Jie Wen

Full Professor@Harbin Institute of Technology·中国·OpenReview

研究方向

multi-view learning · incomplete multi-view clustering · multi-modal learning · Multi-view learning · clustering · classification · feature extraction

Jie Wen

Permutation-Consistent Variational Encoding for Incomplete Multi-View Multi-Label Classification

Confident Block Diagonal Structure-Aware Invariable Graph Completion for Incomplete Multi-view Clustering

Efficient Visual Grounding via Alignment Priors and Scale Adaptability

Expert-Guided Cross-View Fusion with Self-Derived Lesion Proposals for Multi-View Diabetic Retinopathy Grading

DKP: Semantic Consistency Distillation via Key-layer Pre-alignment with Large Vision-language Models for Cross-Modal Retrieval

WGREC: Weakly Supervised Generalized Referring Expression Comprehension Empowered by Large Language Model

SAID: Empowering Large Language Models with Self-Activating Internal Defense

SPARC: Multi-view Spatial Transcriptomics Clustering via Prototypical Contrast and Attentional Fusion

Learning from Disjoint Views: A Contrastive Prototype Matching Network for Fully Incomplete Multi-View Clustering

NeuroH-TGL: Neuro-Heterogeneity Guided Temporal Graph Learning Strategy for Brain Disease Diagnosis

A Set of Generalized Components to Achieve Effective Poison-only Clean-label Backdoor Attacks with Collaborative Sample Selection and Triggers

Confidence-Aware With Prototype Alignment for Partial Multi-label Learning

Hierarchical Information Aggregation for Incomplete Multimodal Alzheimer's Disease Diagnosis

Vad-R1: Towards Video Anomaly Reasoning via Perception-to-Cognition Chain-of-Thought