mlsanityData to 14 Oct 2026

NurtureNet: A Multi-task Video-based Approach for Newborn Anthropometry

arXiv 2405.05530 ↗First posted 9 May 2024cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Malnutrition among newborns is a top public health concern in developing countries. Identification and subsequent growth monitoring are key to successful interventions. However, this is challenging in rural communities where health systems tend to be inaccessible and under-equipped, with poor adherence to protocol. Our goal is to equip health workers and public health systems with a solution for contactless newborn anthropometry in the community. We propose NurtureNet, a multi-task model that fuses visual information (a video taken with a low-cost smartphone) with tabular inputs to regress multiple anthropometry estimates including weight, length, head circumference, and chest circumference. We show that visual proxy tasks of segmentation and keypoint prediction further improve performance. We establish the efficacy of the model through several experiments and achieve a relative error of 3.9% and mean absolute error of 114.3 g for weight estimation. Model compression to 15 MB also allows offline deployment to low-cost smartphones.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 24 of its 75 references that are in the map. First posted on arXiv 9 May 2024.

Builds on

24 of 75 references.

References · 24

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  4. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,548
  5. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  6. 2017End-to-end Recovery of Human Shape and Posecited by 885
  7. 2018Pixel2Mesh: Generating 3D Mesh Models from Single RGB Imagescited by 651
  8. 2017Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentationscited by 620
  9. 2015Multi-view Convolutional Neural Networks for 3D Shape Recognitioncited by 565
  10. 2019PointRend: Image Segmentation as Renderingcited by 440
  11. 2020End-to-End Human Pose and Mesh Reconstruction with Transformerscited by 418
  12. 2019Which Tasks Should Be Learned Together in Multi-task Learning?cited by 375
12 more
  1. 2017Temporal Relational Reasoning in Videoscited by 324
  2. 2019Convolutional Mesh Regression for Single-Image Human Shape Reconstructioncited by 270
  3. 2020Pose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human Posecited by 248
  4. 2021Probabilistic Modeling for Human Mesh Recoverycited by 153
  5. 2020Coherent Reconstruction of Multiple Humans from a Single Imagecited by 136
  6. 2020Invariant Representation Learning for Infant Pose Estimation with Small Datacited by 20
  7. 2022AggPose: Deep Aggregation Vision Transformer for Infant Pose Estimationcited by 13
  8. 2020Towards human-level performance on automatic pose estimation of infant spontaneous movementscited by 10
  9. 2020Preterm infants' pose estimation with spatio-temporal featurescited by 9
  10. 2022Under the Cover Infant Pose Estimation using Multimodal Datacited by 6
  11. 2022Semi-supervised Body Parsing and Pose Estimation for Enhancing Infant General Movement Assessmentcited by 6
  12. 2021Height Estimation of Children under Five Years using Depth Imagescited by 1

Built on by

Not cited yet.