformer (2021, unknown): “The models trained on VIPL-HR are directly tested on MMSE-HR.”
Multimodal Spontaneous Emotion Corpus for Human Behavior Analysis (2016, methodology): “Partial data have also been used successfully for application of video-based heart rate estimation [27].”
Algorithmic Principles of Remote PPG (2017, background): “ing, such as the monitoring of heart rate [7]–[11], respiration [8], SpO2 [8], [12], blood pressure [13], neonates [14], [15], and the detection of atrial fibrillation [16] and mental”
Learning Deep Models for Face Anti-Spoofing: Binary or Auxiliary Supervision (2018, methodology): “Remote Photoplethysmography (rPPG) Remote photo-plethysmography (rPPG) is the technique to track vital signals, such as heart rate, without any contact with human skin [9,20,41,44,46].”
DeepPhys: Video-Based Physiological Measurement Using Convolutional Attention Networks (2018, methodology): “B Video I Every video frame was center-cropped to 492x492 pixels to remove the lateral blank areas before being fed into our processing pipeline. We compare our proposed approach to six other methods [10, 19, 3, 13, 37, 34] for recovering the blood volume pulse. For recovering the respiration, we co”
RhythmNet: End-to-End Heart Rate Estimation From Face via Spatial-Temporal Representation (2019, methodology): “VIPL-HR database, and compare the proposed approach with a number of state-of-the-art traditional methods (Haan2013 [4], Tulyakov2016 [6], POS [7]).”
Remote Photoplethysmograph Signal Measurement from Facial Videos Using Spatio-Temporal Networks (2019, methodology): “The first four [4, 10, 14, 22] are earlier methods not involving neural network.”
Video Acceleration Magnification (2017, background): “In more recent work on heartrate estimation [24] the tracking and selection of features is achieved by matrix completion.”
Remote Heart Rate Measurement From Highly Compressed Facial Videos: An End-to-End Deep Learning Solution With Video Enhancement (2019, methodology): “In past few years, several traditional methods explored rPPG measurement from videos by analyzing subtle color changes on facial regions of interest (ROI), including blind source separation [19, 18], least mean square [12], majority voting [10] and self-adaptive matrix completion [31].”
Face Anti-Spoofing: Model Matters, so Does Data (2019, background): “Multiple spatial scales have been leveraged in [38] to classify live and spoof images.”
FakeCatcher: Detection of Synthetic Portrait Videos using Biological Signals (2019, methodology): “Several approaches proposed improvements to PPG, using chrominance features [18], G channel components [61], optical properties [20], kalman ﬁlters [5], and different facial areas for signal extraction [61, 54, 20, 47].”