Shuang Wu

papers

803

total citations

papers (20)

Temporal Feature Alignment and Mutual Information Maximization for Video-Based Human Pose Estimation

CVPR 2022arXiv

citations

Online Map Vectorization for Autonomous Driving: A Rasterization Perspective

NEURIPS 2023arXiv

citations

Multi-faceted Distillation of Base-Novel Commonality for Few-Shot Object Detection

ECCV 2022arXiv

citations

Direct3D-S2: Gigascale 3D Generation Made Easy with Spatial Sparse Attention

NEURIPS 2025arXiv

citations

Self-Aware Personalized Federated Learning

NEURIPS 2022arXiv

citations

Few-Shot Object Detection by Knowledge Distillation Using Bag-of-Visual-Words Representations

ECCV 2022arXiv

citations

UniVoxel: Fast Inverse Rendering by Unified Voxelization of Scene Representation

ECCV 2024arXiv

citations

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

AAAI 2025

citations

Motion Prediction Using Trajectory Cues

ICCV 2021

citations

Rethinking the Learning Paradigm for Dynamic Facial Expression Recognition

CVPR 2023

citations

Re-thinking Data Availability Attacks Against Deep Neural Networks

CVPR 2024

citations

High-quality Text-to-3D Character Generation with SparseCubes and Sparse Transformers.

ICLR 2025

citations

Detecting Camouflaged Object in Frequency Domain

CVPR 2022

citations

Towards Efficient Data Free Black-Box Adversarial Attack

CVPR 2022

citations

Shape Matters: Deformable Patch Attack

ECCV 2022

citations

Shuang Wu

papers (20)

DENSE: Data-Free One-Shot Federated Learning

Deep Dual Consecutive Network for Human Pose Estimation

Content-based Unrestricted Adversarial Attack

Exposing the Deception: Uncovering More Forgery Clues for Deepfake Detection

Towards Practical Certifiable Patch Defense With Vision Transformer

Temporal Feature Alignment and Mutual Information Maximization for Video-Based Human Pose Estimation

Online Map Vectorization for Autonomous Driving: A Rasterization Perspective

Multi-faceted Distillation of Base-Novel Commonality for Few-Shot Object Detection

Direct3D-S2: Gigascale 3D Generation Made Easy with Spatial Sparse Attention

Self-Aware Personalized Federated Learning

Few-Shot Object Detection by Knowledge Distillation Using Bag-of-Visual-Words Representations

UniVoxel: Fast Inverse Rendering by Unified Voxelization of Scene Representation

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

Motion Prediction Using Trajectory Cues

Rethinking the Learning Paradigm for Dynamic Facial Expression Recognition

Re-thinking Data Availability Attacks Against Deep Neural Networks

High-quality Text-to-3D Character Generation with SparseCubes and Sparse Transformers.

Detecting Camouflaged Object in Frequency Domain

Towards Efficient Data Free Black-Box Adversarial Attack

Shape Matters: Deformable Patch Attack

papers (20)

DENSE: Data-Free One-Shot Federated Learning

Deep Dual Consecutive Network for Human Pose Estimation

Content-based Unrestricted Adversarial Attack

Exposing the Deception: Uncovering More Forgery Clues for Deepfake Detection

Towards Practical Certifiable Patch Defense With Vision Transformer

Temporal Feature Alignment and Mutual Information Maximization for Video-Based Human Pose Estimation

Online Map Vectorization for Autonomous Driving: A Rasterization Perspective

Multi-faceted Distillation of Base-Novel Commonality for Few-Shot Object Detection

Direct3D-S2: Gigascale 3D Generation Made Easy with Spatial Sparse Attention

Self-Aware Personalized Federated Learning

Few-Shot Object Detection by Knowledge Distillation Using Bag-of-Visual-Words Representations

UniVoxel: Fast Inverse Rendering by Unified Voxelization of Scene Representation

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

Motion Prediction Using Trajectory Cues

Rethinking the Learning Paradigm for Dynamic Facial Expression Recognition

Re-thinking Data Availability Attacks Against Deep Neural Networks

High-quality Text-to-3D Character Generation with SparseCubes and Sparse Transformers.

Detecting Camouflaged Object in Frequency Domain

Towards Efficient Data Free Black-Box Adversarial Attack

Shape Matters: Deformable Patch Attack