mlsanityData to 14 Oct 2026

CFE-PPAR: Compression-friendly encryption for privacy-preserving action recognition leveraging video transformers

arXiv 2605.05692 ↗First posted 7 May 2026cs.CV cs.AI cs.CRcited by 0

Not on the map. Why?

Abstract (arXiv)

Privacy-preserving action recognition (PPAR) enables machines to understand human activities in videos without revealing sensitive visual content. Among the various strategies for PPAR, encryption-based methods achieve strong privacy protection while maintaining high recognition performance. However, these methods lead to a catastrophic decrease in recognition performance and visual quality when the encrypted videos are compressed. That is, the previous methods are not compression-friendly. To address these issues, in this paper, we propose the first compression-friendly encryption method for PPAR, called CFE-PPAR. In CFE-PPAR, videos encrypted with secret keys can be directly recognized by a video transformer, which uses parameters transformed by the same keys as those used for video encryption. In experiments, it is verified that CFE-PPAR outperforms previous methods on the UCF101 and HMDB51 datasets under Motion-JPEG and H.264 compression.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 12 of its 23 references that are in the map. First posted on arXiv 7 May 2026.

Builds on

12 of 23 references.

References · 12

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  2. 2021ViViT: A Video Vision Transformercited by 1,620
  3. 2022VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Trainingcited by 1,322
  4. 2018Towards Privacy-Preserving Visual Recognition via Adversarial Training: A Pilot Studycited by 48
  5. 2016Privacy-Preserving Human Activity Recognition from Extreme Low Resolutioncited by 43
  6. 2017Extreme Low Resolution Activity Recognition with Multi-Siamese Embedding Learningcited by 15
  7. 2022Privacy-Preserving Action Recognition via Motion Difference Quantizationcited by 14
  8. 2017A Genetic Algorithm-Based Solver for Very Large Jigsaw Puzzlescited by 13
  9. 2021Secure Human Action Recognition by Encrypted Neural Network Inferencecited by 10
  10. 2024Selective, Interpretable, and Motion Consistent Privacy Attribute Obfuscation for Action Recognitioncited by 8
  11. 2024Efficient Fine-Tuning with Domain Adaptation for Privacy-Preserving Vision Transformercited by 3
  12. 2024Activity Recognition on Avatar-Anonymized Datasets with Masked Differential Privacycited by 3

Built on by

Not cited yet.