Zehui Chen

papers

423

total citations

papers (11)

LiDAR-LLM: Exploring the Potential of Large Language Models for 3D LiDAR Understanding

AAAI 2025arXiv

116

citations

Towards Domain Generalization for Multi-View 3D Object Detection in Bird-Eye-View

CVPR 2023arXiv

citations

Unsupervised Domain Adaptation for Monocular 3D Object Detection via Self-Training

ECCV 2022arXiv

citations

Continual-MAE: Adaptive Distribution Masked Autoencoders for Continual Test-Time Adaptation

CVPR 2024arXiv

citations

Leveraging Imagery Data with Spatial Point Prior for Weakly Semi-supervised 3D Object Detection

AAAI 2024arXiv

citations

VFM-Adapter: Adapting Visual Foundation Models for Dense Prediction with Dynamic Hybrid Operation Mapping

AAAI 2025

citations

Learning from Noisy Data for Semi-Supervised 3D Object Detection

ICCV 2023

citations

Zehui Chen

papers (11)

LiDAR-LLM: Exploring the Potential of Large Language Models for 3D LiDAR Understanding

Deformable Feature Aggregation for Dynamic Multi-modal 3D Object Detection

DETRDistill: A Universal Knowledge Distillation Framework for DETR-families

Stream Query Denoising for Vectorized HD-Map Construction

Exploring Sparse Visual Prompt for Domain Adaptive Dense Prediction

Towards Domain Generalization for Multi-View 3D Object Detection in Bird-Eye-View

Unsupervised Domain Adaptation for Monocular 3D Object Detection via Self-Training

Continual-MAE: Adaptive Distribution Masked Autoencoders for Continual Test-Time Adaptation

Leveraging Imagery Data with Spatial Point Prior for Weakly Semi-supervised 3D Object Detection

VFM-Adapter: Adapting Visual Foundation Models for Dense Prediction with Dynamic Hybrid Operation Mapping

Learning from Noisy Data for Semi-Supervised 3D Object Detection

papers (11)

LiDAR-LLM: Exploring the Potential of Large Language Models for 3D LiDAR Understanding

Deformable Feature Aggregation for Dynamic Multi-modal 3D Object Detection

DETRDistill: A Universal Knowledge Distillation Framework for DETR-families

Stream Query Denoising for Vectorized HD-Map Construction

Exploring Sparse Visual Prompt for Domain Adaptive Dense Prediction

Towards Domain Generalization for Multi-View 3D Object Detection in Bird-Eye-View

Unsupervised Domain Adaptation for Monocular 3D Object Detection via Self-Training

Continual-MAE: Adaptive Distribution Masked Autoencoders for Continual Test-Time Adaptation

Leveraging Imagery Data with Spatial Point Prior for Weakly Semi-supervised 3D Object Detection

VFM-Adapter: Adapting Visual Foundation Models for Dense Prediction with Dynamic Hybrid Operation Mapping

Learning from Noisy Data for Semi-Supervised 3D Object Detection