Chenhang He

papers

544

total citations

papers (10)

Voxel Set Transformer: A Set-to-Set Approach to 3D Object Detection From Point Clouds

CVPR 2022arXiv

207

citations

A Dual Weighting Label Assignment Scheme for Object Detection

CVPR 2022arXiv

113

citations

Class-Balanced Pixel-Level Self-Labeling for Domain Adaptive Semantic Segmentation

CVPR 2022arXiv

102

citations

DynaMask: Dynamic Mask Selection for Instance Segmentation

CVPR 2023arXiv

citations

One-to-Few Label Assignment for End-to-End Dense Detection

CVPR 2023arXiv

citations

MSF: Motion-Guided Sequential Fusion for Efficient 3D Object Detection From Point Cloud Sequences

CVPR 2023arXiv

citations

SIM: Semantic-Aware Instance Mask Generation for Box-Supervised Instance Segmentation

CVPR 2023arXiv

citations

Chenhang He

papers (10)

Voxel Set Transformer: A Set-to-Set Approach to 3D Object Detection From Point Clouds

A Dual Weighting Label Assignment Scheme for Object Detection

Class-Balanced Pixel-Level Self-Labeling for Domain Adaptive Semantic Segmentation

DynaMask: Dynamic Mask Selection for Instance Segmentation

One-to-Few Label Assignment for End-to-End Dense Detection

MSF: Motion-Guided Sequential Fusion for Efficient 3D Object Detection From Point Cloud Sequences

SIM: Semantic-Aware Instance Mask Generation for Box-Supervised Instance Segmentation

ScatterFormer: Efficient Voxel Transformer with Scattered Linear Attention

Dense Multimodal Alignment for Open-Vocabulary 3D Scene Understanding

Structure Aware Single-Stage 3D Object Detection From Point Cloud

papers (10)

Voxel Set Transformer: A Set-to-Set Approach to 3D Object Detection From Point Clouds

A Dual Weighting Label Assignment Scheme for Object Detection

Class-Balanced Pixel-Level Self-Labeling for Domain Adaptive Semantic Segmentation

DynaMask: Dynamic Mask Selection for Instance Segmentation

One-to-Few Label Assignment for End-to-End Dense Detection

MSF: Motion-Guided Sequential Fusion for Efficient 3D Object Detection From Point Cloud Sequences

SIM: Semantic-Aware Instance Mask Generation for Box-Supervised Instance Segmentation

ScatterFormer: Efficient Voxel Transformer with Scattered Linear Attention

Dense Multimodal Alignment for Open-Vocabulary 3D Scene Understanding

Structure Aware Single-Stage 3D Object Detection From Point Cloud