Minghao Chen

papers

2,313

total citations

papers (17)

CLIP Is Also an Efficient Segmenter: A Text-Driven Approach for Weakly Supervised Semantic Segmentation

CVPR 2023arXiv

189

citations

PVT-SSD: Single-Stage 3D Object Detector With Point-Voxel Transformer

CVPR 2023arXiv

citations

Searching the Search Space of Vision Transformer

NEURIPS 2021arXiv

citations

Frame-Wise Action Representations for Long Videos via Sequence Contrastive Learning

CVPR 2022arXiv

citations

PartGen: Part-level 3D Generation and Reconstruction with Multi-view Diffusion Models

CVPR 2025arXiv

citations

SHAP-EDITOR: Instruction-Guided Latent 3D Editing in Seconds

CVPR 2024arXiv

citations

TagCLIP: A Local-to-Global Framework to Enhance Open-Vocabulary Multi-Label Classification of CLIP without Training

AAAI 2024arXiv

citations

Salient Object Ranking With Position-Preserved Attention

ICCV 2021arXiv

citations

One-Shot Neural Ensemble Architecture Search by Diversity-Guided Search Space Shrinking

CVPR 2021arXiv

citations

AutoPartGen: Autoregressive 3D Part Generation and Discovery

NEURIPS 2025

citations

Pseudo Label Refinery for Unsupervised Domain Adaptation on Cross-dataset 3D Object Detection

CVPR 2024arXiv

citations

Adapt2Reward: Adapting Video-Language Models to Generalizable Robotic Rewards via Failure Prompts

ECCV 2024arXiv

citations

STraj: Self-training for Bridging the Cross-Geography Gap in Trajectory Prediction

AAAI 2025

citations

Minghao Chen

papers (17)

VGGT: Visual Geometry Grounded Transformer

Expanding Language-Image Pretrained Models for General Video Recognition

Rethinking and Improving Relative Position Encoding for Vision Transformer

AutoFormer: Searching Transformers for Visual Recognition

CLIP Is Also an Efficient Segmenter: A Text-Driven Approach for Weakly Supervised Semantic Segmentation

PVT-SSD: Single-Stage 3D Object Detector With Point-Voxel Transformer

Searching the Search Space of Vision Transformer

Frame-Wise Action Representations for Long Videos via Sequence Contrastive Learning

PartGen: Part-level 3D Generation and Reconstruction with Multi-view Diffusion Models

SHAP-EDITOR: Instruction-Guided Latent 3D Editing in Seconds

TagCLIP: A Local-to-Global Framework to Enhance Open-Vocabulary Multi-Label Classification of CLIP without Training

Salient Object Ranking With Position-Preserved Attention

One-Shot Neural Ensemble Architecture Search by Diversity-Guided Search Space Shrinking

AutoPartGen: Autoregressive 3D Part Generation and Discovery

Pseudo Label Refinery for Unsupervised Domain Adaptation on Cross-dataset 3D Object Detection

Adapt2Reward: Adapting Video-Language Models to Generalizable Robotic Rewards via Failure Prompts

STraj: Self-training for Bridging the Cross-Geography Gap in Trajectory Prediction

papers (17)

VGGT: Visual Geometry Grounded Transformer

Expanding Language-Image Pretrained Models for General Video Recognition

Rethinking and Improving Relative Position Encoding for Vision Transformer

AutoFormer: Searching Transformers for Visual Recognition

CLIP Is Also an Efficient Segmenter: A Text-Driven Approach for Weakly Supervised Semantic Segmentation

PVT-SSD: Single-Stage 3D Object Detector With Point-Voxel Transformer

Searching the Search Space of Vision Transformer

Frame-Wise Action Representations for Long Videos via Sequence Contrastive Learning

PartGen: Part-level 3D Generation and Reconstruction with Multi-view Diffusion Models

SHAP-EDITOR: Instruction-Guided Latent 3D Editing in Seconds

TagCLIP: A Local-to-Global Framework to Enhance Open-Vocabulary Multi-Label Classification of CLIP without Training

Salient Object Ranking With Position-Preserved Attention

One-Shot Neural Ensemble Architecture Search by Diversity-Guided Search Space Shrinking

AutoPartGen: Autoregressive 3D Part Generation and Discovery

Pseudo Label Refinery for Unsupervised Domain Adaptation on Cross-dataset 3D Object Detection

Adapt2Reward: Adapting Video-Language Models to Generalizable Robotic Rewards via Failure Prompts

STraj: Self-training for Bridging the Cross-Geography Gap in Trajectory Prediction