用于身份解耦的隐私保护视频情感识别先验知识
Knowledge Priors for Identity-Disentangled Open-Set Privacy-Preserving Video FER
AI总结：
本文提出一种两阶段框架，在无需身份标签的情况下，通过身份抑制网络和去噪模块实现隐私保护的视频情感识别，同时引入验证方法评估隐私鲁棒性。
摘要：
面部表情识别依赖于面部数据，而这些数据本质上暴露了身份，从而引发重大隐私问题。当前隐私保护方法在现实中的开放集视频设置中通常失效，特别是在身份未知且身份标签不可用的情况下。我们提出了一种两阶段框架，用于在具有挑战性的开放集设置中进行基于视频的隐私保护情感识别，该框架在任何阶段都不需要身份标签。为了将隐私与实用性分开，我们首先使用从现实视频中提取的内在和跨视频知识先验来训练身份抑制网络。该网络在匿名化身份的同时保留了表达线索。随后的去噪模块恢复与表情相关的信息，并帮助恢复情感识别性能。此外，我们引入了一种基于欺骗的验证方法，利用识别先验来严格评估隐私鲁棒性，而无需注释的身份标签。在三个视频数据集上的实验表明，我们的方法在保护隐私的同时，情感识别准确性与有身份监督的基线相当。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
