Knowledge Priors for Identity-Disentangled Open-Set Privacy-Preserving Video FER

TL;DR

This paper introduces a privacy-preserving video facial expression recognition framework that effectively anonymizes identities without needing identity labels, ensuring privacy and utility in open-set scenarios.

Contribution

A novel two-stage, label-free framework for open-set privacy-preserving FER that decouples privacy from utility using knowledge priors and a falsification-based validation method.

Findings

Effective privacy protection demonstrated on three datasets.

Maintains FER accuracy comparable to supervised methods.

No identity labels required at any stage.

Abstract

Facial expression recognition relies on facial data that inherently expose identity and thus raise significant privacy concerns. Current privacy-preserving methods typically fail in realistic open-set video settings where identities are unknown, and identity labels are unavailable. We propose a two-stage framework for video-based privacy-preserving FER in challenging open-set settings that requires no identity labels at any stage. To decouple privacy and utility, we first train an identity-suppression network using intra- and inter-video knowledge priors derived from real-world videos without identity labels. This network anonymizes identity while preserving expressive cues. A subsequent denoising module restores expression-related information and helps recover FER performance. Furthermore, we introduce a falsification-based validation method that uses recognition priors to rigorously evaluate privacy robustness without requiring annotated identity labels. Experiments on three video datasets demonstrate that our method effectively protects privacy while maintaining FER accuracy comparable to identity-supervised baselines.