Zongyuan Ge

papers

857

total citations

papers (19)

Hunting Attributes: Context Prototype-Aware Learning for Weakly Supervised Semantic Segmentation

CVPR 2024arXiv

citations

OphCLIP: Hierarchical Retrieval-Augmented Learning for Ophthalmic Surgical Video-Language Pretraining

ICCV 2025arXiv

citations

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding

CVPR 2025arXiv

citations

Node Representation Learning in Graph via Node-to-Neighbourhood Mutual Information Maximization

CVPR 2022arXiv

citations

NurViD: A Large Expert-Level Video Database for Nursing Procedure Activity Understanding

NEURIPS 2023arXiv

citations

Diversified and Personalized Multi-rater Medical Image Segmentation

CVPR 2024arXiv

citations

Derm1M: A Million-scale Vision-Language Dataset Aligned with Clinical Ontology Knowledge for Dermatology

ICCV 2025arXiv

citations

EventRPG: Event Data Augmentation with Relevance Propagation Guidance

ICLR 2024arXiv

citations

Neighbor Does Matter: Density-Aware Contrastive Learning for Medical Semi-supervised Segmentation

AAAI 2025arXiv

citations

SynFER: Towards Boosting Facial Expression Recognition with Synthetic Data

ICCV 2025arXiv

citations

Towards Realistic Semi-supervised Medical Image Classification

AAAI 2025

citations

Differentiable Neural Architecture Search in Equivalent Space with Exploration Enhancement

NEURIPS 2020

citations

Toward Modality Gap: Vision Prototype Learning for Weakly-supervised Semantic Segmentation with CLIP

AAAI 2025arXiv

citations

Generalized Category Discovery under Domain Shift: A Frequency Domain Perspective

NEURIPS 2025arXiv

citations

Zongyuan Ge

papers (19)

Hierarchical Neural Architecture Search for Deep Stereo Matching

Vision-Language Navigation With Random Environmental Mixup

Implicit Motion Handling for Video Camouflaged Object Detection

Towards Trustable Skin Cancer Diagnosis via Rewriting Model's Decision

ZSTAD: Zero-Shot Temporal Activity Detection

Hunting Attributes: Context Prototype-Aware Learning for Weakly Supervised Semantic Segmentation

OphCLIP: Hierarchical Retrieval-Augmented Learning for Ophthalmic Surgical Video-Language Pretraining

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding

Node Representation Learning in Graph via Node-to-Neighbourhood Mutual Information Maximization

NurViD: A Large Expert-Level Video Database for Nursing Procedure Activity Understanding

Diversified and Personalized Multi-rater Medical Image Segmentation

Derm1M: A Million-scale Vision-Language Dataset Aligned with Clinical Ontology Knowledge for Dermatology

EventRPG: Event Data Augmentation with Relevance Propagation Guidance

Neighbor Does Matter: Density-Aware Contrastive Learning for Medical Semi-supervised Segmentation

SynFER: Towards Boosting Facial Expression Recognition with Synthetic Data

Towards Realistic Semi-supervised Medical Image Classification

Differentiable Neural Architecture Search in Equivalent Space with Exploration Enhancement

Toward Modality Gap: Vision Prototype Learning for Weakly-supervised Semantic Segmentation with CLIP

Generalized Category Discovery under Domain Shift: A Frequency Domain Perspective

papers (19)

Hierarchical Neural Architecture Search for Deep Stereo Matching

Vision-Language Navigation With Random Environmental Mixup

Implicit Motion Handling for Video Camouflaged Object Detection

Towards Trustable Skin Cancer Diagnosis via Rewriting Model's Decision

ZSTAD: Zero-Shot Temporal Activity Detection

Hunting Attributes: Context Prototype-Aware Learning for Weakly Supervised Semantic Segmentation

OphCLIP: Hierarchical Retrieval-Augmented Learning for Ophthalmic Surgical Video-Language Pretraining

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding

Node Representation Learning in Graph via Node-to-Neighbourhood Mutual Information Maximization

NurViD: A Large Expert-Level Video Database for Nursing Procedure Activity Understanding

Diversified and Personalized Multi-rater Medical Image Segmentation

Derm1M: A Million-scale Vision-Language Dataset Aligned with Clinical Ontology Knowledge for Dermatology

EventRPG: Event Data Augmentation with Relevance Propagation Guidance

Neighbor Does Matter: Density-Aware Contrastive Learning for Medical Semi-supervised Segmentation

SynFER: Towards Boosting Facial Expression Recognition with Synthetic Data

Towards Realistic Semi-supervised Medical Image Classification

Differentiable Neural Architecture Search in Equivalent Space with Exploration Enhancement

Toward Modality Gap: Vision Prototype Learning for Weakly-supervised Semantic Segmentation with CLIP

Generalized Category Discovery under Domain Shift: A Frequency Domain Perspective