Infant Care Video Dataset for Classification of Interventions Using Transformers

• URL: http://arxiv.org/abs/2608.23838v1
• Date: Mon, 24 Aug 2026 21:25:59 GMT
• Title: Infant Care Video Dataset for Classification of Interventions Using Transformers
• Abstract summary: We present the Infant Care Video dataset (ICVD), a collection of 4,144 videos spanning 12 simulated intervention classes.<n>Our manikin-based approach systematically varies conditions, such as camera angle and clinician skin tone, while ensuring privacy compliance.<n>The ICVD provides a foundation for developing automated documentation systems to reduce clinical burden in neonatal care environments.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Healthcare documentation in the neonatal intensive care unit (NICU) presents significant challenges, with nurses spending approximately 25\% of their time on record-keeping, while up to 60\% of interventions remain undocumented. Motivated by the need to detect interventions from video automatically, we present the Infant Care Video Dataset (ICVD), a collection of 4,144 videos spanning 12 simulated intervention classes designed for developing automated documentation systems. Our manikin-based approach systematically varies conditions, such as camera angle and clinician skin tone, while ensuring privacy compliance. Using video transformer architectures (TimeSformer and MotionFormer), we establish strong baseline performance (93.97\% and 93.17\% top-1 accuracy) among the 12 infant care classes. Our ablation study comparing temporal models with a framewise approach (23.17\% accuracy) demonstrates a 70.80\% performance gap, validating the need for temporal modeling. The ICVD provides a foundation for developing automated documentation systems to reduce clinical burden in neonatal care environments and improve existing practices.

Related papers

• Scaling Video Pretraining for Surgical Foundation Models [51.92777479821822]
  SurgRec is a scalable and reproducible pretraining recipe for surgical video understanding.<n>We curate a large corpus of 10,535 videos and 214.5M frames spanning endoscopy, laparoscopy, cataract, and robotic surgery.
  arXiv  Detail & Related papers  (2026-03-31T16:31:25Z)
• 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)
• EchoBench: Benchmarking Sycophancy in Medical Large Vision-Language Models [82.43729208063468]
  Recent benchmarks for medical Large Vision-Language Models (LVLMs) emphasize leaderboard accuracy, overlooking reliability and safety.<n>We study sycophancy -- models' tendency to uncritically echo user-provided information.<n>We introduce EchoBench, a benchmark to systematically evaluate sycophancy in medical LVLMs.
  arXiv  Detail & Related papers  (2025-09-24T14:09:55Z)
• Vision-Based Embedded System for Noncontact Monitoring of Preterm Infant Behavior in Low-Resource Care Settings [0.0]
  Preterm birth is a leading cause of neonatal mortality, disproportionately affecting low-resource settings with limited access to advanced neonatal intensive care units (NICUs)<n>This paper presents a novel, noninvasive, and automated vision-based framework to address this gap.<n>We introduce an embedded monitoring system that utilizes a quantized MobileNet model deployed on a Raspberry Pi for real-time behavioral state detection.
  arXiv  Detail & Related papers  (2025-09-02T07:05:47Z)
• A Modular Approach for Clinical SLMs Driven by Synthetic Data with Pre-Instruction Tuning, Model Merging, and Clinical-Tasks Alignment [46.776978552161395]
  Small language models (SLMs) offer a cost-effective alternative to large language models such as GPT-4.<n>SLMs offer a cost-effective alternative, but their limited capacity requires biomedical domain adaptation.<n>We propose a novel framework for adapting SLMs into high-performing clinical models.
  arXiv  Detail & Related papers  (2025-05-15T21:40:21Z)
• Two-Stream Thermal Imaging Fusion for Enhanced Time of Birth Detection in Neonatal Care [1.101731711817642]
  We present a two-stream fusion system that combines the power of image and video analysis to accurately detect the Time of Birth (ToB)<n>Our system achieves 95.7% precision and 84.8% recall in detecting birth within short video clips.
  arXiv  Detail & Related papers  (2025-03-05T07:52:52Z)
• AI-Based Thermal Video Analysis in Privacy-Preserving Healthcare: A Case Study on Detecting Time of Birth [1.2524536193679123]
  We present an AI-driven, video-based system for automated ToB detection using thermal imaging.<n>Our system achieves 91.4% precision and 97.4% recall in detecting ToB within thermal video clips during performance evaluation.
  arXiv  Detail & Related papers  (2025-02-05T07:01:49Z)
• PitVis-2023 Challenge: Workflow Recognition in videos of Endoscopic Pituitary Surgery [46.2901962659261]
  The Pituitary Vision (VisVis) 2023 Challenge tasks the community to step and instrument recognition in videos of endoscopic pituitary surgery. This is a unique task when compared to other minimally invasive surgeries due to the smaller working space. There were 18-s from 9-teams across 6-countries, using a variety of deep learning models.
  arXiv  Detail & Related papers  (2024-09-02T11:38:06Z)
• Localizing Moments of Actions in Untrimmed Videos of Infants with Autism Spectrum Disorder [5.2289135066938375]
  We introduce a self-attention based TAL model designed to identify ASD-related behaviors in infant videos. This study is the first to conduct end-to-end temporal action localization in untrimmed videos of infants with ASD. We achieve 70% accuracy for look face, 79% accuracy for look object, 72% for smile and 65% for vocalization.
  arXiv  Detail & Related papers  (2024-04-08T20:31:27Z)
• Evaluation of self-supervised pre-training for automatic infant movement classification using wearable movement sensors [2.995873287514728]
  The infant wearable MAIJU provides a means to automatically evaluate infants' motor performance in out-of-hospital settings. We investigated how self-supervised pre-training improves performance of the classifiers used for analyzing MAIJU recordings.
  arXiv  Detail & Related papers  (2023-05-16T11:46:16Z)
• Self-supervised contrastive learning of echocardiogram videos enables label-efficient cardiac disease diagnosis [48.64462717254158]
  We developed a self-supervised contrastive learning approach, EchoCLR, to catered to echocardiogram videos. When fine-tuned on small portions of labeled data, EchoCLR pretraining significantly improved classification performance for left ventricular hypertrophy (LVH) and aortic stenosis (AS) EchoCLR is unique in its ability to learn representations of medical videos and demonstrates that SSL can enable label-efficient disease classification from small, labeled datasets.
  arXiv  Detail & Related papers  (2022-07-23T19:17:26Z)
• 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)

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.