Weijun Lv

Feature-Label Modal Alignment for Robust Partial Multi-Label Learning

Yu Chen, Weijun Lv, Yue Huang, Xiaozhao Fang et autres

In partial multi-label learning (PML), each instance is associated with a set of candidate labels containing both ground-truth and noisy labels. The presence of noisy labels disrupts the correspondence between features and labels, degrading classification performance. To address this challenge, we propose …

Bringing Clustering to MLL: Weakly-Supervised Clustering for Partial Multi-Label Learning

Yu Chen, Weijun Lv, Yue Huang, Xuhuan Zhu et autres

Label noise in multi-label learning (MLL) poses significant challenges for model training, particularly in partial multi-label learning (PML) where candidate labels contain both relevant and irrelevant labels. While clustering offers a natural approach to exploit data structure for noise identification, traditional clustering …

Bringing Clustering to MLL: Weakly-Supervised Clustering for Partial Multi-Label Learning

Yu Chen, Weijun Lv, Yue Huang, Xuhuan Zhu et autres

Label noise in multi-label learning (MLL) poses significant challenges for model training, particularly in partial multi-label learning (PML) where candidate labels contain both relevant and irrelevant labels. While clustering offers a natural approach to exploit data structure for noise identification, traditional clustering …

cn (code pays fourni par la source)

Feature-Label Modal Alignment for Robust Partial Multi-Label Learning

Yu Chen, Weijun Lv, Yue Huang, Xiaozhao Fang et autres

In partial multi-label learning (PML), each instance is associated with a set of candidate labels containing both ground-truth and noisy labels. The presence of noisy labels disrupts the correspondence between features and labels, degrading classification performance. To address this challenge, we propose …

cn (code pays fourni par la source)

Prototype-Based Semantic Consistency Alignment for Domain Adaptive Retrieval

Tianle Hu, Weijun Lv, Na Han, Xiaozhao Fang et autres

Domain adaptive retrieval aims to transfer knowledge from a labeled source domain to an unlabeled target domain, enabling effective retrieval while mitigating domain discrepancies. However, existing methods encounter several fundamental limitations: 1) neglecting class-level semantic alignment and excessively pursuing pair-wise sample alignment; …

cn (code pays fourni par la source)

Prototype-Based Semantic Consistency Alignment for Domain Adaptive Retrieval

Association for Artificial Intelligence 2026, Xiaozhao Fang, Na Han, Tianle Hu et autres

Domain adaptive retrieval aims to transfer knowledge from a labeled source domain to an unlabeled target domain, enabling effective retrieval while mitigating domain discrepancies. However, existing methods encounter several fundamental limitations: 1) neglecting class-level semantic alignment and excessively pursuing pair-wise sample alignment; …

cn (code pays fourni par la source)

1341 - Prototype-Based Semantic Consistency Alignment for Domain Adaptive Retrieval

Association for Artificial Intelligence 2026, Xiaozhao Fang, Na Han, Tianle Hu et autres

Domain adaptive retrieval aims to transfer knowledge from a labeled source domain to an unlabeled target domain, enabling effective retrieval while mitigating domain discrepancies. However, existing methods encounter several fundamental limitations: 1) neglecting class-level semantic alignment and excessively pursuing pair-wise sample alignment; …

cn (code pays fourni par la source)

A novel polysaccharide from Qamgur (Brassica rapa L.) mitigates pulmonary fibrosis by regulating inflammatory, epithelial-mesenchymal transition, and fibrotic pathways

Jasar Abai, YouDa Wang, Ruihan Jin, Hadiya Abduwali et autres

cn (code pays fourni par la source)

Deciphering the Molecular Pathways: How Polygonatum sibiricum Alleviates Myocardial Ischemia

Zhenzhong Zhu, Yuanlong Zhang, Yanxia Lv, Yunxiang Wang et autres

Herbal medicine, like Polygonatum sibiricum , is gaining attention for its potential in treating myocardial ischemia. Comprehensive research on its molecular interplay is essential for its development as a therapeutic agent. The aim is to investigate the molecular mechanisms by which Polygonatum …

cn (code pays fourni par la source)

Plasma metabolic profiling reveals that crude and processed Polygonatum cyrtonema hua extract ameliorates myocardial ischemia-induced damage by regulating branched-chain amino acid and energy metabolism

Weijun Lv, Ying Yang, Yanxia Lv, Yifan Pan et autres

cn (code pays fourni par la source)