Explanipedia

ChromouVQA: Benchmarking Vision-Language Models under Chromatic Camouflaged Images Open

Z. P. Yao, Haoyan Xu, Zhen Yao · 2025

Vision-Language Models (VLMs) have advanced multimodal understanding, yet still struggle when targets are embedded in cluttered backgrounds requiring figure-ground segregation. To address this, we introduce ChromouVQA, a large-scale, multi…

TAGFN: A Text-Attributed Graph Dataset for Fake News Detection in the Age of LLMs Open

Kay Liu, Haoyan Xu, Henry Peng Zou, Shihua Zhao · 2025

Large Language Models (LLMs) have recently revolutionized machine learning on text-attributed graphs, but the application of LLMs to graph outlier detection, particularly in the context of fake news detection, remains significantly underex…

A Systematic Study of Model Extraction Attacks on Graph Foundation Models Open

Haoyan Xu, Ruizhi Qian, Jiate Li, Yushun Dong, Minghong Lin , et al. · 2025

Graph machine learning has advanced rapidly in tasks such as link prediction, anomaly detection, and node classification. As models scale up, pretrained graph models have become valuable intellectual assets because they encode extensive co…

FedPSFV: Personalized Federated Learning via Prototype Sharing for Finger Vein Recognition Open

Haoyan Xu, Yuyang Guo, Yan Qu, Jian Guo, Hengyi Ren · 2025

Finger vein recognition algorithms based on deep learning techniques are widely used in many fields. However, the training of finger vein recognition models is hindered by privacy issues and the scarcity of public datasets. Although applyi…

Generative AI for Simulating Real World Dynamics Applications and Challenges Open

Yao Chen, Qishi Zhan, Zhongye Cao, Danping Li, Yangfan Lin , et al. · 2025

AMMKD: Adaptive Multimodal Multi-teacher Distillation for Lightweight Vision-Language Models Open

Yong Xiang Li, Chuanguang Yang, Junhao Dong, Z. P. Yao, Haoyan Xu , et al. · 2025

The success of large-scale visual language pretraining (VLP) models has driven widespread adoption of image-text retrieval tasks. However, their deployment on mobile devices remains limited due to large model sizes and computational comple…

CATP: Contextually Adaptive Token Pruning for Efficient and Enhanced Multimodal In-Context Learning Open

Yanshu Li, Jianjiang Yang, Zhi-Qiang Shen, Ligong Han, Haoyan Xu , et al. · 2025

Modern large vision-language models (LVLMs) convert each input image into a large set of tokens that far outnumber the text tokens. Although this improves visual perception, it also introduces severe image token redundancy. Because image t…

Frequency division optoelectronic oscillator for high division factor Open

Chong Liu, Xinpeng Wang, Qizhuang Cen, Huan Xu, Feifei Yin , et al. · 2025

An optoelectronic oscillator (OEO) is a traditional microwave photonic loop for low-phase-noise signal generation and processing. OEOs also find applications in many other fields, such as frequency division. Frequency division plays a cruc…

GLIP-OOD: Zero-Shot Graph OOD Detection with Graph Foundation Model Open

Haoyan Xu, Z. P. Yao, Xuzhi Zhang, Ziyi Wang, Langzhou He , et al. · 2025

Out-of-distribution (OOD) detection is critical for ensuring the safety and reliability of machine learning systems, particularly in dynamic and open-world environments. In the vision and text domains, zero-shot OOD detection - which requi…

Hydraulic Support Liquid Supply System Adaptive Pump Controlled Pressure Stabilization Control Under Strong Time-Varying Load Open

Chao Cao, Ke Gao, Hao Wang, Y. B. Pan, Zanhong Deng , et al. · 2024

The hydraulic support liquid supply system provided power for the hydraulic support, serving as the core to ensure safe support of the coal mining face and to maintain continuous, efficient, and stable advancement of the coal mining operat…

LEGO-Learn: Label-Efficient Graph Open-Set Learning Open

Haoyan Xu, Kay Liu, Z. P. Yao, Philip S. Yu, Kaize Ding , et al. · 2024

How can we train graph-based models to recognize unseen classes while keeping labeling costs low? Graph open-set learning (GOL) and out-of-distribution (OOD) detection aim to address this challenge by training models that can accurately cl…

A Highly Sensitive, Low Creep Hydrogel Sensor for Plant Growth Monitoring Open

Haoyan Xu, Guangyao Zhang, Wensheng Wang, Chenrui Sun, Hanyu Wang , et al. · 2024

Ion−conducting hydrogels show significant potential in plant growth monitoring. Nevertheless, traditional ionic hydrogel sensors experience substantial internal creep and inadequate sensitivity, hindering precise plant growth monitoring. I…

Novel Flexible Temperature Sensor Based on Polyvinyl Alcohol Acrylamide Hydrogels with Moisture Content Compensation Open

Yuan Bai, Liangkuan Zhu, Haoyan Xu · 2024

Flexible temperature sensors are of considerable importance in many industrial and domestic fields such as medical care, agriculture, and food.We report a novel flexible temperature sensor based on polyvinyl alcohol acrylamide hydrogels wi…

Research on Service Industry Development Strategy of Guangxi Based on Data Mining Open

Wengui Liu, Zhichao Li, Bowen Zheng, Haoyan Xu, Meng Huang · 2024

With the rapid development of China's economy, the service industry has become an important part of the national economy, among which tourism, as an important pillar of the service industry, has a significant role in promoting regional eco…

High-resolution reconfigurable RF signal spectral processor Open

Zikai Yin, Feifei Yin, Guchang Chen, Haoyan Xu, Zheng Wang , et al. · 2023

Recent developments in microwave photonic filters (MPFs) offer superior properties for radio frequency (RF) signal processing, such as large instantaneous bandwidth, high resolution and multifunctional shapes. However, it is quite challeng…

High Throughput Fabrication of Flexible Top-Driven Sensing Probe Open

Fei Li, Xi Liu, Wensheng Wang, Haoyan Xu, Wenlong Song , et al. · 2022

In this work, considering the current status of conservative and complicated traditional thrombosis treatment methods, a kind of flexible intelligent probe (FIP) with a top-driven sensing strategy is proposed to realize the expected functi…

Multivariate Time Series Forecasting with Transfer Entropy Graph Open

Ziheng Duan, Haoyan Xu, Yida Huang, Jie Feng, Yueyang Wang · 2022

Multivariate Time Series (MTS) forecasting is an essential problem in many fields. Accurate forecasting results can effectively help in making decisions. To date, many MTS forecasting methods have been proposed and widely applied. However,…

A Highly Sensitive, Ultra-Durable, Eco-Friendly Ionic Skin for Human Motion Monitoring Open

Zhaoxin Li, Haoyan Xu, Na Jia, Yifei Li, Liangkuan Zhu , et al. · 2022

Ionic conductive hydrogels have shown great potential in areas such as wearable devices and electronic skins. Aiming at the sensitivity and biodegradability of the traditional flexible hydrogel electronic skin, this paper developed an ioni…

Dubhe: a deep-learning-based B5G coverage analysis method Open

Haoyan Xu, Xiaolong Xu, Fu Xiao · 2021

In recent years, with the rapid development of various technologies such as the Internet of Things and the Internet, the demand for massive device connections and a variety of differentiated new business applications has continued to incre…

Multivariate Time Series Classification with Hierarchical Variational Graph Pooling Open

Ziheng Duan, Haoyan Xu, Yueyang Wang, Yida Huang, Anni Ren , et al. · 2020

With the advancement of sensing technology, multivariate time series classification (MTSC) has recently received considerable attention. Existing deep learning-based MTSC techniques, which mostly rely on convolutional or recurrent neural n…

Modeling Complex Spatial Patterns with Temporal Features via Heterogenous Graph Embedding Networks. Open

Yida Huang, Haoyan Xu, Ziheng Duan, Anni Ren, Jie Feng , et al. · 2020

Multivariate time series (MTS) forecasting is an important problem in many fields. Accurate forecasting results can effectively help decision-making. Variables in MTS have rich relations among each other and the value of each variable in M…

MTHetGNN: A Heterogeneous Graph Embedding Framework for Multivariate Time Series Forecasting Open

Yueyang Wang, Ziheng Duan, Yida Huang, Haoyan Xu, Jie Feng , et al. · 2020

Multivariate time series forecasting, which analyzes historical time series to predict future trends, can effectively help decision-making. Complex relations among variables in MTS, including static, dynamic, predictable, and latent relati…

Parallel Extraction of Long-term Trends and Short-term Fluctuation Framework for Multivariate Time Series Forecasting Open

Haoyan Xu, Ziheng Duan, Yida Huang, Jie Feng, Anni Ren , et al. · 2020

Multivariate time series forecasting is widely used in various fields. Reasonable prediction results can assist people in planning and decision-making, generate benefits and avoid risks. Normally, there are two characteristics of time seri…

Improved object recognition using neural networks trained to mimic the brain’s statistical properties Open

Callie Federer, Haoyan Xu, Alona Fyshe, Joel Zylberberg · 2020

Graph Partitioning and Graph Neural Network based Hierarchical Graph Matching for Graph Similarity Computation Open

Haoyan Xu, Ziheng Duan, Jie Feng, Runjian Chen, Qianru Zhang , et al. · 2020

Graph similarity computation aims to predict a similarity score between one pair of graphs to facilitate downstream applications, such as finding the most similar chemical compounds similar to a query compound or Fewshot 3D Action Recognit…

Hierarchical Large-scale Graph Similarity Computation via Graph Coarsening and Matching Open

Haoyan Xu, Runjian Chen, Yunsheng Bai, Ziheng Duan, Jie Feng , et al. · 2020

In this work, we focus on large graph similarity computation problem and propose a novel embedding-coarsening-matching learning framework, which outperforms state-of-the-art methods in this task and has significant improvement in time effi…

Hierarchical and Fast Graph Similarity Computation via Graph Coarsening and Deep Graph Learning. Open

Haoyan Xu, Runjian Chen, Yunsheng Bai, Jie Feng, Ziheng Duan , et al. · 2020

In this work, we focus on large graph similarity computation problem and propose a novel embedding-coarsening-matching learning framework, which outperforms state-of-the-art methods in this task and has significant improvement in time effi…

CoSimGNN: Towards Large-scale Graph Similarity Computation Open

Haoyan Xu, Runjian Chen, Yunsheng Bai, Ziheng Duan, Jie Feng , et al. · 2020

The ability to compute similarity scores between graphs based on metrics such as Graph Edit Distance (GED) is important in many real-world applications. Computing exact GED values is typically an NP-hard problem and traditional algorithms …

Multivariate Time Series Forecasting with Transfer Entropy Graph Open

Ziheng Duan, Haoyan Xu, Yida Huang, Jie Feng, Yueyang Wang · 2020

Multivariate time series (MTS) forecasting is an essential problem in many fields. Accurate forecasting results can effectively help decision-making. To date, many MTS forecasting methods have been proposed and widely applied. However, the…

Multivariate Time Series Forecasting Based on Causal Inference with Transfer Entropy and Graph Neural Network. Open

Haoyan Xu, Yida Huang, Ziheng Duan, Jie Feng, Pengyu Song · 2020

Multivariate time series (MTS) forecasting is an important problem in many fields. Accurate forecasting results can effectively help decision-making. To date, many MTS forecasting methods have been proposed and widely applied. However, the…

Haoyan Xu YOU? Author Swipe