Recoverable Anonymization for Pose Estimation: A Privacy-Enhancing Approach
Not on the map. Why?
Abstract (arXiv)
Human pose estimation (HPE) is crucial for various applications. However, deploying HPE algorithms in surveillance contexts raises significant privacy concerns due to the potential leakage of sensitive personal information (SPI) such as facial features, and ethnicity. Existing privacy-enhancing methods often compromise either privacy or performance, or they require costly additional modalities. We propose a novel privacy-enhancing system that generates privacy-enhanced portraits while maintaining high HPE performance. Our key innovations include the reversible recovery of SPI for authorized personnel and the preservation of contextual information. By jointly optimizing a privacy-enhancing module, a privacy recovery module, and a pose estimator, our system ensures robust privacy protection, efficient SPI recovery, and high-performance HPE. Experimental results demonstrate the system's robust performance in privacy enhancement, SPI recovery, and HPE.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 40 of its 75 references that are in the map. First posted on arXiv 1 Sep 2024.
Builds on
40 of 75 references.
References · 40
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
- 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
- 2014Microsoft COCO: Common Objects in Contextcited by 17,498
- 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
- 2014Conditional Generative Adversarial Netscited by 2,152
- 2017Cascaded Pyramid Network for Multi-Person Pose Estimationcited by 341
- 2013DeepPose: Human Pose Estimation via Deep Neural Networkscited by 305
- 2014Efficient Object Localization Using Convolutional Networkscited by 226
- 2020TransPose: Keypoint Localization via Transformercited by 126
- 2019DeepPrivacy: A Generative Adversarial Network for Face Anonymizationcited by 108
- 2021TokenPose: Learning Keypoint Tokens for Human Pose Estimationcited by 106
- 2021Pose Recognition with Cascade Transformerscited by 99
28 more
- 2020Rethinking the Heatmap Regression for Bottom-up Human Pose Estimationcited by 69
- 2020Learning Delicate Local Representations for Multi-Person Pose Estimationcited by 65
- 2018Devil in the Details: Towards Accurate Single and Multiple Human Parsingcited by 64
- 2018Learning to Anonymize Faces for Privacy Preserving Action Detectioncited by 63
- 2022Towards a Deeper Understanding of Skeleton-based Gait Recognitioncited by 55
- 2022DeepPrivacy2: Towards Realistic Full-Body Anonymizationcited by 51
- 2019Live Face De-Identification in Videocited by 48
- 2022SPAct: Self-supervised Privacy Preservation for Action Recognitioncited by 47
- 2023Human Pose as Compositional Tokenscited by 45
- 2016Privacy-Preserving Human Activity Recognition from Extreme Low Resolutioncited by 43
- 2022Poseur: Direct Human Pose Regression with Transformerscited by 43
- 2019Adversarial Learning of Privacy-Preserving and Task-Oriented Representationscited by 35
- 2020Graph-PCNN: Two Stage Human Pose Estimation with Graph Pose Refinementcited by 33
- 2020High-Fidelity Neural Human Motion Transfer from Monocular Videocited by 31
- 2024Credit Card Fraud Detection Using Advanced Transformer Modelcited by 26
- 2014Articulated Pose Estimation by a Graphical Model with Image Dependent Pairwise Relationscited by 24
- 2024TaskCLIP: Extend Large Vision-Language Model for Task Oriented Object Detectioncited by 21
- 2020Human Pose Estimation on Privacy-Preserving Low-Resolution Depth Imagescited by 16
- 2023Person Re-Identification without Identification via Event Anonymizationcited by 16
- 2013Beyond Physical Connections: Tree Models in Human Pose Estimationcited by 14
- 2024MissionGNN: Hierarchical Multimodal GNN-based Weakly Supervised Video Anomaly Recognition with Mission-Specific Knowledge Graph Generationcited by 14
- 2024Advanced User Credit Risk Prediction Model using LightGBM, XGBoost and Tabnet with SMOTEENNcited by 10
- 2024Advanced Payment Security System:XGBoost, LightGBM and SMOTE Integratedcited by 8
- 2021In-Bed Human Pose Estimation from Unseen and Privacy-Preserving Image Domainscited by 7
- 2024HyperSense: Hyperdimensional Intelligent Sensing for Energy-Efficient Sparse Data Processingcited by 7
- 2021OmniPose: A Multi-Scale Framework for Multi-Person Pose Estimationcited by 6
- 2024Privacy-preserving Optics for Enhancing Protection in Face De-identificationcited by 4
- 2024EcoSense: Energy-Efficient Intelligent Sensing for In-Shore Ship Detection through Edge-Cloud Collaborationcited by 1
Built on by
Citing papers per year: 2024: 1; 2025: 0; 2026: 1.
2 papers.