# Fusing Deep Learned and Hand-Crafted Features of Appearance, Shape, and Dynamics for Automatic Pain Estimation

arXiv: https://arxiv.org/abs/1701.04540 · HTML: https://mlsanity.com/paper/1701.04540/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Jan 2017.

## Built on by (most cited first, 5 of 5)

- [Faces of Experimental Pain: Transferability of Deep Learned Heat Pain Features to Electrical Pain](https://mlsanity.com/paper/2406.11808/) (2024)
- [Personalized Federated Deep Learning for Pain Estimation From Face Images](https://mlsanity.com/paper/2101.04800/) (2021)
- [Unobtrusive Pain Monitoring in Older Adults with Dementia using Pairwise and Contrastive Training](https://mlsanity.com/paper/2101.03251/) (2021)
- [Do Deep Neural Networks Forget Facial Action Units? -- Exploring the Effects of Transfer Learning in Health Related Facial Expression Recognition](https://mlsanity.com/paper/2104.07389/) (2021)
- [FRANS: Automatic Feature Extraction for Time Series Forecasting](https://mlsanity.com/paper/2209.07018/) (2022)

## Abstract (arXiv)

Automatic continuous time, continuous value assessment of a patient's pain from face video is highly sought after by the medical profession. Despite the recent advances in deep learning that attain impressive results in many domains, pain estimation risks not being able to benefit from this due to the difficulty in obtaining data sets of considerable size. In this work we propose a combination of hand-crafted and deep-learned features that makes the most of deep learning techniques in small sample settings. Encoding shape, appearance, and dynamics, our method significantly outperforms the current state of the art, attaining a RMSE error of less than 1 point on a 16-level pain scale, whilst simultaneously scoring a 67.3% Pearson correlation coefficient between our predicted pain level time series and the ground truth.