Xin Wen

Affiliations

The University of Hong Kong

papers

1,584

total citations

papers (23)

SnowflakeNet: Point Cloud Completion by Snowflake Point Deconvolution With Skip-Transformer

ICCV 2021arXiv

296

citations

Cycle4Completion: Unpaired Point Cloud Completion Using Cycle Transformation With Missing Region Coding

CVPR 2021arXiv

109

citations

Learning Semi-supervised Gaussian Mixture Models for Generalized Category Discovery

ICCV 2023arXiv

citations

Self-Supervised Visual Representation Learning with Semantic Grouping

NEURIPS 2022arXiv

citations

Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training

CVPR 2024arXiv

citations

CoDet: Co-occurrence Guided Region-Word Alignment for Open-Vocabulary Object Detection

NEURIPS 2023arXiv

citations

3D Shape Reconstruction From 2D Images With Disentangled Attribute Flow

CVPR 2022arXiv

citations

Masked Scene Contrast: A Scalable Framework for Unsupervised 3D Representation Learning

CVPR 2023arXiv

citations

Learning Deep Implicit Functions for 3D Shapes With Dynamic Code Clouds

CVPR 2022arXiv

citations

Retro-FPN: Retrospective Feature Pyramid Network for Point Cloud Semantic Segmentation

ICCV 2023arXiv

citations

Can OOD Object Detectors Learn from Foundation Models?

ECCV 2024arXiv

citations

Classes Are Not Equal: An Empirical Study on Image Recognition Fairness

CVPR 2024arXiv

citations

Vision Foundation Models as Effective Visual Tokenizers for Autoregressive Generation

NEURIPS 2025

citations

VasTSD: Learning 3D Vascular Tree-state Space Diffusion Model for Angiography Synthesis

CVPR 2025arXiv

citations

``Principal Components" Enable A New Language of Images

ICCV 2025

citations

Learning from Neighbors: Category Extrapolation for Long-Tail Learning

CVPR 2025arXiv

citations

A Data-Centric Revisit of Pre-Trained Vision Models for Robot Learning

CVPR 2025arXiv

citations

Equipping Vision Foundation Model with Mixture of Experts for Out-of-Distribution Detection

ICCV 2025arXiv

citations

Adaptive Variance Based Label Distribution Learning For Facial Age Estimation

ECCV 2020

citations

What If the TV Was Off? Examining Counterfactual Reasoning Abilities of Multi-modal Language Models

CVPR 2024arXiv

citations

Xin Wen

Affiliations

papers (23)

SnowflakeNet: Point Cloud Completion by Snowflake Point Deconvolution With Skip-Transformer

Point Cloud Completion by Skip-Attention Network With Hierarchical Folding

PMP-Net: Point Cloud Completion by Learning Multi-Step Point Moving Paths

Parametric Classification for Generalized Category Discovery: A Baseline Study

Cycle4Completion: Unpaired Point Cloud Completion Using Cycle Transformation With Missing Region Coding

Learning Semi-supervised Gaussian Mixture Models for Generalized Category Discovery

Self-Supervised Visual Representation Learning with Semantic Grouping

Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training

CoDet: Co-occurrence Guided Region-Word Alignment for Open-Vocabulary Object Detection

3D Shape Reconstruction From 2D Images With Disentangled Attribute Flow

Masked Scene Contrast: A Scalable Framework for Unsupervised 3D Representation Learning

Learning Deep Implicit Functions for 3D Shapes With Dynamic Code Clouds

Retro-FPN: Retrospective Feature Pyramid Network for Point Cloud Semantic Segmentation

Can OOD Object Detectors Learn from Foundation Models?

Classes Are Not Equal: An Empirical Study on Image Recognition Fairness

Vision Foundation Models as Effective Visual Tokenizers for Autoregressive Generation

VasTSD: Learning 3D Vascular Tree-state Space Diffusion Model for Angiography Synthesis

``Principal Components" Enable A New Language of Images

Learning from Neighbors: Category Extrapolation for Long-Tail Learning

A Data-Centric Revisit of Pre-Trained Vision Models for Robot Learning

Equipping Vision Foundation Model with Mixture of Experts for Out-of-Distribution Detection

Adaptive Variance Based Label Distribution Learning For Facial Age Estimation

What If the TV Was Off? Examining Counterfactual Reasoning Abilities of Multi-modal Language Models

papers (23)

SnowflakeNet: Point Cloud Completion by Snowflake Point Deconvolution With Skip-Transformer

Point Cloud Completion by Skip-Attention Network With Hierarchical Folding

PMP-Net: Point Cloud Completion by Learning Multi-Step Point Moving Paths

Parametric Classification for Generalized Category Discovery: A Baseline Study

Cycle4Completion: Unpaired Point Cloud Completion Using Cycle Transformation With Missing Region Coding

Learning Semi-supervised Gaussian Mixture Models for Generalized Category Discovery

Self-Supervised Visual Representation Learning with Semantic Grouping

Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training

CoDet: Co-occurrence Guided Region-Word Alignment for Open-Vocabulary Object Detection

3D Shape Reconstruction From 2D Images With Disentangled Attribute Flow

Masked Scene Contrast: A Scalable Framework for Unsupervised 3D Representation Learning

Learning Deep Implicit Functions for 3D Shapes With Dynamic Code Clouds

Retro-FPN: Retrospective Feature Pyramid Network for Point Cloud Semantic Segmentation

Can OOD Object Detectors Learn from Foundation Models?

Classes Are Not Equal: An Empirical Study on Image Recognition Fairness

Vision Foundation Models as Effective Visual Tokenizers for Autoregressive Generation

VasTSD: Learning 3D Vascular Tree-state Space Diffusion Model for Angiography Synthesis

``Principal Components" Enable A New Language of Images

Learning from Neighbors: Category Extrapolation for Long-Tail Learning

A Data-Centric Revisit of Pre-Trained Vision Models for Robot Learning

Equipping Vision Foundation Model with Mixture of Experts for Out-of-Distribution Detection

Adaptive Variance Based Label Distribution Learning For Facial Age Estimation

What If the TV Was Off? Examining Counterfactual Reasoning Abilities of Multi-modal Language Models