Xiaochun Cao

26

Papers

435

Total Citations

Papers (26)

Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding

Revisiting Backdoor Attacks against Large Vision-Language Models from Domain Shift

Does Few-Shot Learning Suffer from Backdoor Attacks?

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

SUMI-IFL: An Information-Theoretic Framework for Image Forgery Localization with Sufficiency and Minimality Constraints

Focal-SAM: Focal Sharpness-Aware Minimization for Long-Tailed Classification

PTUS: Photo-Realistic Talking Upper-Body Synthesis via 3D-Aware Motion Decomposition

Lie Detector: Unified Backdoor Detection via Cross-Examination Framework

UMDATrack: Unified Multi-Domain Adaptive Tracking Under Adverse Weather Conditions

SDGAN: Disentangling Semantic Manipulation for Facial Attribute Editing

Omnidirectional Image Super-resolution via Bi-projection Fusion

Hide in Thicket: Generating Imperceptible and Rational Adversarial Perturbations on 3D Point Clouds

Improving Graph Contrastive Learning via Adaptive Positive Sampling

Logit Standardization in Knowledge Distillation

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

Size-invariance Matters: Rethinking Metrics and Losses for Imbalanced Multi-object Salient Object Detection

Interpreting Object-level Foundation Models via Visual Precision Search

Harnessing Hierarchical Label Distribution Variations in Test Agnostic Long-tail Recognition

Semi-Supervised State-Space Model with Dynamic Stacking Filter for Real-World Video Deraining

RobustSplat: Decoupling Densification and Dynamics for Transient-Free 3DGS

Gradient-Reweighted Adversarial Camouflage for Physical Object Detection Evasion

Transparent Vision: A Theory of Hierarchical Invariant Representations

3D Gaussian Splatting Driven Multi-View Robust Physical Adversarial Camouflage Generation

DADM: Dual Alignment of Domain and Modality for Face Anti-spoofing

Critical Forgetting-Based Multi-Scale Disentanglement for Deepfake Detection

Graph Contrastive Learning with Joint Spectral Augmentation of Attribute and Topology