mlsanityData to 14 Oct 2026

Privacy-Preserving Human Activity Recognition from Extreme Low Resolution

arXiv 1604.03196 ↗First posted 12 Apr 2016cs.CVcited by 43

Not on the map. Why?

Abstract (arXiv)

Privacy protection from surreptitious video recordings is an important societal challenge. We desire a computer vision system (e.g., a robot) that can recognize human activities and assist our daily life, yet ensure that it is not recording video that may invade our privacy. This paper presents a fundamental approach to address such contradicting objectives: human activity recognition while only using extreme low-resolution (e.g., 16x12) anonymized videos. We introduce the paradigm of inverse super resolution (ISR), the concept of learning the optimal set of image transformations to generate multiple low-resolution (LR) training videos from a single video. Our ISR learns different types of sub-pixel transformations optimized for the activity classification, allowing the classifier to best take advantage of existing high-resolution videos (e.g., YouTube videos) by creating multiple LR training videos tailored for the problem. We experimentally confirm that the paradigm of inverse super resolution is able to benefit activity recognition from extreme low-resolution videos.

Key facts. Cited by 43 papers in the map (data through 14 Oct 2026). First posted on arXiv 12 Apr 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 9; 2022: 8; 2023: 10; 2024: 4; 2025: 7; 2026: 5.

43 papers.

Sort:

  1. 2023An Outlook into the Future of Egocentric Visioncited by 84
  2. 2021A Study of Face Obfuscation in ImageNetcited by 83
  3. 2022SPAct: Self-supervised Privacy Preservation for Action Recognitioncited by 47
  4. 2023STPrivacy: Spatio-Temporal Privacy-Preserving Action Recognitioncited by 29
  5. 2021IdentityDP: Differential Private Identification Protection for Face Imagescited by 24
  6. 2023TeD-SPAD: Temporal Distinctiveness for Self-supervised Privacy-preservation for video Anomaly Detectioncited by 23
  7. 2023Bullying10K: A Large-Scale Neuromorphic Dataset towards Privacy-Preserving Bullying Recognitioncited by 17
  8. 2023Instance Tracking in 3D Scenes from Egocentric Videoscited by 17
  9. 2022PrivHAR: Recognizing Human Actions From Privacy-preserving Lenscited by 16
  10. 2021Generative Adversarial Networks: A Survey Towards Private and Secure Applicationscited by 15
  11. 2022Privacy-Preserving Action Recognition via Motion Difference Quantizationcited by 14
  12. 2021Privacy-Preserving Video Classification with Convolutional Neural Networkscited by 10
31 more
  1. 2021Analysis and Mitigations of Reverse Engineering Attacks on Local Feature Descriptorscited by 10
  2. 2023Differentially Private Video Activity Recognitioncited by 9
  3. 2024Selective, Interpretable, and Motion Consistent Privacy Attribute Obfuscation for Action Recognitioncited by 8
  4. 2021When Crowdsensing Meets Federated Learning: Privacy-Preserving Mobile Crowdsensing Systemcited by 7
  5. 2021Unsupervised domain adaptation for clinician pose estimation and instance segmentation in the operating roomcited by 7
  6. 2022Privacy-Preserving Person Detection Using Low-Resolution Infrared Camerascited by 7
  7. 2023Modeling the Trade-off of Privacy Preservation and Activity Recognition on Low-Resolution Imagescited by 6
  8. 2021Foreground-Aware Stylization and Consensus Pseudo-Labeling for Domain Adaptation of First-Person Hand Segmentationcited by 5
  9. 20233D-Aware Adversarial Makeup Generation for Facial Privacy Protectioncited by 5
  10. 2024An Unsupervised Approach for Periodic Source Detection in Time Seriescited by 5
  11. 2022Optical Flow for Video Super-Resolution: A Surveycited by 4
  12. 2024Privacy-preserving Optics for Enhancing Protection in Face De-identificationcited by 4
  13. 2025Balancing Privacy and Action Performance: A Penalty-Driven Approach to Image Anonymizationcited by 4
  14. 2025EgoPrivacy: What Your First-Person Camera Says About You?cited by 4
  15. 2022Privacy-Enhancing Optical Embeddings for Lensless Classificationcited by 3
  16. 2025Video-DPRP: A Differentially Private Approach for Visual Privacy-Preserving Video Human Activity Recognitioncited by 3
  17. 2023Sparse and Privacy-enhanced Representation for Human Pose Estimationcited by 2
  18. 2023CamPro: Camera-based Anti-Facial Recognitioncited by 2
  19. 2024Recoverable Anonymization for Pose Estimation: A Privacy-Enhancing Approachcited by 2
  20. 2026From Pixels to Privacy: Temporally Consistent Video Anonymization via Token Pruning for Privacy Preserving Action Recognitioncited by 2
  21. 2021Privacy-preserving Object Detectioncited by 1
  22. 2025Privacy Beyond Pixels: Latent Anonymization for Privacy-Preserving Video Understandingcited by 1
  23. 2025StegaVAR: Privacy-Preserving Video Action Recognition via Steganographic Domain Analysiscited by 1
  24. 2022Debiased-CAM to mitigate systematic error with faithful visual explanations of machine learningcited by 0
  25. 2022Scale Invariant Privacy Preserving Video via Wavelet Decompositioncited by 0
  26. 2025AffectSRNet : Facial Emotion-Aware Super-Resolution Networkcited by 0
  27. 2025Learning Private Representations through Entropy-based Adversarial Trainingcited by 0
  28. 2026WiFi2Cap: Semantic Action Captioning from Wi-Fi CSI via Limb-Level Semantic Alignmentcited by 0
  29. 2026CFE-PPAR: Compression-friendly encryption for privacy-preserving action recognition leveraging video transformerscited by 0
  30. 2026Lens Privacy Sealing: A New Benchmark and Method for Physical Privacy-Preserving Action Recognitioncited by 0
  31. 2026Face De-Identification: A Domain-Centric Survey from Capture to Processingcited by 0