Automated Vision-Based Sensing of Paediatric Pain Using 2D-Facial Landmark Trajectories Derived from 3D Geometric Normalisation and a Spatial-Temporal Attention Long Short-Term Memory (STA-LSTM) Network
Teddy Fabila, Tiehua Du, Chin Wen Tan, Rehena Sultana, Choon Looi Bong, Ban Leong Sng · 2026
Read Automated Vision-Based Sensing of Paediatric Pain Using 2D-Facial Landmark Trajectories Derived from 3D Geometric Normalisation and a Spatial-Temporal Attention Long Short-Term Memory (STA-LSTM) Network by Teddy Fabila, Tiehua Du, Chin Wen Tan, Rehena Sultana, Choon Looi Bong, Ban Leong Sng (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13611101.txt.
Description
Fabila and coauthors build a camera system that spots pain in children. Pain checks in children rest on staff judgment and can miss shifts. A camera tool could watch pain signs nonstop at the bedside. The team used face point tracks from video clips.
They filmed 125 children aged 6 to 17 around planned surgery. An app on a phone took front face videos. Software mapped near 500 face points in each frame. Depth checks cleaned the point tracks for fair contrast. A smart network then learned pain patterns over time. The goal is fast, fair pain flags for care teams.
Catalog record
| CREATOR | Teddy Fabila, Tiehua Du, Chin Wen Tan, Rehena Sultana, Choon Looi Bong, Ban Leong Sng |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 32 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |