Min-Hung Chen

papers

1,037

total citations

papers (11)

2D-3D Interlaced Transformer for Point Cloud Segmentation with Scene-Level Supervision

ICCV 2023arXiv

citations

PartDistill: 3D Shape Part Segmentation by Vision-Language Model Distillation

CVPR 2024arXiv

citations

Image-Text Co-Decomposition for Text-Supervised Semantic Segmentation

CVPR 2024arXiv

citations

Learning Continuous Exposure Value Representations for Single-Image HDR Reconstruction

ICCV 2023arXiv

citations

LongSplat: Robust Unposed 3D Gaussian Splatting for Casual Long Videos

ICCV 2025arXiv

citations

AuraFusion360: Augmented Unseen Region Alignment for Reference-based 360° Unbounded Scene Inpainting

CVPR 2025arXiv

citations

Omni-RGPT: Unifying Image and Video Region-level Understanding via Token Marks

CVPR 2025arXiv

citations

HERMES: temporal-coHERent long-forM understanding with Episodes and Semantics

ICCV 2025arXiv

citations

Min-Hung Chen

papers (11)

DoRA: Weight-Decomposed Low-Rank Adaptation

Action Segmentation With Joint Self-Supervised Temporal Domain Adaptation

Hymba: A Hybrid-head Architecture for Small Language Models

2D-3D Interlaced Transformer for Point Cloud Segmentation with Scene-Level Supervision

PartDistill: 3D Shape Part Segmentation by Vision-Language Model Distillation

Image-Text Co-Decomposition for Text-Supervised Semantic Segmentation

Learning Continuous Exposure Value Representations for Single-Image HDR Reconstruction

LongSplat: Robust Unposed 3D Gaussian Splatting for Casual Long Videos

AuraFusion360: Augmented Unseen Region Alignment for Reference-based 360° Unbounded Scene Inpainting

Omni-RGPT: Unifying Image and Video Region-level Understanding via Token Marks

HERMES: temporal-coHERent long-forM understanding with Episodes and Semantics

papers (11)

DoRA: Weight-Decomposed Low-Rank Adaptation

Action Segmentation With Joint Self-Supervised Temporal Domain Adaptation

Hymba: A Hybrid-head Architecture for Small Language Models

2D-3D Interlaced Transformer for Point Cloud Segmentation with Scene-Level Supervision

PartDistill: 3D Shape Part Segmentation by Vision-Language Model Distillation

Image-Text Co-Decomposition for Text-Supervised Semantic Segmentation

Learning Continuous Exposure Value Representations for Single-Image HDR Reconstruction

LongSplat: Robust Unposed 3D Gaussian Splatting for Casual Long Videos

AuraFusion360: Augmented Unseen Region Alignment for Reference-based 360° Unbounded Scene Inpainting

Omni-RGPT: Unifying Image and Video Region-level Understanding via Token Marks

HERMES: temporal-coHERent long-forM understanding with Episodes and Semantics