Zongyuan Ge

18

Papers

105

Total Citations

Papers (18)

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

Diversified and Personalized Multi-rater Medical Image Segmentation

EventRPG: Event Data Augmentation with Relevance Propagation Guidance

SynFER: Towards Boosting Facial Expression Recognition with Synthetic Data

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

Towards Realistic Semi-supervised Medical Image Classification

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

ZSTAD: Zero-Shot Temporal Activity Detection

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

Implicit Motion Handling for Video Camouflaged Object Detection

Towards Trustable Skin Cancer Diagnosis via Rewriting Model's Decision

Vision-Language Navigation With Random Environmental Mixup

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

Differentiable Neural Architecture Search in Equivalent Space with Exploration Enhancement

Hierarchical Neural Architecture Search for Deep Stereo Matching

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