Shu-Tao Xia

53

Papers

185

Total Citations

Papers (53)

BadCLIP: Trigger-Aware Prompt Learning for Backdoor Attacks on CLIP

Towards Compact 3D Representations via Point Feature Enhancement Masked Autoencoders

Towards Faithful XAI Evaluation via Generalization-Limited Backdoor Watermark

Accelerated Stochastic Greedy Coordinate Descent by Soft Thresholding Projection onto Simplex

NeurIPS 2017arXiv

Error-quantified Conformal Inference for Time Series

Enhancing Partially Relevant Video Retrieval with Hyperbolic Learning

Protecting Your Video Content: Disrupting Automated Video-based LLM Annotations

Efficient Self-Supervised Video Hashing with Selective State Spaces

Controller-Guided Partial Label Consistency Regularization with Unlabeled Data

Hierarchical Features Matter: A Deep Exploration of Progressive Parameterization Method for Dataset Distillation

Embracing Collaboration Over Competition: Condensing Multiple Prompts for Visual In-Context Learning

Pre-Trained Vision-Language Models as Noisy Partial Annotators

Vision-Language Pre-training with Object Contrastive Learning for 3D Scene Understanding

GMMFormer: Gaussian-Mixture-Model Based Transformer for Efficient Partially Relevant Video Retrieval

Not All Prompts Are Secure: A Switchable Backdoor Attack Against Pre-trained Vision Transfomers

Iterative Learning With Open-Set Noisy Labels

Second-Order Attention Network for Single Image Super-Resolution

Maintaining Discrimination and Fairness in Class Incremental Learning

One-Shot Adversarial Attacks on Visual Tracking With Dual Attention

PILC: Practical Image Lossless Compression With an End-to-End GPU Oriented Neural Framework

Boosting Black-Box Attack With Partially Transferred Conditional Adversarial Distribution

Learning Transferable Spatiotemporal Representations From Natural Script Knowledge

Backdoor Defense via Adaptively Splitting Poisoned Dataset

Hilbert-Based Generative Defense for Adversarial Examples

TokenPose: Learning Keypoint Tokens for Human Pose Estimation

Towards Robust Model Watermark via Reducing Parametric Vulnerability

Unsupervised Surface Anomaly Detection with Diffusion Probabilistic Model

Instance-aware Dynamic Prompt Tuning for Pre-trained Point Cloud Models

GIFD: A Generative Gradient Inversion Method with Feature Domain Optimization

One-bit Flip is All You Need: When Bit-flip Attack Meets Model Training

Targeted Attack for Deep Hashing based Retrieval

Improving Query Efficiency of Black-box Adversarial Attack

Hardly Perceptible Trojan Attack against Neural Networks with Bit Flips

SimCC: A Simple Coordinate Classification Perspective for Human Pose Estimation

Improving Vision Transformers by Revisiting High-Frequency Components

NeXT: Towards High Quality Neural Radiance Fields via Multi-Skip Transformer

Training Interpretable Convolutional Neural Networks by Differentiating Class-specific Filters

AutoSSVH: Exploring Automated Frame Sampling for Efficient Self-Supervised Video Hashing

PMA: Towards Parameter-Efficient Point Cloud Understanding via Point Mamba Adapter

MambaIRv2: Attentive State Space Restoration

Adapting Pre-trained 3D Models for Point Cloud Video Understanding via Cross-frame Spatio-temporal Perception

FastVAR: Linear Visual Autoregressive Modeling via Cached Token Pruning

Cassic: Towards Content-Adaptive State-Space Models for Learned Image Compression

One Perturbation is Enough: On Generating Universal Adversarial Perturbations against Vision-Language Pre-training Models

GCD-Sampling: A General Cross-scale Decoupled Sampling for Point Cloud

Diffusion Prior Interpolation for Flexibility Real-World Face Super-Resolution

CALF: Aligning LLMs for Time Series Forecasting via Cross-modal Fine-Tuning

BML: A High-performance, Low-cost Gradient Synchronization Algorithm for DML Training

Adversarial Weight Perturbation Helps Robust Generalization

Stochastic Deep Gaussian Processes over Graphs

Clustering Effect of Adversarial Robust Models

Untargeted Backdoor Watermark: Towards Harmless and Stealthy Dataset Copyright Protection

Domain Watermark: Effective and Harmless Dataset Copyright Protection is Closed at Hand