Hao Yu

papers

828

total citations

papers (23)

Deep Graph-Based Spatial Consistency for Robust Non-Rigid Point Cloud Registration

CVPR 2023arXiv

citations

MatchU: Matching Unseen Objects for 6D Pose Estimation from RGB-D Images

CVPR 2024arXiv

citations

Quantization without Tears

CVPR 2025arXiv

citations

Dynamic Hyperbolic Attention Network for Fine Hand-object Reconstruction

ICCV 2023arXiv

citations

Domain Shifting: A Generalized Solution for Heterogeneous Cross-Modality Person Re-Identification

ECCV 2024

citations

ComRoPE: Scalable and Robust Rotary Position Embedding Parameterized by Trainable Commuting Angle Matrices

CVPR 2025arXiv

citations

From Laboratory to Real World: A New Benchmark Towards Privacy-Preserved Visible-Infrared Person Re-Identification

CVPR 2025

citations

FreeNet: Liberating Depth-Wise Separable Operations for Building Faster Mobile Vision Architectures

AAAI 2025

citations

Handling Spatial-Temporal Data Heterogeneity for Federated Continual Learning via Tail Anchor

CVPR 2025arXiv

citations

Memory-Efficient Generative Models via Product Quantization

ICCV 2025

citations

Treasures in Discarded Weights for LLM Quantization

AAAI 2025

citations

What Is a Good Question? Assessing Question Quality via Meta-Fact Checking

AAAI 2025

citations

Decouple then Classify: A Dynamic Multi-view Labeling Strategy with Shared and Specific Information

ICML 2024

citations

CoFiNet: Reliable Coarse-to-fine Correspondences for Robust PointCloud Registration

NEURIPS 2021

citations

Differentiable Auxiliary Learning for Sketch Re-identification

AAAI 2024

citations

Efficient Federated Incomplete Multi-View Clustering

ICML 2025

citations

VPR-Cloak: A First Look at Privacy Cloak Against Visual Place Recognition

ICCV 2025

citations

TOPLight: Lightweight Neural Networks With Task-Oriented Pretraining for Visible-Infrared Recognition

CVPR 2023

citations

Hao Yu

papers (23)

Geometric Transformer for Fast and Robust Point Cloud Registration

Rotation-Invariant Transformer for Point Cloud Matching

VisualAgentBench: Towards Large Multimodal Models as Visual Foundation Agents

Modality Unifying Network for Visible-Infrared Person Re-Identification

Training Vision Transformers with Only 2040 Images

Deep Graph-Based Spatial Consistency for Robust Non-Rigid Point Cloud Registration

MatchU: Matching Unseen Objects for 6D Pose Estimation from RGB-D Images

Quantization without Tears

Dynamic Hyperbolic Attention Network for Fine Hand-object Reconstruction

Domain Shifting: A Generalized Solution for Heterogeneous Cross-Modality Person Re-Identification

ComRoPE: Scalable and Robust Rotary Position Embedding Parameterized by Trainable Commuting Angle Matrices

From Laboratory to Real World: A New Benchmark Towards Privacy-Preserved Visible-Infrared Person Re-Identification

FreeNet: Liberating Depth-Wise Separable Operations for Building Faster Mobile Vision Architectures

Handling Spatial-Temporal Data Heterogeneity for Federated Continual Learning via Tail Anchor

Memory-Efficient Generative Models via Product Quantization

Treasures in Discarded Weights for LLM Quantization

What Is a Good Question? Assessing Question Quality via Meta-Fact Checking

Decouple then Classify: A Dynamic Multi-view Labeling Strategy with Shared and Specific Information

CoFiNet: Reliable Coarse-to-fine Correspondences for Robust PointCloud Registration

Differentiable Auxiliary Learning for Sketch Re-identification

Efficient Federated Incomplete Multi-View Clustering

VPR-Cloak: A First Look at Privacy Cloak Against Visual Place Recognition

TOPLight: Lightweight Neural Networks With Task-Oriented Pretraining for Visible-Infrared Recognition

papers (23)

Geometric Transformer for Fast and Robust Point Cloud Registration

Rotation-Invariant Transformer for Point Cloud Matching

VisualAgentBench: Towards Large Multimodal Models as Visual Foundation Agents

Modality Unifying Network for Visible-Infrared Person Re-Identification

Training Vision Transformers with Only 2040 Images

Deep Graph-Based Spatial Consistency for Robust Non-Rigid Point Cloud Registration

MatchU: Matching Unseen Objects for 6D Pose Estimation from RGB-D Images

Quantization without Tears

Dynamic Hyperbolic Attention Network for Fine Hand-object Reconstruction

Domain Shifting: A Generalized Solution for Heterogeneous Cross-Modality Person Re-Identification

ComRoPE: Scalable and Robust Rotary Position Embedding Parameterized by Trainable Commuting Angle Matrices

From Laboratory to Real World: A New Benchmark Towards Privacy-Preserved Visible-Infrared Person Re-Identification

FreeNet: Liberating Depth-Wise Separable Operations for Building Faster Mobile Vision Architectures

Handling Spatial-Temporal Data Heterogeneity for Federated Continual Learning via Tail Anchor

Memory-Efficient Generative Models via Product Quantization

Treasures in Discarded Weights for LLM Quantization

What Is a Good Question? Assessing Question Quality via Meta-Fact Checking

Decouple then Classify: A Dynamic Multi-view Labeling Strategy with Shared and Specific Information

CoFiNet: Reliable Coarse-to-fine Correspondences for Robust PointCloud Registration

Differentiable Auxiliary Learning for Sketch Re-identification

Efficient Federated Incomplete Multi-View Clustering

VPR-Cloak: A First Look at Privacy Cloak Against Visual Place Recognition

TOPLight: Lightweight Neural Networks With Task-Oriented Pretraining for Visible-Infrared Recognition