Xuming He

Affiliations

ShanghaiTech University

papers

2,432

total citations

papers (25)

Bipartite Graph Network With Adaptive Message Passing for Unbiased Scene Graph Generation

CVPR 2021arXiv

249

citations

GNeRF: GAN-Based Neural Radiance Field Without Posed Camera

ICCV 2021arXiv

218

citations

SGTR: End-to-End Scene Graph Generation With Transformer

CVPR 2022arXiv

145

citations

HOICLIP: Efficient Knowledge Transfer for HOI Detection With Vision-Language Models

CVPR 2023arXiv

citations

Relation-aware Instance Refinement for Weakly Supervised Visual Grounding

CVPR 2021arXiv

citations

General Incremental Learning With Domain-Aware Categorical Representations

CVPR 2022arXiv

citations

From Pixels to Graphs: Open-Vocabulary Scene Graph Generation with Vision-Language Models

CVPR 2024arXiv

citations

Dynamic Grained Encoder for Vision Transformers

NEURIPS 2021arXiv

citations

Learning Semantic Correspondence with Sparse Annotations

ECCV 2022arXiv

citations

Class-relation Knowledge Distillation for Novel Class Discovery

ICCV 2023arXiv

citations

Human-centric Scene Understanding for 3D Large-scale Scenarios

ICCV 2023arXiv

citations

Generative Negative Text Replay for Continual Vision-Language Pretraining

ECCV 2022arXiv

citations

DSGG: Dense Relation Transformer for an End-to-end Scene Graph Generation

CVPR 2024arXiv

citations

ATTA: Anomaly-aware Test-Time Adaptation for Out-of-Distribution Detection in Segmentation

NEURIPS 2023arXiv

citations

Grounded Image Text Matching with Mismatched Relation Reasoning

ICCV 2023arXiv

citations

Mining Fine-Grained Image-Text Alignment for Zero-Shot Captioning via Text-Only Training

AAAI 2024arXiv

citations

P$^2$OT: Progressive Partial Optimal Transport for Deep Imbalanced Clustering

ICLR 2024arXiv

citations

Dual-level Adaptive Self-Labeling for Novel Class Discovery in Point Cloud Segmentation

ECCV 2024arXiv

citations

Relation-aware Hierarchical Prompt for Open-vocabulary Scene Graph Generation

AAAI 2025arXiv

citations

Learning by Correction: Efficient Tuning Task for Zero-Shot Generative Vision-Language Reasoning

CVPR 2024arXiv

citations

NoisyGRPO: Incentivizing Multimodal CoT Reasoning via Noise Injection and Bayesian Estimation

NEURIPS 2025arXiv

citations

GeoDistill: Geometry-Guided Self-Distillation for Weakly Supervised Cross-View Localization

ICCV 2025arXiv

citations

Xuming He

Affiliations

papers (25)

DER: Dynamically Expandable Representation for Class Incremental Learning

Part-aware Prototype Network for Few-shot Semantic Segmentation

Distribution Alignment: A Unified Framework for Long-Tail Visual Recognition

Bipartite Graph Network With Adaptive Message Passing for Unbiased Scene Graph Generation

GNeRF: GAN-Based Neural Radiance Field Without Posed Camera

SGTR: End-to-End Scene Graph Generation With Transformer

HOICLIP: Efficient Knowledge Transfer for HOI Detection With Vision-Language Models

Relation-aware Instance Refinement for Weakly Supervised Visual Grounding

General Incremental Learning With Domain-Aware Categorical Representations

From Pixels to Graphs: Open-Vocabulary Scene Graph Generation with Vision-Language Models

Dynamic Grained Encoder for Vision Transformers

Learning Semantic Correspondence with Sparse Annotations

Class-relation Knowledge Distillation for Novel Class Discovery

Human-centric Scene Understanding for 3D Large-scale Scenarios

Generative Negative Text Replay for Continual Vision-Language Pretraining

DSGG: Dense Relation Transformer for an End-to-end Scene Graph Generation

ATTA: Anomaly-aware Test-Time Adaptation for Out-of-Distribution Detection in Segmentation

Grounded Image Text Matching with Mismatched Relation Reasoning

Mining Fine-Grained Image-Text Alignment for Zero-Shot Captioning via Text-Only Training

P$^2$OT: Progressive Partial Optimal Transport for Deep Imbalanced Clustering

Dual-level Adaptive Self-Labeling for Novel Class Discovery in Point Cloud Segmentation

Relation-aware Hierarchical Prompt for Open-vocabulary Scene Graph Generation

Learning by Correction: Efficient Tuning Task for Zero-Shot Generative Vision-Language Reasoning

NoisyGRPO: Incentivizing Multimodal CoT Reasoning via Noise Injection and Bayesian Estimation

GeoDistill: Geometry-Guided Self-Distillation for Weakly Supervised Cross-View Localization

papers (25)

DER: Dynamically Expandable Representation for Class Incremental Learning

Part-aware Prototype Network for Few-shot Semantic Segmentation

Distribution Alignment: A Unified Framework for Long-Tail Visual Recognition

Bipartite Graph Network With Adaptive Message Passing for Unbiased Scene Graph Generation

GNeRF: GAN-Based Neural Radiance Field Without Posed Camera

SGTR: End-to-End Scene Graph Generation With Transformer

HOICLIP: Efficient Knowledge Transfer for HOI Detection With Vision-Language Models

Relation-aware Instance Refinement for Weakly Supervised Visual Grounding

General Incremental Learning With Domain-Aware Categorical Representations

From Pixels to Graphs: Open-Vocabulary Scene Graph Generation with Vision-Language Models

Dynamic Grained Encoder for Vision Transformers

Learning Semantic Correspondence with Sparse Annotations

Class-relation Knowledge Distillation for Novel Class Discovery

Human-centric Scene Understanding for 3D Large-scale Scenarios

Generative Negative Text Replay for Continual Vision-Language Pretraining

DSGG: Dense Relation Transformer for an End-to-end Scene Graph Generation

ATTA: Anomaly-aware Test-Time Adaptation for Out-of-Distribution Detection in Segmentation

Grounded Image Text Matching with Mismatched Relation Reasoning

Mining Fine-Grained Image-Text Alignment for Zero-Shot Captioning via Text-Only Training

P$^2$OT: Progressive Partial Optimal Transport for Deep Imbalanced Clustering

Dual-level Adaptive Self-Labeling for Novel Class Discovery in Point Cloud Segmentation

Relation-aware Hierarchical Prompt for Open-vocabulary Scene Graph Generation

Learning by Correction: Efficient Tuning Task for Zero-Shot Generative Vision-Language Reasoning

NoisyGRPO: Incentivizing Multimodal CoT Reasoning via Noise Injection and Bayesian Estimation

GeoDistill: Geometry-Guided Self-Distillation for Weakly Supervised Cross-View Localization