mlsanityData to 14 Oct 2026

PrivHAR: Recognizing Human Actions From Privacy-preserving Lens

arXiv 2206.03891 ↗First posted 8 Jun 2022cs.CV cs.AI cs.CRcited by 16

Not on the map. Why?

Abstract (arXiv)

The accelerated use of digital cameras prompts an increasing concern about privacy and security, particularly in applications such as action recognition. In this paper, we propose an optimizing framework to provide robust visual privacy protection along the human action recognition pipeline. Our framework parameterizes the camera lens to successfully degrade the quality of the videos to inhibit privacy attributes and protect against adversarial attacks while maintaining relevant features for activity recognition. We validate our approach with extensive simulations and hardware experiments.

Key facts. Cited by 16 papers in the map (data through 14 Oct 2026). Builds on 26 of its 60 references that are in the map. First posted on arXiv 8 Jun 2022.

Builds on

26 of 60 references.

References · 26

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
  3. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
  4. 2014Going Deeper with Convolutionscited by 4,241
  5. 2021On the Opportunities and Risks of Foundation Modelscited by 4,033
  6. 2016Wide Residual Networkscited by 3,070
  7. 2016Xception: Deep Learning with Depthwise Separable Convolutionscited by 2,332
  8. 2018OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,162
  9. 2018MnasNet: Platform-Aware Neural Architecture Search for Mobilecited by 943
  10. 2016Temporal Segment Networks: Towards Good Practices for Deep Action Recognitioncited by 902
  11. 2016MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognitioncited by 624
  12. 2019DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Bettercited by 362
14 more
  1. 2019Video Classification with Channel-Separated Convolutional Networkscited by 290
  2. 2017Towards a Visual Privacy Advisor: Understanding and Predicting Privacy Risks in Imagescited by 101
  3. 2016Spatiotemporal Residual Networks for Video Action Recognitioncited by 91
  4. 2020Spatiotemporal Relationship Reasoning for Pedestrian Intent Predictioncited by 71
  5. 2020Counting Out Time: Class Agnostic Video Repetition Counting in the Wildcited by 68
  6. 2018Learning to Anonymize Faces for Privacy Preserving Action Detectioncited by 63
  7. 2019Deep Optics for Single-shot High-dynamic-range Imagingcited by 62
  8. 2019Resource Efficient 3D Convolutional Neural Networkscited by 50
  9. 2018Towards Privacy-Preserving Visual Recognition via Adversarial Training: A Pilot Studycited by 48
  10. 2022SPAct: Self-supervised Privacy Preservation for Action Recognitioncited by 47
  11. 2016Privacy-Preserving Human Activity Recognition from Extreme Low Resolutioncited by 43
  12. 2018Learning Privacy Preserving Encodings through Adversarial Trainingcited by 30
  13. 2019Privacy-Preserving Action Recognition using Coded Aperture Videoscited by 20
  14. 2017Extreme Low Resolution Activity Recognition with Multi-Siamese Embedding Learningcited by 15

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 4; 2024: 3; 2025: 4; 2026: 5.

16 papers.

Sort:

  1. 2023TeD-SPAD: Temporal Distinctiveness for Self-supervised Privacy-preservation for video Anomaly Detectioncited by 23
  2. 2023Person Re-Identification without Identification via Event Anonymizationcited by 16
  3. 2024Selective, Interpretable, and Motion Consistent Privacy Attribute Obfuscation for Action Recognitioncited by 8
  4. 2024Privacy-preserving Optics for Enhancing Protection in Face De-identificationcited by 4
  5. 2025EgoPrivacy: What Your First-Person Camera Says About You?cited by 4
  6. 2023Sparse and Privacy-enhanced Representation for Human Pose Estimationcited by 2
  7. 2023CamPro: Camera-based Anti-Facial Recognitioncited by 2
  8. 2024OpticalDR: A Deep Optical Imaging Model for Privacy-Protective Depression Recognitioncited by 2
  9. 2025Privacy Beyond Pixels: Latent Anonymization for Privacy-Preserving Video Understandingcited by 1
  10. 2025POET: Prompt Offset Tuning for Continual Human Action Adaptationcited by 0
  11. 2025Unmasking Performance Gaps: A Comparative Study of Human Anonymization and Its Effects on Video Anomaly Detectioncited by 0
  12. 2026PrivHAR-Bench: A Graduated Privacy Benchmark Dataset for Video-Based Action Recognitioncited by 0
4 more
  1. 2026DAP: Doppler-aware Point Network for Heterogeneous mmWave Action Recognitioncited by 0
  2. 2026Lens Privacy Sealing: A New Benchmark and Method for Physical Privacy-Preserving Action Recognitioncited by 0
  3. 2026Face De-Identification: A Domain-Centric Survey from Capture to Processingcited by 0
  4. 2026Privacy-Preserving Action Recognition: Taxonomy, Methods, and Privacy-Utility Trade-offscited by 0