Xingyu Liu

papers

1,902

total citations

papers (18)

CATRE: Iterative Point Clouds Alignment for Category-Level Object Pose Refinement

ECCV 2022arXiv

citations

Deformer: Dynamic Fusion Transformer for Robust Hand Pose Estimation

ICCV 2023arXiv

citations

Sequential Voting With Relational Box Fields for Active Object Detection

CVPR 2022arXiv

citations

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

ECCV 2024

citations

UNOPose: Unseen Object Pose Estimation with an Unposed RGB-D Reference Image

CVPR 2025arXiv

citations

Street Gaussians without 3D Object Tracker

ICCV 2025arXiv

citations

KP-RED: Exploiting Semantic Keypoints for Joint 3D Shape Retrieval and Deformation

CVPR 2024arXiv

citations

Coarse-to-Fine Implicit Representation Learning for 3D Hand-Object Reconstruction from a Single RGB-D Image

ECCV 2024

citations

Boosting the Dual-Stream Architecture in Ultra-High Resolution Segmentation with Resolution-Biased Uncertainty Estimation

CVPR 2025

citations

Keypoint Fusion for RGB-D Based 3D Hand Pose Estimation

AAAI 2024

citations

Differentiable Auxiliary Learning for Sketch Re-identification

AAAI 2024

citations

Prior-aware Dynamic Temporal Modeling Framework for Sequential 3D Hand Pose Estimation

ICCV 2025

citations

Parallel Attention Interaction Network for Few-Shot Skeleton-Based Action Recognition

ICCV 2023

citations

No Pains, More Gains: Recycling Sub-Salient Patches for Efficient High-Resolution Image Recognition

CVPR 2025

citations

Xingyu Liu

papers (18)

Ego4D: Around the World in 3,000 Hours of Egocentric Video

KeyPose: Multi-View 3D Labeling and Keypoint Estimation for Transparent Objects

RePOSE: Fast 6D Object Pose Refinement via Deep Texture Rendering

StereOBJ-1M: Large-Scale Stereo Image Dataset for 6D Object Pose Estimation

CATRE: Iterative Point Clouds Alignment for Category-Level Object Pose Refinement

Deformer: Dynamic Fusion Transformer for Robust Hand Pose Estimation

Sequential Voting With Relational Box Fields for Active Object Detection

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

UNOPose: Unseen Object Pose Estimation with an Unposed RGB-D Reference Image

Street Gaussians without 3D Object Tracker

KP-RED: Exploiting Semantic Keypoints for Joint 3D Shape Retrieval and Deformation

Coarse-to-Fine Implicit Representation Learning for 3D Hand-Object Reconstruction from a Single RGB-D Image

Boosting the Dual-Stream Architecture in Ultra-High Resolution Segmentation with Resolution-Biased Uncertainty Estimation

Keypoint Fusion for RGB-D Based 3D Hand Pose Estimation

Differentiable Auxiliary Learning for Sketch Re-identification

Prior-aware Dynamic Temporal Modeling Framework for Sequential 3D Hand Pose Estimation

Parallel Attention Interaction Network for Few-Shot Skeleton-Based Action Recognition

No Pains, More Gains: Recycling Sub-Salient Patches for Efficient High-Resolution Image Recognition

papers (18)

Ego4D: Around the World in 3,000 Hours of Egocentric Video

KeyPose: Multi-View 3D Labeling and Keypoint Estimation for Transparent Objects

RePOSE: Fast 6D Object Pose Refinement via Deep Texture Rendering

StereOBJ-1M: Large-Scale Stereo Image Dataset for 6D Object Pose Estimation

CATRE: Iterative Point Clouds Alignment for Category-Level Object Pose Refinement

Deformer: Dynamic Fusion Transformer for Robust Hand Pose Estimation

Sequential Voting With Relational Box Fields for Active Object Detection

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

UNOPose: Unseen Object Pose Estimation with an Unposed RGB-D Reference Image

Street Gaussians without 3D Object Tracker

KP-RED: Exploiting Semantic Keypoints for Joint 3D Shape Retrieval and Deformation

Coarse-to-Fine Implicit Representation Learning for 3D Hand-Object Reconstruction from a Single RGB-D Image

Boosting the Dual-Stream Architecture in Ultra-High Resolution Segmentation with Resolution-Biased Uncertainty Estimation

Keypoint Fusion for RGB-D Based 3D Hand Pose Estimation

Differentiable Auxiliary Learning for Sketch Re-identification

Prior-aware Dynamic Temporal Modeling Framework for Sequential 3D Hand Pose Estimation

Parallel Attention Interaction Network for Few-Shot Skeleton-Based Action Recognition

No Pains, More Gains: Recycling Sub-Salient Patches for Efficient High-Resolution Image Recognition