Xingyu Liu

20

Papers

15

Total Citations

Papers (20)

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

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

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

Street Gaussians without 3D Object Tracker

Differentiable Auxiliary Learning for Sketch Re-identification

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

FlowNet3D: Learning Scene Flow in 3D Point Clouds

Learning Video Representations From Correspondence Proposals

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

Sequential Voting With Relational Box Fields for Active Object Detection

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

MeteorNet: Deep Learning on Dynamic 3D Point Cloud Sequences

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

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

Deformer: Dynamic Fusion Transformer for Robust Hand Pose Estimation

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

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

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

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

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