Shanshan Wang

ProtoPSR: Prototype-guided Pairwise Similarity Regularization for Robust Spatial Multi-Omics Integration

Yu Zhang, Mengzhu Wang, Luoxi Jing, Shanshan Wang et autres

cn, hk (code pays fourni par la source)

TypiCD: Cognitive Diagnosis via Problem-Type-Guided Bias Correction

Shanshan Wang, Yali Ye, Xun Yang, Pichao Wang et autres

cn, us (code pays fourni par la source)

Towards personalized long-term learning modeling in knowledge tracing

Shanshan Wang, Jianqi Qiu, JiaXin Pang, Xun Yang et autres

cn (code pays fourni par la source)

Style-Aware Contrastive Test-Time Adaptation: A Dual-Cache Model for Robust Vision-Language Alignment

Shanshan Wang, ALuSi, Xun Yang, Pichao Wang et autres

Test-time adaptation (TTA) has emerged as a key strategy to enhance vision-language models (VLMs) under real-world distribution changes. However, existing methods always face two problems: 1) The fundamental trade-off dilemma: parameter-free TTA retains inference efficiency but fails to correct modality misalignment, while …

cn, us (code pays fourni par la source)

ASCD: An Adaptive Framework for Long-Tailed Cognitive Diagnosis

Shanshan Wang, Zhen Zeng, Xun Yang, Yuanhong Zhong et autres

Cognitive Diagnosis Modeling is a fundamental task in intelligent education, intending to assess students’ mastery levels on knowledge concepts through interactions. Previous methodologies prioritized enhancing average diagnostic accuracy. However, they often neglected the Long-Tailed issue in interactions. To address this issue, we …

cn (code pays fourni par la source)

Antimicrobial paeonol modulates efflux pumps and membrane permeability in Aeromonas hydrophila: Proteomic insights and application in grass carp meat preservation

Xin Chen, Zhengyang Zhu, Lishan Zhang, Xiaowei Zhang et autres

The growing drug resistance of the fish pathogen Aeromonas hydrophila places a significant strain on aquaculture production and food safety. Paeonol, a plant-derived compound, exhibits substantial antibacterial potential. Our study shows that paeonol inhibits 12 bacterial strains, with an IC 50 of …

cn (code pays fourni par la source)

AI-Enabled Integration of Chang'an-Themed Tang Poetry into French Language Teaching: Path Model Construction and Competency Cultivation Effect Analysis

Shanshan Wang

Against the “New Liberal Arts” and Chinese culture international dissemination backdrop, integrating traditional Chinese culture into foreign language teaching to foster interdisciplinary talents is critical. This paper constructs an AI-enabled four-year progressive model for integrating Chang'an-themed Tang poetry into undergraduate French curricula, …

cn (code pays fourni par la source)

FOUND: Fourier-based von Mises Distribution for Robust Single Domain Generalization in Object Detection

Mengzhu Wang, Shanshan Wang, Nan Yin, Long Lan et autres

Single Domain Generalization (SDG) for object detection aims to train a model on a single source domain that can generalize effectively to unseen target domains. While recent methods like CLIP-based semantic augmentation have shown promise, they often overlook the underlying structure of …

Unified Brain Network Representation Learning via Adaptive Multimodal Fusion for Alzheimer’s Disease Analysis

Hongjie Jiang, Yongcheng Zong, Guoheng Huang, Sibo Qiao et autres

The fusion of structural and functional brain network analysis has been widely applied in the analysis of various brain diseases, especially in identifying the progression stages of Alzheimer’s disease. However, most existing multimodal brain network analysis methods separately construct functional and structural …

cn, hk (code pays fourni par la source)

Probability-Guided Contrastive Learning for Long-Tailed Domain Generalization

Houcheng Su, Shanshan Wang, Nan Yin, Long Lan et autres

After training on a specific source domain, models can leverage domain generalization (DG) techniques to achieve superior and broader performance on new, unseen target domains. Existing DG often utilizes contrastive learning to learn domain-invariant features. The goal of contrastive learning is to …

cn, hk, ae (code pays fourni par la source)

Cerebrovascular Diseases Screening from Color Fundus Photography via Cross-View Fusion and Graph-Based Discrimination

Congyu Tian, Shihao Zou, Xiangyun Liao, Cheng Chen et autres

cn, hk (code pays fourni par la source)

Local-Global Feature Fusion for Enhancing 3D Human Pose Estimation

Yuanhong Zhong, Guangxia Yang, Daidi Zhong, Xun Yang et autres

Based on its excellent capability to extract temporal features, transformer has been widely used in monocular 3D human pose estimation. However, due to its global perspective, it performs inadequately in extracting spatial features, which hinders breakthroughs in performance. In this paper, we …

cn (code pays fourni par la source)