Overcoming Small Data Limitations in Video-Based Infant Respiration Estimation

• URL: http://arxiv.org/abs/2512.06888v1
• Date: Sun, 07 Dec 2025 15:25:17 GMT
• Title: Overcoming Small Data Limitations in Video-Based Infant Respiration Estimation
• Authors: Liyang Song, Hardik Bishnoi, Sai Kumar Reddy Manne, Sarah Ostadabbas, Briana J. Taylor, Michael Wan,
• Abstract summary: We introduce the annotated infant respiration dataset of 400 videos (AIR-400), contributing 275 new annotated videos from 10 recruited subjects to the public corpus.<n>We develop the first reproducible pipelines for infant respiration estimation, based on infant-specific region-of-interest detection andtemporal neural processing enhanced by optical flow inputs.<n>We establish, through comprehensive experiments, the first reproducible benchmarks for the state-of-the-art in vision-based infant respiration estimation.
• Score: 7.723650415926449
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: The development of contactless respiration monitoring for infants could enable advances in the early detection and treatment of breathing irregularities, which are associated with neurodevelopmental impairments and conditions like sudden infant death syndrome (SIDS). But while respiration estimation for adults is supported by a robust ecosystem of computer vision algorithms and video datasets, only one small public video dataset with annotated respiration data for infant subjects exists, and there are no reproducible algorithms which are effective for infants. We introduce the annotated infant respiration dataset of 400 videos (AIR-400), contributing 275 new, carefully annotated videos from 10 recruited subjects to the public corpus. We develop the first reproducible pipelines for infant respiration estimation, based on infant-specific region-of-interest detection and spatiotemporal neural processing enhanced by optical flow inputs. We establish, through comprehensive experiments, the first reproducible benchmarks for the state-of-the-art in vision-based infant respiration estimation. We make our dataset, code repository, and trained models available for public use.

Related papers

• VideoPulse: Neonatal heart rate and peripheral capillary oxygen saturation (SpO2) estimation from contact free video [1.8148696158263362]
  VideoPulse contains 157 recordings totaling 2.6 hours from 52 neonates with diverse face orientations.<n>Our pipeline performs face alignment and artifact aware supervision using denoised pulse oximeter signals.<n>On the NBHR neonatal dataset, we obtain heart rate MAE 2.97 bpm using 2 second windows and SpO2 MAE 1.69 percent.
  arXiv  Detail & Related papers  (2026-02-27T07:57:04Z)
• Beyond Benchmarks of IUGC: Rethinking Requirements of Deep Learning Methods for Intrapartum Ultrasound Biometry from Fetal Ultrasound Videos [58.71502465551297]
  Intrapartum Ultrasound Grand Challenge (IUGC) co-hosted with MICCAI 2024 was launched.<n>IUGC introduces a clinically oriented multi-task automatic measurement framework that integrates standard plane classification, fetal head-pubic symphysis segmentation, and biometry.<n>The challenge releases the largest multi-center intrapartum ultrasound video dataset to date, comprising 774 videos (68,106 frames) collected from three hospitals.
  arXiv  Detail & Related papers  (2026-02-13T13:28:22Z)
• Pediatric Asthma Detection with Googles HeAR Model: An AI-Driven Respiratory Sound Classifier [0.8463972278020965]
  This work presents an AI-powered diagnostic pipeline to detect early signs of asthma from pediatric respiratory sounds.<n>The SPRSound dataset is used to extract 2-second audio segments labeled as wheeze, crackle, rhonchi, stridor, or normal.<n>The system achieves over 91% accuracy, with strong performance on precision-recall metrics for positive cases.
  arXiv  Detail & Related papers  (2025-04-28T12:52:17Z)
• BabyVLM: Data-Efficient Pretraining of VLMs Inspired by Infant Learning [33.64851748019174]
  Human infants rapidly develop visual reasoning skills from minimal input.<n>Recent efforts have leveraged infant-inspired datasets like SAYCam.<n>We propose BabyVLM, a novel framework comprising comprehensive in-domain evaluation benchmarks and a synthetic training dataset.
  arXiv  Detail & Related papers  (2025-04-13T04:17:12Z)
• Machine learning-based algorithms for at-home respiratory disease monitoring and respiratory assessment [45.104212062055424]
  This work aims to develop machine learning-based algorithms to facilitate at-home respiratory disease monitoring and assessment. Data were collected from 30 healthy adults, encompassing respiratory pressure, flow, and dynamic thoraco-abdominal circumferential measurements. Various machine learning models, including the random forest classifier, logistic regression, and support vector machine (SVM), were trained to predict breathing types.
  arXiv  Detail & Related papers  (2024-09-05T02:14:31Z)
• LoCI-DiffCom: Longitudinal Consistency-Informed Diffusion Model for 3D Infant Brain Image Completion [45.361733575664886]
  We propose LoCI-DiffCom, a novel Longitudinal Consistency-Informed Diffusion model for infant brain image Completion. Our approach can extract individualized developmental features while ensuring context-aware consistency.
  arXiv  Detail & Related papers  (2024-05-17T10:53:40Z)
• Self-supervised vision-langage alignment of deep learning representations for bone X-rays analysis [53.809054774037214]
  This paper proposes leveraging vision-language pretraining on bone X-rays paired with French reports. It is the first study to integrate French reports to shape the embedding space devoted to bone X-Rays representations.
  arXiv  Detail & Related papers  (2024-05-14T19:53:20Z)
• Automatic Infant Respiration Estimation from Video: A Deep Flow-based Algorithm and a Novel Public Benchmark [10.097634735211654]
  We develop a deep-learning method for estimating respiratory rate and waveform from plain video footage in natural settings. Our model supports the first public annotated infant respiration dataset with 125 videos. When trained and tested on the AIR-125 infant data, our method significantly outperforms other state-of-the-art methods in respiratory rate estimation.
  arXiv  Detail & Related papers  (2023-07-24T19:59:15Z)
• Object Detection During Newborn Resuscitation Activities [3.5661795505491445]
  We propose a two-step process in order to detect activities possibly overlapping in time. The first step is to detect and track the relevant objects, like bag-mask resuscitator, heart rate sensors etc. The performance of the object detection during activities were 96.97 % (ventilations), 100 % (attaching/removing heart rate sensor) and 75 % (suction) on a test set of 20 videos.
  arXiv  Detail & Related papers  (2023-03-14T11:04:50Z)
• Activity Recognition From Newborn Resuscitation Videos [3.54339629317433]
  A dataset of recorded signals during newborn resuscitation, including videos, has been collected in Haydom, Tanzania. We propose a two-step deep neural network system, ORAA-net, to do activity recognition during newborn resuscitation. The system recognized the activities newborn uncovered, stimulation, ventilation and suction with a mean precision of 77.67 %, a mean recall of 77,64 %, and a mean accuracy of 92.40 %.
  arXiv  Detail & Related papers  (2023-03-14T11:04:32Z)
• A Spatio-temporal Attention-based Model for Infant Movement Assessment from Videos [44.71923220732036]
  We develop a new method for fidgety movement assessment using human poses extracted from short clips. Human poses capture only relevant motion profiles of joints and limbs and are free from irrelevant appearance artifacts. Our experiments show that the proposed method achieves the ROC-AUC score of 81.87%, significantly outperforming existing competing methods with better interpretability.
  arXiv  Detail & Related papers  (2021-05-20T14:31:54Z)
• Deep learning in the ultrasound evaluation of neonatal respiratory status [11.308283140003676]
  Lung ultrasound imaging is reaching growing interest from the scientific community. Image analysis and pattern recognition approaches have proven their ability to fully exploit the rich information contained in these data. We present a thorough analysis of recent deep learning networks and training strategies carried out on a vast and challenging multicenter dataset.
  arXiv  Detail & Related papers  (2020-10-31T18:57:55Z)
• Identification of deep breath while moving forward based on multiple body regions and graph signal analysis [45.62293065676075]
  This paper presents an unobtrusive solution that can automatically identify deep breath when a person is walking past the global depth camera. In validation experiments, the proposed approach outperforms the comparative methods with the accuracy, precision, recall and F1 of 75.5%, 76.2%, 75.0% and 75.2%, respectively.
  arXiv  Detail & Related papers  (2020-10-20T08:26:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.