Face Recognition

ZeroMark revolutionizes dataset ownership verification by enabling copyright protection without exposing watermarks, leveraging the intrinsic properties of DNNs trained on watermarked data.

Vision Mamba Mender systematically optimizes the Mamba model by identifying and repairing internal and external state flaws, significantly improving its performance in visual recognition tasks.

TopoFR enhances face recognition by aligning topological structures between input and latent spaces. Using persistent homology, it preserves crucial data structure info, overcoming overfitting. A har…

SpeechForensics leverages audio-visual speech representation learning to achieve superior face forgery detection, outperforming state-of-the-art methods in cross-dataset generalization and robustness.

RLE: A novel data augmentation strategy unifying cross-spectral re-ID, significantly boosting model performance by mimicking local linear transformations.

ProxyFusion, a novel face feature fusion method, achieves real-time performance by using sparse experts to weight features without relying on intermediate representations or metadata, substantially im…

Researchers developed Light Decoupling, a novel approach to model 3D facial textures under complex illumination, achieving more realistic and accurate results by decoupling unnatural lighting into mul…

Balancing Alignment and Uniformity (BAU) framework improves generalizable person re-identification by mitigating the polarized effects of data augmentation, achieving state-of-the-art performance.

FreqBlender enhances DeepFake detection by cleverly blending frequency domain knowledge of real and fake faces, improving model generalization and providing a complementary strategy to existing spatia…

New feature-level adversarial attacks disrupt visible-infrared person re-identification (VIReID) systems by cleverly aligning and manipulating features to cause incorrect ranking results.

DiffusionFake enhances deepfake detection by cleverly reversing the image generation process, enabling detectors to learn more robust features and significantly improve cross-domain generalization.

Cross-Modality Perturbation Synergy (CMPS) attack: A novel universal perturbation method for cross-modality person re-identification, effectively misleading ReID models by leveraging gradients from di…

CemiFace: Generating high-quality synthetic facial data for robust face recognition, while addressing privacy concerns.

ProDet: Deepfake detection enhanced by progressively organizing blendfake and deepfake data in the latent space, improving generalization and robustness.

AdjointDEIS: Efficient gradients for diffusion models via bespoke ODE solvers, simplifying backpropagation and improving guided generation.

ID³: A novel diffusion model generates diverse, identity-preserving synthetic face datasets for accurate and privacy-preserving face recognition, exceeding current state-of-the-art methods.