Min Xu

Conditional local feature encoding for graph neural networks

Yongze Wang, Haimin Zhang, Qiang Wu, Min Xu

Graph neural networks (GNNs) have shown great success in learning on graph-based data. A key mechanism of current GNNs is message passing, wherein a node’s feature is updated based on information aggregated from the local neighbourhood. A consequence of this mechanism is …

au (code pays fourni par la source)

Bistatic Passive Sensing via CSI Power

Zhongqin Wang, J. Andrew Zhang, Kai Wu, Kuangda Chen et autres

Passive object sensing with communication signals is a key enabler of perceptive mobile networks and integrated sensing and communication. In practical bistatic deployments, transmitter-receiver asynchrony and hardware impairments introduce time-varying random phase offsets in Channel State Information (CSI). Together with limited bandwidth …

au (code pays fourni par la source)

PromptHG: Prompt-Enhanced Heterogeneous Graph for Personalized News Recommendation

Hai-Dang Kieu, Delvin Ce Zhang, Minh-Duc Nguyen, Qiang Wu et autres

au, vn, gb (code pays fourni par la source)

Safe and Interactive Integration of Prediction and Planning for Autonomous Vehicles with Residual Chain Loss

Donglei Rong, Congcong Bai, Wenbin Yao, Qiaoqiao Ren et autres

The Integration of Prediction and Planning (IPP) methodology enhances interrelationships between autonomous vehicle modules while improving system interpretability. However, safety, interaction, and performance evaluation present significant challenges that may lead to safety risks. This paper introduces IPP* (Safe and Interactive Integration of …

cn, hk (code pays fourni par la source)

The correlation of lactate/albumin ratio and their association for short-term and long-term mortality in patients with acute aortic dissection

Min Xu, Zhenyu Liao, Zhaorui Liu, Jiuling Chen et autres

Objective: The direct impact on survival of lactate-to-albumin ratio (LAR) in acute aortic dissection (AAD) remains uncertain. Methods: Medical electric records of 919 patients in the intensive care unit (ICU) who diagnosed with AAD were extracted from the MIMIC-IV database. These patients …

cn (code pays fourni par la source)

Noisy Correspondence Rectification in Multimodal Clustering Space for Cross-Modal Matching

Shuo Yang, Yancheng Long, Yujie Wei, Hongxun Yao et autres

As one of the most fundamental techniques in multimodal learning, cross-modal matching aims to project various sensory modalities into a shared feature space. To achieve this, massive and correctly aligned data pairs are required for model training. However, unlike unimodal datasets, multimodal …

cn, au (code pays fourni par la source)

A Multi-Modal Prompt-Tuning Framework for Non-Overlapping Multi-Domain Recommendation

Li Wang, Shoujin Wang, Qiang Wu, Min Xu

Cross-domain recommendation (CDR) aims to enhance recommendation accuracy in data-sparse domains by transferring knowledge from data-rich domains. Most existing CDR methods conduct knowledge transfer based on overlapping users or items to address the user cold-start problems, including few-shot (i.e., users with sparse …

au (code pays fourni par la source)

StructGS: Adaptive Spherical Harmonics and Rendering Enhancements for Superior 3D Gaussian Splatting

Zhuan Qing Huang, Min Xu, Stuart Perry

Recent advancements in 3D reconstruction coupled with neural rendering techniques have greatly improved the creation of photo-realistic 3D scenes, influencing both academic research and industry applications. The technique of 3D Gaussian Splatting and its variants incorporate the strengths of both primitive-based and …

au (code pays fourni par la source)

FedPCL-CDR: A federated prototype-based contrastive learning framework for privacy-preserving cross-domain recommendation

Li Wang, Qiang Wu, Min Xu

au (code pays fourni par la source)

Neighbour-level message interaction encoding for improved representation learning on graphs

Haimin Zhang, Min Xu

Message passing has become the dominant framework in graph representation learning. The essential idea of the message-passing framework is to update node embeddings based on the information aggregated from local neighbours. However, most existing aggregation methods have not encoded neighbour-level message interactions …

au (code pays fourni par la source)

GaussianFocus: Constrained Attention Focus for 3D Gaussian Splatting

Zhuan Qing Huang, Min Xu, Stuart Perry

au (code pays fourni par la source)

RLD-GS: Reinforcement Learning-Driven Gaussian Splatting for High-Fidelity Neural Rendering

Zhuan Qing Huang, Min Xu, Stuart Perry

au (code pays fourni par la source)