# Privacy-Preserving Action Recognition via Motion Difference Quantization

arXiv: https://arxiv.org/abs/2208.02459 · HTML: https://mlsanity.com/paper/2208.02459/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 39 references that are in the map.
- First posted on arXiv 4 Aug 2022.

## Builds on (most cited first, 23 of 23)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation](https://mlsanity.com/paper/1606.06650/) (2016)
- [TDN: Temporal Difference Networks for Efficient Action Recognition](https://mlsanity.com/paper/2012.10071/) (2020)
- [Video to Events: Recycling Video Datasets for Event Cameras](https://mlsanity.com/paper/1912.03095/) (2019)
- [TEA: Temporal Excitation and Aggregation for Action Recognition](https://mlsanity.com/paper/2004.01398/) (2020)
- [Quantization Networks](https://mlsanity.com/paper/1911.09464/) (2019)
- [STM: SpatioTemporal and Motion Encoding for Action Recognition](https://mlsanity.com/paper/1908.02486/) (2019)
- [Towards a Visual Privacy Advisor: Understanding and Predicting Privacy Risks in Images](https://mlsanity.com/paper/1703.10660/) (2017)
- [TEINet: Towards an Efficient Architecture for Video Recognition](https://mlsanity.com/paper/1911.09435/) (2019)
- [Learning to Anonymize Faces for Privacy Preserving Action Detection](https://mlsanity.com/paper/1803.11556/) (2018)
- [Towards Privacy-Preserving Visual Recognition via Adversarial Training: A Pilot Study](https://mlsanity.com/paper/1807.08379/) (2018)
- [Mitigating Information Leakage in Image Representations: A Maximum Entropy Approach](https://mlsanity.com/paper/1904.05514/) (2019)
- [SPAct: Self-supervised Privacy Preservation for Action Recognition](https://mlsanity.com/paper/2203.15205/) (2022)
- [Privacy-Preserving Human Activity Recognition from Extreme Low Resolution](https://mlsanity.com/paper/1604.03196/) (2016)
- [Learning Privacy Preserving Encodings through Adversarial Training](https://mlsanity.com/paper/1802.05214/) (2018)
- [IPN Hand: A Video Dataset and Benchmark for Real-Time Continuous Hand Gesture Recognition](https://mlsanity.com/paper/2005.02134/) (2020)
- [Privacy-Preserving Action Recognition using Coded Aperture Videos](https://mlsanity.com/paper/1902.09085/) (2019)
- [Human Pose Estimation on Privacy-Preserving Low-Resolution Depth Images](https://mlsanity.com/paper/2007.08340/) (2020)
- [Extreme Low Resolution Activity Recognition with Multi-Siamese Embedding Learning](https://mlsanity.com/paper/1708.00999/) (2017)
- [Generative Adversarial Privacy](https://mlsanity.com/paper/1807.05306/) (2018)
- [FlowSAN: Privacy-enhancing Semi-Adversarial Networks to Confound Arbitrary Face-based Gender Classifiers](https://mlsanity.com/paper/1905.01388/) (2019)

## Built on by (most cited first, 14 of 14)

- [Bullying10K: A Large-Scale Neuromorphic Dataset towards Privacy-Preserving Bullying Recognition](https://mlsanity.com/paper/2306.11546/) (2023)
- [Person Re-Identification without Identification via Event Anonymization](https://mlsanity.com/paper/2308.04402/) (2023)
- [Selective, Interpretable, and Motion Consistent Privacy Attribute Obfuscation for Action Recognition](https://mlsanity.com/paper/2403.12710/) (2024)
- [Privacy-Preserving Visual Localization with Event Cameras](https://mlsanity.com/paper/2212.03177/) (2022)
- [Privacy-preserving Optics for Enhancing Protection in Face De-identification](https://mlsanity.com/paper/2404.00777/) (2024)
- [MaSS: Multi-attribute Selective Suppression for Utility-preserving Data Transformation from an Information-theoretic Perspective](https://mlsanity.com/paper/2405.14981/) (2024)
- [AnonyNoise: Anonymizing Event Data with Smart Noise to Outsmart Re-Identification and Preserve Privacy](https://mlsanity.com/paper/2411.16440/) (2024)
- [PASS: Private Attributes Protection with Stochastic Data Substitution](https://mlsanity.com/paper/2506.07308/) (2025)
- [Privacy Beyond Pixels: Latent Anonymization for Privacy-Preserving Video Understanding](https://mlsanity.com/paper/2511.08666/) (2025)
- [POET: Prompt Offset Tuning for Continual Human Action Adaptation](https://mlsanity.com/paper/2504.18059/) (2025)
- [Privacy in Image Datasets: A Case Study on Pregnancy Ultrasounds](https://mlsanity.com/paper/2602.07149/) (2026)
- [PrivHAR-Bench: A Graduated Privacy Benchmark Dataset for Video-Based Action Recognition](https://mlsanity.com/paper/2604.00761/) (2026)
- [CFE-PPAR: Compression-friendly encryption for privacy-preserving action recognition leveraging video transformers](https://mlsanity.com/paper/2605.05692/) (2026)
- [Privacy-Preserving Action Recognition: Taxonomy, Methods, and Privacy-Utility Trade-offs](https://mlsanity.com/paper/2608.04501/) (2026)

## Abstract (arXiv)

The widespread use of smart computer vision systems in our personal spaces has led to an increased consciousness about the privacy and security risks that these systems pose. On the one hand, we want these systems to assist in our daily lives by understanding their surroundings, but on the other hand, we want them to do so without capturing any sensitive information. Towards this direction, this paper proposes a simple, yet robust privacy-preserving encoder called BDQ for the task of privacy-preserving human action recognition that is composed of three modules: Blur, Difference, and Quantization. First, the input scene is passed to the Blur module to smoothen the edges. This is followed by the Difference module to apply a pixel-wise intensity subtraction between consecutive frames to highlight motion features and suppress obvious high-level privacy attributes. Finally, the Quantization module is applied to the motion difference frames to remove the low-level privacy attributes. The BDQ parameters are optimized in an end-to-end fashion via adversarial training such that it learns to allow action recognition attributes while inhibiting privacy attributes. Our experiments on three benchmark datasets show that the proposed encoder design can achieve state-of-the-art trade-off when compared with previous works. Furthermore, we show that the trade-off achieved is at par with the DVS sensor-based event cameras. Code available at: https://github.com/suakaw/BDQ_PrivacyAR.