AutoHR: A Strong End-to-End Baseline for Remote Heart Rate Measurement With Neural Searching

Yu, Zitong; Li, Xiaobai; Niu, Xuesong; Shi, Jingang; Zhao, Guoying

doi:10.1109/lsp.2020.3007086

Cited by 113 publications

(56 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For the perspective of automated computer vision (Au-toCV) applications, NAS has been developed for face analysis [39], gesture recognition [40], person ReID [41] and object detection [42] tasks. Different from generic object classification task, the FAS task relies on intrinsic cues between live and spoofing faces, which are easily contaminated by domain shift and unknown attack types.…”

Section: Related Workmentioning

confidence: 99%

NAS-FAS: Static-Dynamic Central Difference Network Search for Face Anti-Spoofing

Wan

Qin

et al. 2021

IEEE Trans. Pattern Anal. Mach. Intell.

Self Cite

185

102

View full text Add to dashboard Cite

Face anti-spoofing (FAS) plays a vital role in securing face recognition systems. Existing methods heavily rely on the expert-designed networks, which may lead to a sub-optimal solution for FAS task. Here we propose the first FAS method based on neural architecture search (NAS), called NAS-FAS, to discover the well-suited task-aware networks. Unlike previous NAS works mainly focus on developing efficient search strategies in generic object classification, we pay more attention to study the search spaces for FAS task. The challenges of utilizing NAS for FAS are in two folds: the networks searched on 1) a specific acquisition condition might perform poorly in unseen conditions, and 2) particular spoofing attacks might generalize badly for unseen attacks. To overcome these two issues, we develop a novel search space consisting of central difference convolution and pooling operators. Moreover, an efficient static-dynamic representation is exploited for fully mining the FAS-aware spatio-temporal discrepancy. Besides, we propose Domain/Type-aware Meta-NAS, which leverages cross-domain/type knowledge for robust searching. Finally, in order to evaluate the NAS transferability for cross datasets and unknown attack types, we release a large-scale 3D mask dataset, namely CASIA-SURF 3DMask, for supporting the new 'cross-dataset cross-type' testing protocol. Experiments demonstrate that the proposed NAS-FAS achieves state-of-the-art performance on nine FAS benchmark datasets with four testing protocols.

show abstract

Section: Related Workmentioning

confidence: 99%

NAS-FAS: Static-Dynamic Central Difference Network Search for Face Anti-Spoofing

Wan

Qin

et al. 2021

IEEE Trans. Pattern Anal. Mach. Intell.

Self Cite

185

102

View full text Add to dashboard Cite

show abstract

“…Yu et al [ 31 ] utilized neural architecture search (NAS) to automatically find the best-suited backbone 3D CNN for rPPG signal extraction ( Figure 7 ). In their research, a special 3D convolution operation, namely temporal difference convolution (TDC), was designed to help track the ROI and improve the robustness in the presence of motion and poor illumination.…”

Section: End-to-end Deep Learning Methodsmentioning

confidence: 99%

Deep Learning Methods for Remote Heart Rate Measurement: A Review and Future Research Agenda

Cheng

Wong

Chin

et al. 2021

Sensors

View full text Add to dashboard Cite

Heart rate (HR) is one of the essential vital signs used to indicate the physiological health of the human body. While traditional HR monitors usually require contact with skin, remote photoplethysmography (rPPG) enables contactless HR monitoring by capturing subtle light changes of skin through a video camera. Given the vast potential of this technology in the future of digital healthcare, remote monitoring of physiological signals has gained significant traction in the research community. In recent years, the success of deep learning (DL) methods for image and video analysis has inspired researchers to apply such techniques to various parts of the remote physiological signal extraction pipeline. In this paper, we discuss several recent advances of DL-based methods specifically for remote HR measurement, categorizing them based on model architecture and application. We further detail relevant real-world applications of remote physiological monitoring and summarize various common resources used to accelerate related research progress. Lastly, we analyze the implications of research findings and discuss research gaps to guide future explorations.

show abstract

“…LCOMS Lab's solution pipeline traction and pulse rate estimation. According to the way of iPPG signal extraction, we can divide the existing works into two major approaches either conventional based methods using image and signal processing algorithms [12,17,4,20,18,1], or deep learning based methods that extract the iPPG signal automatically [3,11,21,2]. In this section, we review mainly the state-of-the-art deep learning based methods for contactless pulse rate measurement.…”

Section: Related Workmentioning

confidence: 99%

“…However, at present most of these methods present a weakness in the case of uncontrolled measurement conditions, in particular the subject's motions and low lighting conditions as well as very dark skin (phototype 6) [1,14]. In this field, deep learning based methods show better performance than conventional state-of-the-art algorithms based on image and signal processing [11,21]. Recently, several deep learning architectures have been proposed to extract the iPPG signal from a video stream.…”

Section: Introductionmentioning

confidence: 99%

LCOMS Lab’s approach to the Vision For Vitals (V4V) Challenge

Ouzar¹,

Djeldjli²,

Bousefsaf³

et al. 2021

2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)

View full text Add to dashboard Cite

AutoHR: A Strong End-to-End Baseline for Remote Heart Rate Measurement With Neural Searching

Cited by 113 publications

References 22 publications

NAS-FAS: Static-Dynamic Central Difference Network Search for Face Anti-Spoofing

NAS-FAS: Static-Dynamic Central Difference Network Search for Face Anti-Spoofing

Deep Learning Methods for Remote Heart Rate Measurement: A Review and Future Research Agenda

LCOMS Lab’s approach to the Vision For Vitals (V4V) Challenge

Contact Info

Product

Resources

About