Shouhong Ding

58

Papers

164

Total Citations

Papers (58)

Generalizing Deepfake Video Detection with Plug-and-Play: Video-Level Blending and Spatiotemporal Adapter Tuning

Test-Time Domain Generalization for Face Anti-Spoofing

Rethinking Generalizable Face Anti-spoofing via Hierarchical Prototype-guided Distribution Refinement in Hyperbolic Space

PCE-Palm: Palm Crease Energy Based Two-Stage Realistic Pseudo-Palmprint Generation

AIGI-Holmes: Towards Explainable and Generalizable AI-Generated Image Detection via Multimodal Large Language Models

SlerpFace: Face Template Protection via Spherical Linear Interpolation

Anchor-based Robust Finetuning of Vision-Language Models

Antidote: A Unified Framework for Mitigating LVLM Hallucinations in Counterfactual Presupposition and Object Perception

Diff-Palm: Realistic Palmprint Generation with Polynomial Creases and Intra-Class Variation Controllable Diffusion Models

Fuse Before Transfer: Knowledge Fusion for Heterogeneous Distillation

Stylized-Face: A Million-level Stylized Face Dataset for Face Recognition

SDPose: Tokenized Pose Estimation via Circulation-Guide Self-Distillation

LaRE^2: Latent Reconstruction Error Based Method for Diffusion-Generated Image Detection

Privacy-Preserving Face Recognition Using Trainable Feature Subtraction

PiD: Generalized AI-Generated Images Detection with Pixelwise Decomposition Residuals

Model Tailor: Mitigating Catastrophic Forgetting in Multi-modal Large Language Models

Delving into Data: Effectively Substitute Training for Black-box Attack

Detecting Camouflaged Object in Frequency Domain

ContrastMask: Contrastive Learning To Segment Every Thing

Evaluation-Oriented Knowledge Distillation for Deep Face Recognition

Exploring Frequency Adversarial Attacks for Face Forgery Detection

Towards Efficient Data Free Black-Box Adversarial Attack

Towards Practical Certifiable Patch Defense With Vision Transformer

End-to-End Reconstruction-Classification Learning for Face Forgery Detection

Sibling-Attack: Rethinking Transferable Adversarial Attacks Against Face Recognition

Instance-Aware Domain Generalization for Face Anti-Spoofing

Rethinking the Learning Paradigm for Dynamic Facial Expression Recognition

Probabilistic Knowledge Distillation of Face Ensembles

DistilPose: Tokenized Pose Regression With Heatmap Distillation

Disentangled High Quality Salient Object Detection

RPG-Palm: Realistic Pseudo-data Generation for Palmprint Recognition

Contrastive Pseudo Learning for Open-World DeepFake Attribution

Privacy-Preserving Face Recognition Using Random Frequency Components

Shape Matters: Deformable Patch Attack

Generative Domain Adaptation for Face Anti-Spoofing

ECO-TR: Efficient Correspondences Finding via Coarse-to-Fine Refinement

Privacy-Preserving Face Recognition with Learnable Privacy Budgets in Frequency Domain

Hierarchical Contrastive Inconsistency Learning for Deepfake Video Detection

BézierPalm: A Free Lunch for Palmprint Recognition

An Information Theoretic Approach for Attention-Driven Face Forgery Detection

Domain Adaptive Person Search

Mutually Reinforcing Structure with Proposal Contrastive Consistency for Few-Shot Object Detection

Entropy-Driven Sampling and Training Scheme for Conditional Diffusion Generation

Face Anti-Spoofing via Disentangled Representation Learning

ROD-MLLM: Towards More Reliable Object Detection in Multimodal Large Language Models

Data Synthesis with Diverse Styles for Face Recognition via 3DMM-Guided Diffusion

Unified Adversarial Augmentation for Improving Palmprint Recognition

From Enhancement to Understanding: Build a Generalized Bridge for Low-light Vision via Semantically Consistent Unsupervised Fine-tuning

Instruct Where the Model Fails: Generative Data Augmentation via Guided Self-contrastive Fine-tuning

PVTree: Realistic and Controllable Palm Vein Generation for Recognition Tasks

HDMixer: Hierarchical Dependency with Extendable Patch for Multivariate Time Series Forecasting

MmAP: Multi-Modal Alignment Prompt for Cross-Domain Multi-Task Learning

Domain-Hallucinated Updating for Multi-Domain Face Anti-spoofing

Re-thinking Data Availability Attacks Against Deep Neural Networks

DENSE: Data-Free One-Shot Federated Learning

Adv-Attribute: Inconspicuous and Transferable Adversarial Attack on Face Recognition

CrossGNN: Confronting Noisy Multivariate Time Series Via Cross Interaction Refinement

Content-based Unrestricted Adversarial Attack