Baoyuan Wu

48

Papers

161

Total Citations

Papers (48)

Transcending Forgery Specificity with Latent Space Augmentation for Generalizable Deepfake Detection

Learning to Optimize Permutation Flow Shop Scheduling via Graph-Based Imitation Learning

Activation Gradient based Poisoned Sample Detection Against Backdoor Attacks

Spurious Feature Eraser: Stabilizing Test-Time Adaptation for Vision-Language Foundation Model

Decentralized Directed Collaboration for Personalized Federated Learning

Diverse Image Annotation

CNN in MRF: Video Object Segmentation via Inference in a CNN-Based Higher-Order Spatio-Temporal MRF

Tagging Like Humans: Diverse and Distinct Image Annotation

SIDA: Social Media Image Deepfake Detection, Localization and Explanation with Large Multimodal Model

Joint Representation and Estimator Learning for Facial Action Unit Intensity Estimation

Compressing Convolutional Neural Networks via Factorized Convolutional Filters

Residual Regression With Semantic Prior for Crowd Counting

Exact Adversarial Attack to Image Captioning via Structured Output Learning With Latent Variables

Learning to Compose Dynamic Tree Structures for Visual Contexts

Efficient Decision-Based Black-Box Adversarial Attacks on Face Recognition

Prototype-Supervised Adversarial Network for Targeted Attack of Deep Hashing

TediGAN: Text-Guided Diverse Face Image Generation and Manipulation

Probabilistic Modeling of Semantic Ambiguity for Scene Graph Generation

Accelerating Neural Network Optimization Through an Automated Control Theory Lens

LAS-AT: Adversarial Training With Learnable Attack Strategy

Boosting Black-Box Attack With Partially Transferred Conditional Adversarial Distribution

DropMAE: Masked Autoencoders With Spatial-Attention Dropout for Tracking Tasks

ML-MG: Multi-Label Learning With Missing Labels Using a Mixed Graph

Context-Aware Feature and Label Fusion for Facial Action Unit Intensity Estimation With Partially Labeled Data

Invisible Backdoor Attack With Sample-Specific Triggers

Meta-Attack: Class-Agnostic and Model-Agnostic Physical Adversarial Attack

Parallel Rectangle Flip Attack: A Query-Based Black-Box Attack Against Object Detection

Enhancing Fine-Tuning Based Backdoor Defense with Sharpness-Aware Minimization

ToonTalker: Cross-Domain Face Reenactment

UCF: Uncovering Common Features for Generalizable Deepfake Detection

Global Balanced Experts for Federated Long-Tailed Learning

SPL-MLL: Selecting Predictable Landmarks for Multi-Label Learning

Boosting Decision-based Black-box Adversarial Attacks with Random Sign Flip

Sparse Adversarial Attack via Perturbation Factorization

Prior-Guided Adversarial Initialization for Fast Adversarial Training

A Large-Scale Multiple-Objective Method for Black-Box Attack against Object Detection

StyleHEAT: One-Shot High-Resolution Editable Talking Face Generation via Pre-trained StyleGAN

Target-Aware Deep Tracking

BadVideo: Stealthy Backdoor Attack against Text-to-Video Generation

C2P-CLIP: Injecting Category Common Prompt in CLIP to Enhance Generalization in Deepfake Detection

BadCLIP: Dual-Embedding Guided Backdoor Attack on Multimodal Contrastive Learning

Random Noise Defense Against Query-Based Black-Box Attacks

Effective Backdoor Defense by Exploiting Sensitivity of Poisoned Samples

BackdoorBench: A Comprehensive Benchmark of Backdoor Learning

Boosting the Transferability of Adversarial Attacks with Reverse Adversarial Perturbation

Neural Polarizer: A Lightweight and Effective Backdoor Defense via Purifying Poisoned Features

DeepfakeBench: A Comprehensive Benchmark of Deepfake Detection

Shared Adversarial Unlearning: Backdoor Mitigation by Unlearning Shared Adversarial Examples