# Comparison of marker-less 2D image-based methods for infant pose estimation

arXiv: https://arxiv.org/abs/2410.04980 · HTML: https://mlsanity.com/paper/2410.04980/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 65 references that are in the map.
- First posted on arXiv 7 Oct 2024.

## Builds on (most cited first, 19 of 19)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Deep High-Resolution Representation Learning for Visual Recognition](https://mlsanity.com/paper/1908.07919/) (2019)
- [Deep High-Resolution Representation Learning for Human Pose Estimation](https://mlsanity.com/paper/1902.09212/) (2019)
- [OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1812.08008/) (2018)
- [Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1611.08050/) (2016)
- [ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation](https://mlsanity.com/paper/2204.12484/) (2022)
- [Convolutional Pose Machines](https://mlsanity.com/paper/1602.00134/) (2016)
- [Markerless tracking of user-defined features with deep learning](https://mlsanity.com/paper/1804.03142/) (2018)
- [BlazePose: On-device Real-time Body Pose tracking](https://mlsanity.com/paper/2006.10204/) (2020)
- [Invariant Representation Learning for Infant Pose Estimation with Small Data](https://mlsanity.com/paper/2010.06100/) (2020)
- [AggPose: Deep Aggregation Vision Transformer for Infant Pose Estimation](https://mlsanity.com/paper/2205.05277/) (2022)
- [A Spatio-temporal Attention-based Model for Infant Movement Assessment from Videos](https://mlsanity.com/paper/2105.09783/) (2021)
- [Preterm infants' pose estimation with spatio-temporal features](https://mlsanity.com/paper/2005.08648/) (2020)
- [Efficient Domain Adaptation via Generative Prior for 3D Infant Pose Estimation](https://mlsanity.com/paper/2311.12043/) (2023)
- [EfficientPose: Scalable single-person pose estimation](https://mlsanity.com/paper/2004.12186/) (2020)
- [Automatic infant 2D pose estimation from videos: comparing seven deep neural network methods](https://mlsanity.com/paper/2406.17382/) (2024)
- [Deep learning empowered sensor fusion boosts infant movement classification](https://mlsanity.com/paper/2406.09014/) (2024)
- [Open video data sharing in developmental and behavioural science](https://mlsanity.com/paper/2207.11020/) (2022)
- [Mobile solutions for clinical surveillance and evaluation in infancy -- General Movement Apps](https://mlsanity.com/paper/2303.14699/) (2023)

## Built on by (most cited first, 2 of 2)

- [Markerless Motion Capture for Biomechanical Whole-Body Kinematic Estimation in Infants](https://mlsanity.com/paper/2605.17120/) (2026)
- [The Blind Spot in 2D Infants' Pose Estimation:Robust Learning from Noisy Annotations](https://mlsanity.com/paper/2609.04009/) (2026)

## Abstract (arXiv)

In this study we compare the performance of available generic- and infant-pose estimators for a video-based automated general movement assessment (GMA), and the choice of viewing angle for optimal recordings, i.e., conventional diagonal view used in GMA vs. top-down view. We used 4500 annotated video-frames from 75 recordings of infant spontaneous motor functions from 4 to 26 weeks. To determine which pose estimation method and camera angle yield the best pose estimation accuracy on infants in a GMA related setting, the distance to human annotations and the percentage of correct key-points (PCK) were computed and compared. The results show that the best performing generic model trained on adults, ViTPose, also performs best on infants. We see no improvement from using infant-pose estimators over the generic pose estimators on our infant dataset. However, when retraining a generic model on our data, there is a significant improvement in pose estimation accuracy. The pose estimation accuracy obtained from the top-down view is significantly better than that obtained from the diagonal view, especially for the detection of the hip key-points. The results also indicate limited generalization capabilities of infant-pose estimators to other infant datasets, which hints that one should be careful when choosing infant pose estimators and using them on infant datasets which they were not trained on. While the standard GMA method uses a diagonal view for assessment, pose estimation accuracy significantly improves using a top-down view. This suggests that a top-down view should be included in recording setups for automated GMA research.