# SafeTriage: Facial Video De-identification for Privacy-Preserving Stroke Triage

arXiv: https://arxiv.org/abs/2506.16578 · HTML: https://mlsanity.com/paper/2506.16578/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 39 references that are in the map.
- First posted on arXiv 19 Jun 2025.

## Builds on (most cited first, 26 of 26)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [Visual Prompt Tuning](https://mlsanity.com/paper/2203.12119/) (2022)
- [BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models](https://mlsanity.com/paper/2106.10199/) (2021)
- [Alias-Free Generative Adversarial Networks](https://mlsanity.com/paper/2106.12423/) (2021)
- [AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition](https://mlsanity.com/paper/2205.13535/) (2022)
- [First Order Motion Model for Image Animation](https://mlsanity.com/paper/2003.00196/) (2020)
- [One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencing](https://mlsanity.com/paper/2011.15126/) (2020)
- [Few-Shot Adversarial Learning of Realistic Neural Talking Head Models](https://mlsanity.com/paper/1905.08233/) (2019)
- [Motion Representations for Articulated Animation](https://mlsanity.com/paper/2104.11280/) (2021)
- [Towards Robust Blind Face Restoration with Codebook Lookup Transformer](https://mlsanity.com/paper/2206.11253/) (2022)
- [LivePortrait: Efficient Portrait Animation with Stitching and Retargeting Control](https://mlsanity.com/paper/2407.03168/) (2024)
- [Medical Image Synthesis for Data Augmentation and Anonymization using Generative Adversarial Networks](https://mlsanity.com/paper/1807.10225/) (2018)
- [Unsupervised Semantic Correspondence Using Stable Diffusion](https://mlsanity.com/paper/2305.15581/) (2023)
- [Conv-Adapter: Exploring Parameter Efficient Transfer Learning for ConvNets](https://mlsanity.com/paper/2208.07463/) (2022)
- [SPAct: Self-supervised Privacy Preservation for Action Recognition](https://mlsanity.com/paper/2203.15205/) (2022)
- [GAN-Based Data Augmentation and Anonymization for Skin-Lesion Analysis: A Critical Review](https://mlsanity.com/paper/2104.10603/) (2021)
- [DeepStroke: An Efficient Stroke Screening Framework for Emergency Rooms with Multimodal Adversarial Deep Learning](https://mlsanity.com/paper/2109.12065/) (2021)
- [FaceOff: Anonymizing Videos in the Operating Rooms](https://mlsanity.com/paper/1808.04440/) (2018)
- [Anonymizing medical case-based explanations through disentanglement](https://mlsanity.com/paper/2311.04833/) (2023)
- [3D-Aware Talking-Head Video Motion Transfer](https://mlsanity.com/paper/2311.02549/) (2023)
- [DiffSLVA: Harnessing Diffusion Models for Sign Language Video Anonymization](https://mlsanity.com/paper/2311.16060/) (2023)

## Built on by (most cited first, 3 of 3)

- [Privacy-Preserving Semantic Segmentation from Ultra-Low-Resolution RGB Inputs](https://mlsanity.com/paper/2507.16034/) (2025)
- [Digital FAST: An AI-Driven Multimodal Framework for Rapid and Early Stroke Screening](https://mlsanity.com/paper/2601.11896/) (2026)
- [ReGenHuman: Re-Generating Human Appearances for Realistic Full-Body Video Anonymization](https://mlsanity.com/paper/2606.14972/) (2026)

## Abstract (arXiv)

Effective stroke triage in emergency settings often relies on clinicians' ability to identify subtle abnormalities in facial muscle coordination. While recent AI models have shown promise in detecting such patterns from patient facial videos, their reliance on real patient data raises significant ethical and privacy challenges -- especially when training robust and generalizable models across institutions. To address these concerns, we propose SafeTriage, a novel method designed to de-identify patient facial videos while preserving essential motion cues crucial for stroke diagnosis. SafeTriage leverages a pretrained video motion transfer (VMT) model to map the motion characteristics of real patient faces onto synthetic identities. This approach retains diagnostically relevant facial dynamics without revealing the patients' identities. To mitigate the distribution shift between normal population pre-training videos and patient population test videos, we introduce a conditional generative model for visual prompt tuning, which adapts the input space of the VMT model to ensure accurate motion transfer without needing to fine-tune the VMT model backbone. Comprehensive evaluation, including quantitative metrics and clinical expert assessments, demonstrates that SafeTriage-produced synthetic videos effectively preserve stroke-relevant facial patterns, enabling reliable AI-based triage. Our evaluations also show that SafeTriage provides robust privacy protection while maintaining diagnostic accuracy, offering a secure and ethically sound foundation for data sharing and AI-driven clinical analysis in neurological disorders.