Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Transformer with Leveraged Masked Autoencoder for video-based Pain Assessment

Minh-Duc Nguyen, Hyung-Jeong Yang, Soo-Hyung Kim, Ji-Eun Shin, Seung-Won Kim

TL;DR

This paper enhances pain recognition by employing facial video analysis within a Transformer-based deep learning model, combining a powerful Masked Autoencoder with a Transformers-based classifier that effectively captures pain level indicators through both expressions and micro-expressions.

Abstract

Accurate pain assessment is crucial in healthcare for effective diagnosis and treatment; however, traditional methods relying on self-reporting are inadequate for populations unable to communicate their pain. Cutting-edge AI is promising for supporting clinicians in pain recognition using facial video data. In this paper, we enhance pain recognition by employing facial video analysis within a Transformer-based deep learning model. By combining a powerful Masked Autoencoder with a Transformers-based classifier, our model effectively captures pain level indicators through both expressions and micro-expressions. We conducted our experiment on the AI4Pain dataset, which produced promising results that pave the way for innovative healthcare solutions that are both comprehensive and objective.

Transformer with Leveraged Masked Autoencoder for video-based Pain Assessment

TL;DR

This paper enhances pain recognition by employing facial video analysis within a Transformer-based deep learning model, combining a powerful Masked Autoencoder with a Transformers-based classifier that effectively captures pain level indicators through both expressions and micro-expressions.

Abstract

Accurate pain assessment is crucial in healthcare for effective diagnosis and treatment; however, traditional methods relying on self-reporting are inadequate for populations unable to communicate their pain. Cutting-edge AI is promising for supporting clinicians in pain recognition using facial video data. In this paper, we enhance pain recognition by employing facial video analysis within a Transformer-based deep learning model. By combining a powerful Masked Autoencoder with a Transformers-based classifier, our model effectively captures pain level indicators through both expressions and micro-expressions. We conducted our experiment on the AI4Pain dataset, which produced promising results that pave the way for innovative healthcare solutions that are both comprehensive and objective.
Paper Structure (16 sections, 6 equations, 2 figures, 3 tables)

This paper contains 16 sections, 6 equations, 2 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Related Works
  3. Proposal Method
  4. Spatio-temporal Feature Compression
  5. Residual Transformer Classifier
  6. Absolute position encoding.
  7. Relative position encoding.
  8. Convolutional Transformer Model.
  9. Framework Architecture.
  10. Experiments
  11. Dataset.
  12. Experiment Settings.
  13. Results.
  14. Conclusion
  15. Ethical Impact Statement.
  16. ...and 1 more sections

Figures (2)

  • Figure 1: MARLIN Pre-training Marlin.
  • Figure 2: Overall of Proposed architecture