Computer Vision – ECCV 2022 17th European Conference, Tel Aviv, Israel, October 23–27, 2022, Proceedings, Part XIII

AU-Aware 3D Face Reconstruction through Personalized AU-Specific Blendshape Learning.- B´ezierPalm: A Free Lunch for Palmprint Recognition.- Adaptive Transformers for Robust Few-Shot Cross-Domain Face Anti-Spoofing.- Face2Face?: Real-Time High-Resolution One-Shot Face Reenactment.- Towards Racially Unbiased Skin Tone Estimation via Scene Disambiguation.- BoundaryFace: A Mining Framework with Noise Label Self-Correction for Face Recognition.- Pre-training Strategies and Datasets for Facial Representation Learning.- Look Both Ways: Self-Supervising Driver Gaze Estimation and Road Scene Saliency.- MFIM: Megapixel Facial Identity Manipulation.- 3D Face Reconstruction with Dense Landmarks.- Emotion-Aware Multi-View Contrastive Learning for Facial Emotion Recognition.- Order Learning Using Partially Ordered Data via Chainization.- Unsupervised High-Fidelity Facial Texture Generation and Reconstruction.- Multi-Domain Learning for Updating Face Anti-Spoofing Models.- Towards Metrical Reconstruction of Human Faces.- Discover and Mitigate Unknown Biases with Debiasing Alternate Networks.- Unsupervised and Semi-Supervised Bias Benchmarking in Face Recognition.- Towards Efficient Adversarial Training on Vision Transformers.- MIME: Minority Inclusion for Majority Group Enhancement of AI Performance.- Studying Bias in GANs through the Lens of Race.- Trust, but Verify: Using Self-Supervised Probing to Improve Trustworthiness.- Learning to Censor by Noisy Sampling.- An Invisible Black-Box Backdoor Attack through Frequency Domain.- FairGRAPE: Fairness-Aware GRAdient Pruning mEthod for Face Attribute Classification.- Attaining Class-Level Forgetting in Pretrained Model Using Few Samples.- Anti-Neuron Watermarking: Protecting Personal Data against Unauthorized Neural Networks.- An Impartial Take to the CNN vs Transformer Robustness Contest.- Recover Fair Deep Classification Models via Altering Pre-trained Structure.- Decouple-and-Sample: Protecting Sensitive Information in Task