pith. sign in

arxiv: 2604.25680 · v1 · submitted 2026-04-28 · 💻 cs.CV · eess.IV

Exploring Remote Photoplethysmography for Neonatal Pain Detection from Facial Videos

Ashutosh Dhamaniya , Anup Kumar Gupta , Trishna Saikia , Puneet Gupta This is my paper

Pith reviewed 2026-05-07 16:35 UTC · model grok-4.3

classification 💻 cs.CV eess.IV
keywords remote photoplethysmographyneonatal pain detectionfacial video analysisnon-contact monitoringrPPG signalsblue color channelmultimodal fusion
0
0 comments X

The pith

Remote photoplethysmography signals from neonatal facial videos provide useful information for pain detection.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper tests a non-contact method to measure pulse signals from a baby's face on video and use those signals to detect pain. Contact sensors currently used for this purpose carry infection risks and limit long-term monitoring, so a video-based alternative would reduce those drawbacks in neonatal intensive care. The method identifies the best regions of interest with a quality check to avoid movement distortion, then selects the cleanest signal via signal-to-noise ratio, and reports that the blue color channel yields stronger signals than red or green. Experiments further show that merging the rPPG signals with audio features improves classification accuracy over using either type of data alone.

Core claim

We introduce a novel approach using remote photoplethysmography (rPPG) to estimate pulse signals in a non-contact manner and employ them for neonatal pain detection. The temporal signals acquired from regions-of-interest affected by skin deformations may exhibit lower quality, so a quality parameter selects ROIs least affected by deformations and signal-to-noise ratio selects the least noisy clip. Experimental findings demonstrate that the rPPG signals provide useful information for neonatal pain detection, signals extracted from the blue colour channel outperform those from other colour channels, and combining rPPG and audio features provides better results than individual modalities.

What carries the argument

remote photoplethysmography (rPPG) signals extracted from selected facial ROIs using quality parameter and SNR-based selection

If this is right

  • rPPG signals can serve as a physiological indicator in automated neonatal pain assessment systems
  • Blue-channel rPPG signals are more informative for pain detection than signals from red or green channels
  • Multimodal fusion of rPPG and audio outperforms either modality used alone for this task
  • Non-contact rPPG reduces infection risk and enables longer monitoring periods compared with skin-contact sensors

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The method could be added to existing video cameras already used for infant monitoring in NICUs without new hardware
  • Performance should be checked on datasets that include more varied lighting, camera angles, and infant activity levels
  • The same ROI quality and SNR selection steps might apply to detecting other states such as respiratory distress from video

Load-bearing premise

That a quality parameter can reliably identify ROIs least affected by skin deformations and that SNR-based selection will consistently yield the least noisy rPPG signal suitable for pain classification in real neonatal videos.

What would settle it

A held-out test on neonatal videos where pain classification accuracy using the selected rPPG features equals or falls below a baseline model that ignores rPPG entirely.

read the original abstract

Unaddressed pain in neonates can lead to adverse effects, including delayed development and slower weight gain, emphasising the need for more objective and reliable pain assessment methods. Hence, automated methods using behavioural and physiological pain indicators have been developed to aid healthcare professionals in the Neonatal ICU. Traditional contact-based methods for physiological parameter estimation are unsuitable for long-term monitoring and increase the risk of spreading diseases like COVID-19. We introduce a novel approach using remote photoplethysmography (rPPG) to estimate pulse signals in a non-contact manner and employ them for neonatal pain detection. The temporal signals acquired from regions-of-interest (ROIs) affected by skin deformations may exhibit lower quality and provide erroneous rPPG signals. Therefore, we incorporated a quality parameter to select the temporal signals obtained from ROIs that are least affected by skin deformations. Further, we employed signal-to-noise ratio as a fitness parameter to extract the rPPG signal corresponding to the clip that is least affected by noise. Experimental findings demonstrate that the rPPG signals provide useful information for neonatal pain detection, and signals extracted from the blue colour channel outperform those extracted from other colour channels. We also show that combining rPPG and audio features provides better results than individual modalities.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

3 major / 1 minor

Summary. The manuscript introduces a non-contact approach to neonatal pain detection by extracting remote photoplethysmography (rPPG) signals from facial videos. It describes a quality parameter to select ROIs minimally affected by skin deformations and uses SNR as a fitness criterion to choose the least-noisy temporal signal per clip. The central claims are that rPPG signals (particularly from the blue channel) contain useful information for pain classification and that fusing rPPG with audio features outperforms either modality alone.

Significance. A validated non-contact rPPG pipeline for neonatal pain monitoring would address a genuine clinical need by avoiding skin irritation and infection risks associated with contact sensors. The multi-modal fusion direction is promising. However, the absence of dataset statistics, validation protocols, quantitative performance numbers, and ablations in the current presentation makes it impossible to judge whether the reported gains reflect genuine physiological signal or methodological artifacts.

major comments (3)
  1. [Abstract] Abstract: the claim that 'experimental findings demonstrate that the rPPG signals provide useful information for neonatal pain detection' is unsupported by any reported dataset size, number of subjects, pain-labeling protocol, train/test split, cross-validation scheme, or statistical test. Without these, the experimental support for the central claim cannot be evaluated.
  2. [Method] Method (ROI quality parameter): the quality parameter used to discard ROIs affected by skin deformations is introduced without an equation, threshold value, or validation against an independent measure of signal fidelity (e.g., correlation with simultaneous ECG or manual annotation of motion-free intervals). In the presence of rapid neonatal facial movements, this selection step is load-bearing; an ablation comparing selected-ROI versus all-ROI or random-ROI baselines is required to rule out selection bias.
  3. [Method] Method (SNR selection): the SNR-based choice of the 'least affected by noise' rPPG signal per clip is described at a high level but supplies neither the SNR formula nor any threshold. Neonatal videos contain substantial motion; without explicit validation that the selected signal correlates with ground-truth pulse or yields statistically superior classification, the reported blue-channel superiority and multi-modal gains rest on an unverified preprocessing assumption.
minor comments (1)
  1. [Abstract] Abstract: key quantitative results (accuracy, F1, AUC, p-values) should be included to allow readers to gauge effect sizes.

Simulated Author's Rebuttal

3 responses · 0 unresolved

We thank the referee for the thorough and constructive review. The comments highlight important areas where additional details and analyses will strengthen the manuscript. We address each major comment below and will incorporate revisions to provide the missing experimental details, equations, and ablations.

read point-by-point responses

  1. Referee: [Abstract] Abstract: the claim that 'experimental findings demonstrate that the rPPG signals provide useful information for neonatal pain detection' is unsupported by any reported dataset size, number of subjects, pain-labeling protocol, train/test split, cross-validation scheme, or statistical test. Without these, the experimental support for the central claim cannot be evaluated.

    Authors: We agree that the abstract and main text currently omit key experimental details, making it difficult to fully evaluate the claims. In the revised manuscript we will expand the abstract to report the number of neonates, total video clips, pain-labeling protocol, and quantitative performance metrics with statistical tests. A new Experimental Setup section will detail the train/test split, cross-validation scheme, and full results supporting the utility of rPPG signals for pain detection. revision: yes

  2. Referee: [Method] Method (ROI quality parameter): the quality parameter used to discard ROIs affected by skin deformations is introduced without an equation, threshold value, or validation against an independent measure of signal fidelity (e.g., correlation with simultaneous ECG or manual annotation of motion-free intervals). In the presence of rapid neonatal facial movements, this selection step is load-bearing; an ablation comparing selected-ROI versus all-ROI or random-ROI baselines is required to rule out selection bias.

    Authors: We will add the explicit equation for the ROI quality parameter and the threshold value used. Although simultaneous ECG recordings are not present in the dataset, we will include a new ablation study comparing pain-detection performance when using the quality-selected ROIs versus all ROIs and versus randomly selected ROIs. This will quantify the benefit of the selection step and address potential motion-related bias. revision: partial

  3. Referee: [Method] Method (SNR selection): the SNR-based choice of the 'least affected by noise' rPPG signal per clip is described at a high level but supplies neither the SNR formula nor any threshold. Neonatal videos contain substantial motion; without explicit validation that the selected signal correlates with ground-truth pulse or yields statistically superior classification, the reported blue-channel superiority and multi-modal gains rest on an unverified preprocessing assumption.

    Authors: The revised manuscript will include the precise SNR formula and the selection threshold. We will add an ablation that compares classification accuracy using the SNR-selected signal against using all candidate signals and against random selection, reporting statistical significance. This will demonstrate that the selection improves results and supports the observed blue-channel and multi-modal advantages. revision: yes

Circularity Check

0 steps flagged

No circularity: experimental results are independent of definitional reduction

full rationale

The paper reports empirical classification performance from rPPG signals extracted via ROI quality selection and SNR filtering on neonatal facial videos. These are methodological choices whose outputs (accuracy, channel comparisons, multimodal gains) are measured against held-out labels rather than being forced by construction from the selection rules themselves. No equations, fitted parameters renamed as predictions, or self-citation chains appear in the provided text; the claims remain falsifiable through the reported experiments.

Axiom & Free-Parameter Ledger

2 free parameters · 1 axioms · 0 invented entities

Abstract-only review yields minimal explicit parameters or axioms; the approach implicitly assumes rPPG color changes remain detectable despite neonatal facial motion and that the introduced quality and SNR parameters can be tuned to isolate pain-relevant signals.

free parameters (2)
  • quality parameter threshold
    Used to filter ROIs affected by skin deformations; exact value or selection rule not stated in abstract.
  • SNR fitness threshold
    Used to pick the least noisy clip; no numerical criterion or fitting procedure given.
axioms (1)
  • domain assumption Color intensity changes in facial skin video can be processed to recover a pulse signal (rPPG) that correlates with physiological state including pain.
    Central to the entire non-contact measurement strategy described.

pith-pipeline@v0.9.0 · 5533 in / 1316 out tokens · 72853 ms · 2026-05-07T16:35:40.461226+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

82 extracted references · 3 canonical work pages

  1. [1]

    Applied Computing and Informatics19, 122–143 (2023)

    Brahnam, S., Nanni, L., McMurtrey, S., Lumini, A., Brattin, R., Slack, M., Bar- rier, T.: Neonatal pain detection in videos using the iCOPEvid dataset and an ensemble of descriptors extracted from Gaussian of Local Descriptors. Applied Computing and Informatics19, 122–143 (2023)

    2023

  2. [2]

    IEEE Reviews in Biomedical Engineering11, 77–96 (2017)

    Zamzmi, G., Kasturi, R., Goldgof, D., Zhi, R., Ashmeade, T., Sun, Y.: A review of automated pain assessment in infants: features, classification tasks, and databases. IEEE Reviews in Biomedical Engineering11, 77–96 (2017)

    2017

  3. [3]

    Diagnostics12, 1831 (2022)

    Cheng, X., Zhu, H., Mei, L., Luo, F., Chen, X., Zhao, Y., Chen, S., Pan, Y.: Artificial intelligence based pain assessment technology in clinical application of real-world neonatal blood sampling. Diagnostics12, 1831 (2022)

    2022

  4. [4]

    In: International Conference on Pattern Recognition, pp

    Zamzmi, G., Pai, C.-Y., Goldgof, D., Kasturi, R., Ashmeade, T., Sun, Y.: An approach for automated multimodal analysis of infants’ pain. In: International Conference on Pattern Recognition, pp. 4148–4153 (2016)

    2016

  5. [5]

    Page, G.G.: Are there long-term consequences of pain in newborn or very young infants? The Journal of Perinatal Education13, 10–17 (2004)

    2004

  6. [6]

    Indian Journal of Palliative Care17, 70 (2011)

    Mathews, L.: Pain in children: neglected, unaddressed and mismanaged. Indian Journal of Palliative Care17, 70 (2011)

    2011

  7. [7]

    Meyer, S., Bay, J.P., Poryo, M.: Staffing, skill mix, shortage, and survival in the NICU and PICU: pediatrics quo vadis? European Journal of Pediatrics, 1–2 (2023)

    2023

  8. [8]

    In: International Conference on Trends in Computational and Cognitive Engineering, pp

    Ritu, J.T., Shakil, M.S.H., Hasan, M.N.I., Al Mamun, S., Kaiser, M.S., Mahmud, M.: Facial detection for neonatal infant pain using facial geometry features and LBP. In: International Conference on Trends in Computational and Cognitive Engineering, pp. 509–518 (2022)

    2022

  9. [9]

    arXiv preprint arXiv:2212.04764 (2022)

    Sun, M., Wang, H., Yao, W., Liu, J.: AuE-IPA: An AU engagement based infant pain assessment method. arXiv preprint arXiv:2212.04764 (2022)

    work page arXiv 2022

  10. [10]

    Multimedia Tools and Applications, 1–24 (2023) 18

    Lu, G., Chen, H., Wei, J., Li, X., Zheng, X., Leng, H., Lou, Y., Yan, J.: Video-based neonatal pain expression recognition with cross-stream attention. Multimedia Tools and Applications, 1–24 (2023) 18

    2023

  11. [11]

    In: IEEE Healthcare Innovations and Point of Care Technologies, pp

    Salekin, M.S., Zamzmi, G., Paul, R., Goldgof, D., Kasturi, R., Ho, T., Sun, Y.: Harnessing the power of deep learning methods in healthcare: Neonatal pain assessment from crying sound. In: IEEE Healthcare Innovations and Point of Care Technologies, pp. 127–130 (2019)

    2019

  12. [12]

    In: Image Analysis, pp

    Zamzmi, G., Pai, C.-Y., Goldgof, D., Kasturi, R., Sun, Y., Ashmeade, T.: Automated pain assessment in neonates. In: Image Analysis, pp. 350–361 (2017)

    2017

  13. [13]

    Expert Systems with Applications235, 121082 (2024)

    Jiang, M., Rosio, R., Salanter¨ a, S., Rahmani, A.M., Liljeberg, P., Silva, D.S., Albuquerque, V.H.C., Wu, W.: Personalized and adaptive neural networks for pain detection from multi-modal physiological features. Expert Systems with Applications235, 121082 (2024)

    2024

  14. [14]

    Computers in Biology and Medicine141, 105146 (2022)

    Birla, L., Puneet, G.: AND-rPPG: A novel denoising-rPPG network for improving remote heart rate estimation. Computers in Biology and Medicine141, 105146 (2022)

    2022

  15. [15]

    Computers in Biology and Medicine121, 103813 (2020)

    Gupta, P., Bhowmick, B., Pal, A.: MOMBAT: Heart rate monitoring from face video using pulse modeling and Bayesian tracking. Computers in Biology and Medicine121, 103813 (2020)

    2020

  16. [16]

    In: IEEE/CVF Winter Conference on Applications of Computer Vision, pp

    Gupta, A.K., Kumar, R., Birla, L., Gupta, P.: RADIANT: Better rPPG estima- tion using signal embeddings and Transformer. In: IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 4976–4986 (2023)

    2023

  17. [17]

    IEEE Transactions on Instrumentation and Measurement (2023)

    Saikia, T., Birla, L., Gupta, A.K., Gupta, P.: HREADAI: Heart rate estimation from face mask videos by consolidating Eulerian and Lagrangian approaches. IEEE Transactions on Instrumentation and Measurement (2023)

    2023

  18. [18]

    In: International Conference on Signal and Image Processing, pp

    Li, P., Benezeth, Y., Nakamura, K., Gomez, R., Li, C., Yang, F.: An improvement for video-based heart rate variability measurement. In: International Conference on Signal and Image Processing, pp. 435–439 (2019). IEEE

    2019

  19. [19]

    Expert Systems with Applications225, 120135 (2023)

    Alnaggar, M., Siam, A.I., Handosa, M., Medhat, T., Rashad, M.: Video-based real-time monitoring for heart rate and respiration rate. Expert Systems with Applications225, 120135 (2023)

    2023

  20. [20]

    Expert Systems with Applications, 129190 (2025)

    Agarwal, V., Saikia, T., Gupta, A.K., Gupta, P.: SHINE: Synergizing transform- ers with contrastive learning for thriving rPPG-based SpO2 estimation. Expert Systems with Applications, 129190 (2025)

    2025

  21. [21]

    Engineering Applications of Artificial Intelligence106, 104447 (2021)

    Huang, B., Chen, W., Lin, C.-L., Juang, C.-F., Xing, Y., Wang, Y., Wang, J.: A neonatal dataset and benchmark for non-contact neonatal heart rate monitoring based on spatio-temporal neural networks. Engineering Applications of Artificial Intelligence106, 104447 (2021)

    2021

  22. [22]

    In: IEEE International Conference on Bioinformatics and Biomedicine, pp

    Malafaya, D., Domingues, S., Oliveira, H.P.: Domain adaptation for heart rate 19 extraction in the Neonatal Intensive Care Unit. In: IEEE International Conference on Bioinformatics and Biomedicine, pp. 1082–1086 (2020)

    2020

  23. [23]

    In: Fuzzy Logic and Applications, pp

    Brahnam, S., Chuang, C.-F., Shih, F.Y., Slack, M.R.: SVM classification of Neonatal facial images of pain. In: Fuzzy Logic and Applications, pp. 121–128 (2006)

    2006

  24. [24]

    Artificial Intelligence in Medicine36, 211–222 (2006)

    Brahnam, S., Chuang, C., Shih, F.Y., Slack, M.R.: Machine recognition and rep- resentation of neonatal facial displays of acute pain. Artificial Intelligence in Medicine36, 211–222 (2006)

    2006

  25. [25]

    Pain138, 460–471 (2008)

    Schiavenato, M., Byers, J.F., Scovanner, P., McMahon, J.M., Xia, Y., Lu, N., He, H.: Neonatal pain facial expression: Evaluating the primal face of pain. Pain138, 460–471 (2008)

    2008

  26. [26]

    Pain28, 395–410 (1987)

    Grunau, R.V., Craig, K.D.: Pain expression in Neonates: facial action and cry. Pain28, 395–410 (1987)

    1987

  27. [27]

    In: New Trends in Image Analysis and Processing, pp

    Celona, L., Manoni, L.: Neonatal facial pain assessment combining hand-crafted and deep features. In: New Trends in Image Analysis and Processing, pp. 197–204 (2017)

    2017

  28. [28]

    IEEE Transactions on Affective Computing (2020)

    Yan, J., Lu, G., Li, X., Zheng, W., Huang, C., Cui, Z., Zong, Y., Chen, M., Hao, Q., Liu, Y., et al.: FENP: a database of neonatal facial expression for pain analysis. IEEE Transactions on Affective Computing (2020)

    2020

  29. [29]

    In: IEEE International Conference on Automatic Face and Gesture Recognition, pp

    Salekin, M.S., Zamzmi, G., Goldgof, D., Kasturi, R., Ho, T., Sun, Y.: First investigation into the use of deep learning for continuous assessment of neonatal postoperative pain. In: IEEE International Conference on Automatic Face and Gesture Recognition, pp. 415–419 (2020)

    2020

  30. [30]

    In: International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery, pp

    Lu, G., Hao, Q., Kong, K., Yan, J., Li, H., Li, X.: Deep convolutional neu- ral networks with transfer learning for Neonatal pain expression recognition. In: International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery, pp. 251–256 (2018)

    2018

  31. [31]

    arXiv preprint arXiv:1807.01631 (2018)

    Zamzmi, G., Goldgof, D., Kasturi, R., Sun, Y.: Neonatal pain expression recognition using transfer learning. arXiv preprint arXiv:1807.01631 (2018)

    work page arXiv 2018

  32. [32]

    In: IEEE International Conference on Systems, Man and Cybernetics, pp

    Salekin, M.S., Zamzmi, G., Goldgof, D., Kasturi, R., Ho, T., Sun, Y.: Multi- channel neural network for assessing neonatal pain from videos. In: IEEE International Conference on Systems, Man and Cybernetics, pp. 1551–1556 (2019)

    2019

  33. [33]

    IEEE Journal of Biomedical and Health Informatics (2023) 20

    Zhu, H., Zhao, Y., Chen, X., Luo, F., Mei, L., Chen, S., Pan, Y.: Video-based Neonatal pain assessment in uncontrolled conditions. IEEE Journal of Biomedical and Health Informatics (2023) 20

    2023

  34. [34]

    In: International Conference of the IEEE Engineering in Medicine and Biology Society, pp

    Sun, Y., Kommers, D., Wang, W., Joshi, R., Shan, C., Tan, T., Aarts, R.M., Pul, C., Andriessen, P., With, P.H.: Automatic and continuous discomfort detection for premature infants in a nicu using video-based motion analysis. In: International Conference of the IEEE Engineering in Medicine and Biology Society, pp. 5995– 5999 (2019)

    2019

  35. [35]

    Frontiers in Public Health9(2021)

    Ashwini, K., Vincent, P.D.R., Srinivasan, K., Chang, C.-Y.: Deep learning assisted neonatal cry classification via support vector machine models. Frontiers in Public Health9(2021)

    2021

  36. [36]

    Computers in Biology and Medicine129, 104150 (2021)

    Salekin, M.S., Zamzmi, G., Goldgof, D., Kasturi, R., Ho, T., Sun, Y.: Multi- modal spatio-temporal deep learning approach for Neonatal postoperative pain assessment. Computers in Biology and Medicine129, 104150 (2021)

    2021

  37. [37]

    British Journal of Nursing20, 1370–1376 (2011)

    Raeside, L.: Physiological measures of assessing infant pain: a literature review. British Journal of Nursing20, 1370–1376 (2011)

    2011

  38. [38]

    Pain 80, 143–148 (1999)

    Lindh, V., Wiklund, U., H˚ akansson, S.: Heel lancing in term new-born infants: an evaluation of pain by frequency domain analysis of heart rate variability. Pain 80, 143–148 (1999)

    1999

  39. [39]

    The Clinical Journal of Pain26, 777–782 (2010)

    Faye, P.M., De Jonckheere, J., Logier, R., Kuissi, E., Jeanne, M., Rakza, T., Storme, L.: Newborn infant pain assessment using heart rate variability analysis. The Clinical Journal of Pain26, 777–782 (2010)

    2010

  40. [40]

    Pfl¨ ugers Archiv-European Journal of Physiology 464, 593–599 (2012)

    Weissman, A., Zimmer, E.Z., Aranovitch, M., Blazer, S.: Heart rate dynamics during acute pain in newborns. Pfl¨ ugers Archiv-European Journal of Physiology 464, 593–599 (2012)

    2012

  41. [41]

    In: IEEE International Conference on Cybernetics, pp

    Walter, S., Gruss, S., Ehleiter, H., Tan, J., Traue, H.C., Werner, P., Al-Hamadi, A., Crawcour, S., Andrade, A.O., Silva, G.M.: The BioVid heat pain database data for the advancement and systematic validation of an automated pain recog- nition system. In: IEEE International Conference on Cybernetics, pp. 128–131 (2013)

    2013

  42. [42]

    Frontiers in Physiology14, 1294577 (2023)

    Lu, Z., Ozek, B., Kamarthi, S.: Transformer encoder with multiscale deep learn- ing for pain classification using physiological signals. Frontiers in Physiology14, 1294577 (2023)

    2023

  43. [43]

    Plos one16(7), 0254108 (2021)

    Pouromran, F., Radhakrishnan, S., Kamarthi, S.: Exploration of physiological sensors, features, and machine learning models for pain intensity estimation. Plos one16(7), 0254108 (2021)

    2021

  44. [44]

    In: Companion Pro- ceedings of the International Conference on Multimodal Interaction

    Gupta, A.K., Saikia, T., Gupta, P., Dhall, A.: PainXtract: A multimodal system for multiclass pain classification using physiological signals. In: Companion Pro- ceedings of the International Conference on Multimodal Interaction. Association for Computing Machinery, ??? (2025). (to appear) 21

    2025

  45. [45]

    In: International Joint Conference on Artificial Intelligence, pp

    Yang, R., Guan, Z., Yu, Z., Feng, X., Peng, J., Zhao, G.: Non-contact pain recognition from video sequences with remote physiological measurements predic- tion. In: International Joint Conference on Artificial Intelligence, pp. 1231–1237. International Joint Conferences on Artificial Intelligence Organization, ??? (2021)

    2021

  46. [46]

    In: IEEE International Conference on Image Processing, pp

    Gupta, P., Bhowmick, B., Pal, A.: Accurate heart-rate estimation from face videos using quality-based fusion. In: IEEE International Conference on Image Processing, pp. 4132–4136 (2017)

    2017

  47. [47]

    In: International Conference of the IEEE Engineering in Medicine & Biology Society, pp

    Sahoo, N.N., Murugesan, B., Das, A., Karthik, S., Ram, K., Leonhardt, S., Joseph, J., Sivaprakasam, M.: Deep learning based non-contact physiological mon- itoring in Neonatal Intensive Care Unit. In: International Conference of the IEEE Engineering in Medicine & Biology Society, pp. 1327–1330 (2022)

    2022

  48. [48]

    In: IEEE Winter Conference on Applications of Computer Vision, pp

    Gupta, P., Bhowmik, B., Pal, A.: Robust adaptive heart-rate monitoring using face videos. In: IEEE Winter Conference on Applications of Computer Vision, pp. 530–538 (2018)

    2018

  49. [49]

    In: IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp

    Wang, C.-Y., Bochkovskiy, A., Liao, H.-Y.M.: YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 7464–7475 (2023)

    2023

  50. [50]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp

    Zhao, C., Han, W., Chen, Z., Li, Y., Feng, Y.: Remote estimation of heart rate based on multi-scale facial rois. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 278–279 (2020)

    2020

  51. [51]

    Current Pediatric Research20, 7–10 (2016)

    Hutchon, D.J.: The normal range of heart rate at birth in a healthy term Neonate: a critical review of the evidence. Current Pediatric Research20, 7–10 (2016)

    2016

  52. [52]

    The Lancet377, 1011–1018 (2011)

    Fleming, S., Thompson, M., Stevens, R., Heneghan, C., Pl¨ uddemann, A., Maconochie, I., Tarassenko, L., Mant, D.: Normal ranges of heart rate and res- piratory rate in children from birth to 18 years of age: a systematic review of observational studies. The Lancet377, 1011–1018 (2011)

    2011

  53. [53]

    https://www.nationwidechildrens.org/conditions/health-library/ physical-exam-of-the-newborn#: ∼:text=Normally%20120%20to%20160% 20beats,to%2060%20breaths%20per%20minute

    Hospital, N.C.: Physical Exam of the Newborn — nationwidechil- drens.org. https://www.nationwidechildrens.org/conditions/health-library/ physical-exam-of-the-newborn#: ∼:text=Normally%20120%20to%20160% 20beats,to%2060%20breaths%20per%20minute. [Accessed 10-02-2024]

    2060

  54. [54]

    In: IEEE International Conference on Acoustics, Speech, and Signal Processing, vol

    Papadias, C.B.: A multi-user kurtosis algorithm for blind source separation. In: IEEE International Conference on Acoustics, Speech, and Signal Processing, vol. 5, pp. 3144–3147 (2000)

    2000

  55. [55]

    Biomedical Signal Processing and Control93, 106186 (2024) 22

    Liu, Y., Xu, C., Qi, L., Li, Y.: A robust non-contact heart rate estimation from facial video based on a non-parametric signal extraction model. Biomedical Signal Processing and Control93, 106186 (2024) 22

    2024

  56. [56]

    Gigascience6(5) (2017)

    Saeb, S., Lonini, L., Jayaraman, A., Mohr, D.C., Kording, K.P.: The need to approximate the use-case in clinical machine learning. Gigascience6(5) (2017)

    2017

  57. [57]

    Computers in Biology and Medicine149, 105907 (2022)

    Wang, Q., Wang, M., Yang, Y., Zhang, X.: Multi-modal emotion recognition using EEG and speech signals. Computers in Biology and Medicine149, 105907 (2022)

    2022

  58. [58]

    In: Interna- tional Conference of Information and Communication Technology for Embedded Systems, pp

    Kurpukdee, N., Kasuriya, S., Chunwijitra, V., Wutiwiwatchai, C., Lamsrichan, P.: A study of support vector machines for emotional speech recognition. In: Interna- tional Conference of Information and Communication Technology for Embedded Systems, pp. 1–6 (2017)

    2017

  59. [59]

    In: The Speaker and Language Recognition Workshop, pp

    Shon, S., Ali, A., Glass, J.: Convolutional neural networks and language embeddings for end-to-end dialect recognition. In: The Speaker and Language Recognition Workshop, pp. 98–104 (2018)

    2018

  60. [60]

    In: IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp

    Liu, Z., Hu, H., Lin, Y., Yao, Z., Xie, Z., Wei, Y., Ning, J., Cao, Y., Zhang, Z., Dong, L.,et al.: Swin Transformer v2: Scaling up capacity and resolution. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 12009–12019 (2022)

    2022

  61. [61]

    In: International Conference on Learning Representations

    Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., Houlsby, N.: An image is worth 16x16 words: Transformers for image recognition at scale. In: International Conference on Learning Representations. OpenReview.net, ??? (2021)

    2021

  62. [62]

    In: IEEE Conference on Computer Vision and Pattern Recognition, pp

    Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., Fei-Fei, L.: Imagenet: A large- scale hierarchical image database. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 248–255 (2009)

    2009

  63. [63]

    In: Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pp

    Wolf, T., Debut, L., Sanh, V., Chaumond, J., Delangue, C., Moi, A., Cistac, P., Rault, T., Louf, R., Funtowicz, M.,et al.: Transformers: State-of-the-art natural language processing. In: Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pp. 38–45 (2020)

    2020

  64. [64]

    In: IEEE Conference on Computer Vision and Pattern Recognition, pp

    Yang, S., Luo, P., Loy, C.-C., Tang, X.: Wider Face: A face detection benchmark. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 5525–5533 (2016)

    2016

  65. [65]

    In: International Conference of the IEEE Engineering in Medicine & Biology Society, pp

    Grooby, E., Sitaula, C., Ahani, S., Holsti, L., Malhotra, A., Dumont, G.A., Marzbanrad, F.: Neonatal face and facial landmark detection from video record- ings. In: International Conference of the IEEE Engineering in Medicine & Biology Society, pp. 1–5 (2023)

    2023

  66. [66]

    Bioinformatics36, 250–256 (2020) 23

    Le, T.T., Fu, W., Moore, J.H.: Scaling tree-based automated machine learning to biomedical big data with a feature set selector. Bioinformatics36, 250–256 (2020) 23

    2020

  67. [67]

    In: Genetic and Evolutionary Computation Conference, pp

    Olson, R.S., Bartley, N., Urbanowicz, R.J., Moore, J.H.: Evaluation of a tree- based pipeline optimization tool for automating data science. In: Genetic and Evolutionary Computation Conference, pp. 485–492 (2016)

    2016

  68. [68]

    Journal of Machine Learning Research12, 2825–2830 (2011)

    Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., Duchesnay, E.: Scikit-learn: Machine learning in Python. Journal of Machine Learning Research12, 2825–2830 (2011)

    2011

  69. [69]

    Sensors21, 4241 (2021)

    Shchelkanova, E., Shchapova, L., Shchelkanov, A., Shibata, T.: Blue as an under- rated alternative to green: Photoplethysmographic heartbeat intervals estimation under two temperature conditions. Sensors21, 4241 (2021)

    2021

  70. [70]

    Serbian Journal of Dermatology and Venereology2, 131–136 (2013)

    Gajinov, Z., Matic, M., Prcic, S., Duran, V.: Optical properties of the human skin. Serbian Journal of Dermatology and Venereology2, 131–136 (2013)

    2013

  71. [71]

    Pharmaceutics14, 433 (2022)

    Rahma, A., Lane, M.E.: Skin barrier function in infants: update and outlook. Pharmaceutics14, 433 (2022)

    2022

  72. [72]

    Health Information Science and Systems14(1), 53 (2026)

    Ding, Y., Dai, Y., Cao, L., Tian, J., Lin, Z., Feng, L.: Detecting stress from videos via intra-subject and inter-subject learning. Health Information Science and Systems14(1), 53 (2026)

    2026

  73. [73]

    Biomedical Signal Processing and Control80, 104214 (2023)

    Mej´ ıa-Mej´ ıa, E., Kyriacou, P.A.: Duration of photoplethysmographic signals for the extraction of pulse rate variability indices. Biomedical Signal Processing and Control80, 104214 (2023)

    2023

  74. [74]

    Frontiers in Neuroscience14, 594880 (2020)

    Shaffer, F., Meehan, Z.M., Zerr, C.L.: A critical review of ultra-short-term heart rate variability norms research. Frontiers in Neuroscience14, 594880 (2020)

    2020

  75. [75]

    Frontiers in public health5, 258 (2017)

    Shaffer, F., Ginsberg, J.P.: An overview of heart rate variability metrics and norms. Frontiers in public health5, 258 (2017)

    2017

  76. [76]

    Behavior Research Methods53(4), 1689–1696 (2021)

    Makowski, D., Pham, T., Lau, Z.J., Brammer, J.C., Lespinasse, F., Pham, H., Sch¨ olzel, C., Chen, S.H.A.: NeuroKit2: A python toolbox for neurophysiological signal processing. Behavior Research Methods53(4), 1689–1696 (2021)

    2021

  77. [77]

    Mobile Information Systems2022(2022)

    Zhang, S., Li, C.: Research on feature fusion speech emotion recognition technol- ogy for smart teaching. Mobile Information Systems2022(2022)

    2022

  78. [78]

    Computers in Biology and Medicine183, 109325 (2024)

    Gupta, A.K., Dhamaniya, A., Gupta, P.: RADIANCE: Reliable and interpretable depression detection from speech using transformer. Computers in Biology and Medicine183, 109325 (2024)

    2024

  79. [79]

    arXiv preprint arXiv:1912.10458 (2019)

    Venkataramanan, K., Rajamohan, H.R.: Emotion recognition from speech. arXiv preprint arXiv:1912.10458 (2019)

    work page arXiv 1912

  80. [80]

    International Journal of Computer Vision 115, 211–252 (2015)

    Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., 24 Karpathy, A., Khosla, A., Bernstein, M., Berg, A.C., Fei-Fei, L.: ImageNet Large Scale Visual Recognition Challenge. International Journal of Computer Vision 115, 211–252 (2015)

    2015

Showing first 80 references.