Privacy-Preserving-Action-Recognition

A collection of resources and papers on Privacy Preserving Action Recognition.

Downsampling-based methods

✔️ 【Single-pixel resolution】[Towards privacy-preserving recognition of human activities]

• [Paper]

✔️ 【Downsampling in simulated environment】[Towards privacy-preserving activity recognition using extremely low temporal and spatial resolution cameras]

• [Paper]

✔️ 【ISR】[Privacy-preserving human activity recognition from extreme low resolution]

• [Paper]

✔️ 【Semi-coupled two stream】[Semi-Coupled Two-Stream Fusion ConvNets for Action Recognition at Extremely Low Resolutions]

• [Paper]

✔️ 【Multi-siamese】[Extreme low resolution activity recognition with multi-siamese embedding learning]

• [Paper]

✔️ 【Fully-coupled two-stream】[Fully-coupled two-stream spatiotemporal networks for extremely low resolution action recognition]

• [Paper]

✔️ 【Indoor Downsampling】[Indoor privacy-preserving action recognition via partially coupled convolutional neural network]

• [Paper]

Adversarial Learning-based methods

✔️ 【SAM1】[Towards Privacy-Preserving Visual Recognition via Adversarial Training: A Pilot Study]

• [Paper]

✔️ 【SAM2】[Privacy-Preserving Deep Action Recognition: An Adversarial Learning Framework and A New Dataset]

• [Paper]

✔️ 【STPrivacy】[STPrivacy: Spatio-Temporal Privacy-Preserving Action Recognition]

• [Paper]

✔️ 【Meta-PPAR】[Joint Attribute and Model Generalization Learning for Privacy-Preserving Action Recognition]

• [Paper]

✔️ 【SPAct】[SPAct: Self-Supervised Privacy Preservation for Action Recognition]

• [Paper]

✔️ 【PPAM】[Patch-Based Privacy Attention for Weakly-Supervised Privacy-Preserving Action Recognition]

• [Paper]

Obfuscation-based methods

✔️ 【Anonymize face】[Learning to Anonymize Faces for Privacy Preserving Action Detection]

• [Paper]

✔️ 【Anonymize body】[Multi-scale, class-generic, privacy-preserving video]

• [Paper]

✔️ 【Skeleton】[Privacy-Preserving Action Recognition]

• [Paper]

✔️ 【PHM Skeleton】[Secure and privacy-preserving human interaction recognition of pervasive healthcare monitoring]

• [Paper]

✔️ 【BDQ】[Privacy-Preserving Action Recognition via Motion Difference Quantization]

• [Paper]

✔️ 【SelectiveObscure】[Selective, Interpretable, and Motion Consistent Privacy Attribute Obfuscation for Action Recognition]

• [Paper]

Encryption-based methods

✔️ 【MPC】[Privacy-preserving video classification with convolutional neural networks]

• [Paper]

✔️ 【LCVE】[Learnable Cube-Based Video Encryption for Privacy-Preserving Action Recognition]

• [Paper]

Device-based methods

✔️ 【PrivHAR】[Privhar: Recognizing human actions from privacy-preserving lens]

• [Paper]

✔️ 【TrustEYE.M4】[TrustEYE. M4: protecting the sensor—not the camera]

• [Paper]

✔️ 【Coded Aperture】[Privacy-preserving action recognition using coded aperture videos]

• [Paper]