Min Xu

papers

674

total citations

papers (19)

MedSegDiff-V2: Diffusion-based Medical Image Segmentation with Transformer

AAAI 2024arXiv

274

citations

RealNet: A Feature Selection Network with Realistic Synthetic Anomaly for Anomaly Detection

CVPR 2024arXiv

176

citations

Sparse Local Patch Transformer for Robust Face Alignment and Landmarks Inherent Relation Learning

CVPR 2022arXiv

citations

BiCro: Noisy Correspondence Rectification for Multi-Modality Data via Bi-Directional Cross-Modal Similarity Consistency

CVPR 2023arXiv

citations

Vox-UDA: Voxel-wise Unsupervised Domain Adaptation for Cryo-Electron Subtomogram Segmentation with Denoised Pseudo-Labeling

AAAI 2025arXiv

citations

DiffCAM: Data-Driven Saliency Maps by Capturing Feature Differences

CVPR 2025

citations

BOE-ViT: Boosting Orientation Estimation with Equivariance in Self-Supervised 3D Subtomogram Alignment

CVPR 2025

citations

OLMD: Orientation-aware Long-term Motion Decoupling for Continuous Sign Language Recognition

AAAI 2025arXiv

citations

Toward Material-Agnostic System Identification from Videos

ICCV 2025arXiv

citations

Harmony: A Generic Unsupervised Approach for Disentangling Semantic Content From Parameterized Transformations

CVPR 2022

citations

Gum-Net: Unsupervised Geometric Matching for Fast and Accurate 3D Subtomogram Image Alignment and Averaging

CVPR 2020

citations

Unsupervised Identification of Protein Compositions and Conformations via Implicit Content-Transformation Disentanglement

ICCV 2025

citations

Towards Molecular Structure Discovery from Cryo-ET Density Volumes via Modelling Auxiliary Semantic Prototypes

AAAI 2024

citations

Weakly Supervised 3D Semantic Segmentation Using Cross-Image Consensus and Inter-Voxel Affinity Relations

ICCV 2021

citations

End-to-End Robust Joint Unsupervised Image Alignment and Clustering

ICCV 2021

citations

Min Xu

papers (19)

MedSegDiff-V2: Diffusion-based Medical Image Segmentation with Transformer

RealNet: A Feature Selection Network with Realistic Synthetic Anomaly for Anomaly Detection

Sparse Local Patch Transformer for Robust Face Alignment and Landmarks Inherent Relation Learning

BiCro: Noisy Correspondence Rectification for Multi-Modality Data via Bi-Directional Cross-Modal Similarity Consistency

One-Prompt to Segment All Medical Images

Deep Active Learning with Noise Stability

Synergistic Global-space Camera and Human Reconstruction from Videos

Single-View 3D Object Reconstruction From Shape Priors in Memory

Vox-UDA: Voxel-wise Unsupervised Domain Adaptation for Cryo-Electron Subtomogram Segmentation with Denoised Pseudo-Labeling

DiffCAM: Data-Driven Saliency Maps by Capturing Feature Differences

BOE-ViT: Boosting Orientation Estimation with Equivariance in Self-Supervised 3D Subtomogram Alignment

OLMD: Orientation-aware Long-term Motion Decoupling for Continuous Sign Language Recognition

Toward Material-Agnostic System Identification from Videos

Harmony: A Generic Unsupervised Approach for Disentangling Semantic Content From Parameterized Transformations

Gum-Net: Unsupervised Geometric Matching for Fast and Accurate 3D Subtomogram Image Alignment and Averaging

Unsupervised Identification of Protein Compositions and Conformations via Implicit Content-Transformation Disentanglement

Towards Molecular Structure Discovery from Cryo-ET Density Volumes via Modelling Auxiliary Semantic Prototypes

Weakly Supervised 3D Semantic Segmentation Using Cross-Image Consensus and Inter-Voxel Affinity Relations

End-to-End Robust Joint Unsupervised Image Alignment and Clustering

papers (19)

MedSegDiff-V2: Diffusion-based Medical Image Segmentation with Transformer

RealNet: A Feature Selection Network with Realistic Synthetic Anomaly for Anomaly Detection

Sparse Local Patch Transformer for Robust Face Alignment and Landmarks Inherent Relation Learning

BiCro: Noisy Correspondence Rectification for Multi-Modality Data via Bi-Directional Cross-Modal Similarity Consistency

One-Prompt to Segment All Medical Images

Deep Active Learning with Noise Stability

Synergistic Global-space Camera and Human Reconstruction from Videos

Single-View 3D Object Reconstruction From Shape Priors in Memory

Vox-UDA: Voxel-wise Unsupervised Domain Adaptation for Cryo-Electron Subtomogram Segmentation with Denoised Pseudo-Labeling

DiffCAM: Data-Driven Saliency Maps by Capturing Feature Differences

BOE-ViT: Boosting Orientation Estimation with Equivariance in Self-Supervised 3D Subtomogram Alignment

OLMD: Orientation-aware Long-term Motion Decoupling for Continuous Sign Language Recognition

Toward Material-Agnostic System Identification from Videos

Harmony: A Generic Unsupervised Approach for Disentangling Semantic Content From Parameterized Transformations

Gum-Net: Unsupervised Geometric Matching for Fast and Accurate 3D Subtomogram Image Alignment and Averaging

Unsupervised Identification of Protein Compositions and Conformations via Implicit Content-Transformation Disentanglement

Towards Molecular Structure Discovery from Cryo-ET Density Volumes via Modelling Auxiliary Semantic Prototypes

Weakly Supervised 3D Semantic Segmentation Using Cross-Image Consensus and Inter-Voxel Affinity Relations

End-to-End Robust Joint Unsupervised Image Alignment and Clustering