检索结果-内蒙古大学图书馆

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Sun, Yatong Yang, Xiaochun Sun, Zhu Wang, Yan Wang, Bin Qu, Xinghua School of Computer Science and Engineering Northeastern University China School of Computing Macquarie University Australia Singapore University of Technology and Design Singapore National Frontiers Science Center for Industrial Intelligence and Systems Optimization China Key Laboratory of Data Analytics and Optimization for Smart Industry (Northeastern University) Ministry of Education China Bytedance(Seed) Singapore

ISBN: (纸本)157735897X

Sequential Recommenders (SRs) are trained to predict the next item as the target given its preceding items as the input, assuming every input-target pair is matched and is reliable for training. However, users can be induced by external distractions to click on items inconsistent with their true preferences, resulting in unreliable training instances with mismatched input-target pairs. To resist unreliable data, researchers attempt to develop Robust SRs (RSRs). However, our data analysis unveils that existing RSRs are data-driven. That is, for most instances formed by infrequently co-occurred items, existing RSRs are uncertain about their reliability. To fill this gap, we propose a generic framework - LLM4RSR (Large Language Models for Robust Sequential Recommendation) to semantically complement data-driven RSRs by correcting uncertain instances into reliable ones based on LLMs' semantic comprehension of items beyond co-occurrence. In this way, RSRs can be re-trained with the corrected data for better accuracy. This is a selective knowledge distillation procedure, where the LLM acts as a teacher guiding student RSRs via uncertain instances. To align LLMs with the data correction task and mitigate inherent hallucinations, we equip the LLM with profile, plan, and memory modules, which are automatically optimized via textual gradient descent, eliminating the need for human effort and expertise. Experiments on four real-world datasets spanning eight backbones verify the generality, effectiveness, and efficiency of LLM4RSR. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Transverse Velocity Field Measurement in High-Resolution Solar Images Based on Deep Learning

arXiv

引用

arXiv 2023年

作者： Shang, Zhen-Hong Mu, Si-Yu Ji, Kai-Fan Qiang, Zhen-Ping Faculty of Information Engineering and Automation Kunming University of Science and Technology Kunming650500 China Yunnan Key Laboratory of Artificial Intelligence Kunming University of Science and Technology Kunming650500 China Yunnan Observatories Chinese Academy of Sciences Kunming650216 China College of Big Data and Intelligent Engineering Southwest Forestry University Kunming650224 China

To address the problem of the low accuracy of transverse velocity field measurements for small targets in high-resolution solar images, we proposed a novel velocity field measurement method for high-resolution solar images based on PWCNet. This method transforms the transverse velocity field measurements into an optical flow field prediction problem. We evaluated the performance of the proposed method using the Hα and TiO datasets obtained from New Vacuum Solar Telescope (NVST) observations. The experimental results show that our method effectively predicts the optical flow of small targets in images compared with several typical machine- and deep-learning methods. On the Hα dataset, the proposed method improves the image structure similarity from 0.9182 to 0.9587 and reduces the mean of residuals from 24.9931 to 15.2818;on the TiO dataset, the proposed method improves the image structure similarity from 0.9289 to 0.9628 and reduces the mean of residuals from 25.9908 to 17.0194. The optical flow predicted using the proposed method can provide accurate data for the atmospheric motion information of solar images. The code implementing the proposed method is available on https:// ***/lygmsy123/transverse-velocity-field-measurement. Copyright © 2023, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Improved performance of Insight-HXMT/HE CsI detectors

引用

Science China(Physics,Mechanics & Astronomy) 2025年第7期Mechanics & Astronomy) .卷 108-120页

作者： Chao Zheng Shao-Lin Xiong Cheng-Kui Li Xiao-Bo Li Xu-Fang Li Gang Li Peng Zhang Wang-Chen Xue Yan-Qiu Zhang Cong-Zhan Liu Juan Zhang Bing Li Ming-Yu Ge Li-Ming Song Wen-Jun Tan Chen-Wei Wang Yue Wang Jin-Peng Wang Jia-Cong Liu Sheng-Lun Xie Ce Cai Shuo Xiao Wen-Long Zhang Hao-Xuan Guo Yu-Peng Xu Shu Zhang Shuang-Nan Zhang Key Laboratory of Particle Astrophysics Institute of High Energy PhysicsChinese Academy of Sciences University of Chinese Academy of Sciences College of Electronic and Information Engineering Tongji University Institute of Astrophysics Central China Normal University College of Physics and Hebei Key Laboratory of Photophysics Research and Application Hebei Normal University Guizhou Provincial Key Laboratory of Radio Astronomy and Data Processing Guizhou Normal University School of Physics and Electronic Science Guizhou Normal University School of Physics and Physical Engineering Qufu Normal University Department of Nuclear Science and Technology School of Energy and Power EngineeringXi'an Jiaotong University

As one of three primary scientific payloads of Insight-Hard X-ray Modulation Telescope（Insight-HXMT）,the High Energy Xray telescope（HE） consists of 18 Nal/CsI phoswich detectors,and the CsI detectors can detect gamma-rays that penetrate the satellite from all directions,with an energy range of about 60 keV to 3.2 MeV and a total geometric area of about 5100 *** characteristics make the CsI detectors suitable for monitoring GRBs and other high-energy *** calibration and performance studies of the CsI detectors' instrumental response were conducted during the early operation phase *** this work,we refine the cross-calibration of CsI detectors using a large sample of 85 bright *** analysis reveals that the effective area is inversely proportional to the incident angle（θ）,with no correlation observed with the azimuthal angle（θ）.We subsequently incorporated this relationship into the calibration database to correct for systematic biases in the initial ***,we demonstrate that joint spectral analyses incorporating CsI data provide better constraints on highenergy spectral parameters for most ***,we evaluate,for the first time,the energy response of CsI detectors for pointing observation by measuring the Crab Nebula using the Earth occultation *** effort extends the energy range of the Insight-HXMT telescope from 1-250 to 1-750 keV for pointing *** results show that the spectra measured by CsI detectors are consistent with other well-calibrated instruments,validating the reliability and accuracy of the CsI detectors' *** work will contribute to Insight-HXMT's capacity to generate more scientific outputs in the field of time-domain astronomy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Ultrasound-Guided Registration Pseudo-Labels for Semi-Supervised Brachial Plexus Segmentation

Ultrasound-Guided Registration Pseudo-Labels for Semi-Superv...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Jia Luo Ze Zhang Yi Ding Yiqian Wang Jian Zhang Network and Data Security Key Laboratory of Sichuan Province School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu China Yibin GREAT Technology Co. Ltd Yibin China Sichuan Provincial Hospital for Women and Children/Affilated Women and Children’s Hospital of Chengdu Medical College Chengdu China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

In semi-supervised medical image segmentation, two main challenges arise. First, the quality of pseudo-labels generated by segmentation networks in data-limited scenarios is often poor, reducing segmentation accuracy. Second, many methods fail to effectively utilize the temporal context in video data. Moreover, the intricate relationships among multiple targets make the conventional teacher-student network consistency loss unsuitable for multi-target tasks, leading to inaccurate feature capture and degraded performance. To address these issues, we propose a registration-based pseudo-label generation strategy that produces pseudo-labels more closely aligned with actual labels. Additionally, we introduce multiple guidance mechanisms into the teacher-student network to ensure correct optimization. Experimental results show that our approach significantly outperforms leading semi-supervised segmentation methods. Specifically, at a 50% label rate, our method improves the Dice coefficient by 6.9% over existing methods.

关键词： Deformable models Image segmentation Accuracy Ultrasonic imaging Deformation Signal processing Brachytherapy Speech processing Optimization Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

Roof greening in major Chinese cities possibly afford a large potential carbon sink

引用

Science Bulletin 2024年第20期69卷 3216-3220页

作者： Chao Yang Yinghui Zhang Min Chen Song Zhu Yuzhi Tang Zhixin Zhang Wei Ma Huizeng Liu Junyi Chen Bohui Tang Dejin Zhang Zhengdong Huang Xuqing Wang Wei Tu Cuiling Liu Tiezhu Shi Haiying Xu Aihong Cui Fanyi Meng Tianhong Zhao Kai Guo Wenhao Guo Bi Fan Quande Qin Wuyang Hong Haishan Wu Bing Wang Jinrong Zeng Ka Wai Wu Qingquan Li Key Laboratory for Geo-Environmental Monitoring of Great Bay Area Ministry of Natural Resources&Guangdong Key Laboratory of Urban InformaticsShenzhen UniversityShenzhen 518060China School of Architecture and Urban Planning Shenzhen UniversityShenzhen 518060China Key Laboratory of Virtual Geographic Environment Ministry of EducationNanjing Normal UniversityNanjing 210023China Jiangsu Center for Collaborative Innovation in Geographical Information Resource Development and Application Nanjing 210023China International Research Center of Big Data for Sustainable Development Goals Beijing 100094China Shenzhen Zhiyuan Space Innovation Technology Co. LtdShenzhen 518060China Guangdong Laboratory of Artificial Intelligence and Digital Economy(SZ) Shenzhen 518107China School of Geography and Ocean Science Nanjing UniversityNanjing 210008China School of Geography Nanjing Normal UniversityNanjing 210023China School of Civil Engineering Chongqing Jiaotong UniversityChongqing 400074China Institute for Advanced Study&Shenzhen University Shenzhen 518060China Tiandu-Shenzhen University Deep Space Joint Laboratory Shenzhen UniversityShenzhen 518060China Faculty of Land Resource Engineering Kunming University of Science and TechnologyKunming 650093China Center for Hydrogeology and Environmental Geology China Geological SurveyBaoding 071051China Department of Landscape Architecture and Urban Planning Texas A&M UniversityTX 77840USA Department of Geography Hong Kong Baptist UniversityHong Kong 999077China College of Civil and Transportation Engineering Shenzhen UniversityShenzhen 518060China College of Big Data and Internet Shenzhen Technology UniversityShenzhen 518118China Faculty of Geosciences and Environmental Engineering Southwest Jiaotong UniversityChengdu 611756China College of Management Shenzhen UniversityShenzhen 518060China WeBank(Shenzhen)Co. LtdShenzhen 518060China Department of Aeronautical and Aviation Engineering The Hong Kong Polytechnic UniversityHong Kong 100872China Esri C

China is experiencing accelerated urbanisation,with a large number of people moving from rural to urban areas[1].It has resulted in large losses in the net primary production(NPP),biodiversity and carbon stocks and an increase in environmental pollution and CO_(2)emissions[2–4].In 2015,196 countries signed the Paris Agreement and committed to setting long-term goals to jointly manage climate change and reduce their individual emissions,aiming to control the increase in global average temperature from the pre-industrial level to below 2℃and to curtail the temperature rise within 1.5℃till the end of the 21st century[5].China is bolstering its efforts to achieve the climate change mitigation goals and has announced a plan for achieving carbon neutrality by 2060[6].The carbon neutrality goal poses a challenge to the current policies promoting rapid urbanisation across China.

关键词： jointly carbon goals

来源：评论

学校读者我要写书评

暂无评论

FedMS: Federated Learning with Mixture of Sparsely Activated Foundations Models

arXiv

引用

arXiv 2023年

作者： Wu, Panlong Li, Kangshuo Wang, Ting Wang, Fangxin The Future Network of Intelligence Institute The School of Science and Engineering The Chinese University of Hong Kong Shenzhen518172 China The School of Data Science The Chinese University of Hong Kong Shenzhen518172 China The School of Science and Engineering The Chinese University of Hong Kong Shenzhen518172 China Guangdong Provincial Key Laboratory of Future Networks of Intelligence China

Foundation models have shown great success in natural language processing, computer vision, and multimodal tasks. FMs have a large number of model parameters, thus requiring a substantial amount of data to help optimize the model during the training. Federated learning has revolutionized machine learning by enabling collaborative learning from decentralized data while still preserving the data privacy of clients. Despite the great benefits foundation models can have empowered by federated learning, they face severe computation, communication, and statistical challenges. In this paper, we propose a novel two-stage federated learning algorithm called FedMS. A global expert is trained in the first stage and a local expert is trained in the second stage to provide better personalization. We construct a Mixture of Foundation Models (MoFM) with these two experts and design a gate neural network with an inserted gate adapter that joins the aggregation every communication round in the second stage. To further adapt to edge computing scenarios with limited computational resources, we design a novel Sparsely Activated LoRA (SAL) algorithm that freezes the pre-trained foundation model parameters inserts low-rank adaptation matrices into transformer blocks and activates them progressively during the training. We employ extensive experiments to verify the effectiveness of FedMS, results show that FedMS outperforms other SOTA baselines by up to 55.25% in default settings. Copyright © 2023, The Authors. All rights reserved.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

cVTS: A Constrained Voronoi Tree Search Method for High Dimensional Analog Circuit Synthesis

cVTS: A Constrained Voronoi Tree Search Method for High Dime...

引用

Design Automation Conference

作者： Aidong Zhao Xianan Wang Zixiao Lin Zhaori Bi Xudong Li Changhao Yan Fan Yang Li Shang Dian Zhou Xuan Zeng Microelectronics Department State Key Laboratory of Integrated Chips and Systems Fudan University Shanghai China Department of Electrical Engineering University of Texas Dallas USA Department of Electrical and Computer Engineering University of California San Diego USA School of Data Science Fudan University Shanghai China School of Computer Science Fudan University Shanghai China

A constrained Voronoi tree-based domain decomposition method for high-dimensional Bayesian optimization is proposed to solve large scale analog circuit synthesis problems, which can be formulated as high-dimensional heterogeneous black-box optimization. Hierarchical Voronoi tree progressively breaks down the design space into partitions with implicit performance boundaries such that promising regions are efficiently explored. Fast exploitation is ensured in Voronoi nest via local Bayesian optimization with a few observations. A slice-enhanced Gibbs sampling method is proposed to sample acquisition function cMES in irregular polyhedrons with design constraints. Compared with state-of-the-art methods, cVTS achieves significant speed up without loss of accuracy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Efficient Asynchronous Uplink Sensing in Perceptive Mobile Networks via Accurate Delay Estimation

引用

IEEE Transactions on Cognitive Communications and Networking 2025年

作者： Li, Hang Teng, Fuxian Guo, Qinghua Zhang, J. Andrew Huang, Xiaojing Cheng, Zhiqun Hangzhou Dianzi University School of Electronics and Information Hangzhou310018 China Academy of Network and Communications of CETC National Key Laboratory of Advanced Communication Networks Hebei Shijiazhuang050081 China University of Wollongong School of Electrical Computer and Telecommunications Engineering WollongongNSW2522 Australia University of Technology Sydney Global Big Data Technologies Centre UltimoNSW2007 Australia

In perceptive mobile networks (PMNs) with integrated sensing and communication (ISAC), sensing ambiguity in ranging and velocity measurements can be caused by timing offsets (TOs) and carrier frequency offsets (CFOs) between asynchronous sensing transmitter and receiver. In this paper, we propose an efficient method for uplink sensing with asynchronous transceivers, via accurately estimating path delays including TOs. Firstly, we develop a sparse signal recovery model to decouple multiple sensing parameters, i.e., delay, angle of arrival (AoA) and Doppler for multipath, facilitating efficient and low-complexity sensing parameter estimation. Then, leveraging unitary approximate message passing (UAMP) and sparse Bayesian learning (SBL), we obtain initial delay and signal estimates, which are then refined through Gauss-Seidel iteration. Finally, we conduct estimation and association of the remaining sensing parameters by coherently processing cross-correlation of received signals across the spatial and temporal domains. This effectively removes the sensing ambiguity incurred by time-varying TOs and CFOs, enabling accurate estimation of range and velocity for multiple targets. Simulation results verify the effectiveness of the proposed method, demonstrating its superior sensing performance, compared to existing methods such as cross-antenna cross correlation (CACC). © 2015 IEEE.

关键词： Frequency allocation

来源：评论

学校读者我要写书评

暂无评论

Principle, Structure, and Applications of Gallium Nitride High Electron Mobility Transistors (HEMTs)

Principle, Structure, and Applications of Gallium Nitride Hi...

引用

International Conference on Fuzzy Systems and knowledge Discovery (FSKD)

作者： Fei Yu Qi-Ming Zeng Rong Song Jian Tang Ya-Ting Wu School of Electronics and Communication Engineering Shenzhen Polytechnic ShenZhen China School of Integrated Circuits Shenzhen Polytechnic ShenZhen China School of Physical and Electronic Engineering Yancheng Teachers University Yancheng China Key Laboratory of Specialty Fiber Optics and Optical Access Networks Shanghai Institute for Advanced Communication and Data Science Shanghai University Shanghai China

With the development of electronic information technology, new technology fields have posed increasingly high requirements for the voltage and current parameters of transistors. This article analyzes in detail the band structure, electron mobility, and voltage resistance characteristics of gallium nitride materials, and provides the principle and density of the two-dimensional electron gas generated by gallium nitride heterojunctions. The influence of different material structures on gallium nitride heterojunctions is compared and the structure and future improvements of gallium nitride HEMT are proposed. The equivalent circuit model of gallium nitride HEMT is analyzed, which points out that the SPICE model of gallium nitride HEMT is a key technology for future gallium nitride HEMT design. Finally, this article analyzes and prospects the application value of gallium nitride HEMT in the field of electronic information new technologies.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Incomplete Multi-View Clustering via Multi-Level Contrastive Learning

引用

IEEE Transactions on knowledge and data engineering 2025年

作者： Yin, Jun Wang, Pei Sun, Shiliang Zheng, Zhonglong Shanghai Maritime University College of Information Engineering Shanghai201306 China Shanghai Jiao Tong University Department of Automation Shanghai200240 China Ministry of Education Key Laboratory of Advanced Theory and Application in Statistics and Data Science Shanghai200062 China Zhejiang Normal University School of Computer Science Zhejiang Jinhua321004 China

Although significant progress has been made in multi-view learning over the past few decades, it remains challenging, especially in the context of incomplete multi-view clustering, where modeling complex correlations among different views and handling missing data are key difficulties. In this paper, we propose a novel incomplete multi-view clustering network to address the aforementioned issue, named Incomplete Multi-view Clustering via Multi-level Contrastive Learning (IMC-MCL). Specifically, the proposed model aims to minimize the conditional entropy between views to recover missing data by dual prediction strategy. Moreover, the approach learns multi-level features, including latent, high-level and semantic features, with the goal of satisfying both reconstruction and consistency objectives in distinct feature spaces. Specifically, latent features are utilized to accomplish the reconstruction objective, while high-level features and semantic labels are employed to achieve the two consistency goals through contrastive learning. This framework enables the exploration of shared semantics within high-level features and achieves clustering assignment using semantic features. Extensive experiments have shown that the proposed approach outperforms other state-of-the-art incomplete multi-view clustering methods on seven challenging datasets. © 1989-2012 IEEE.

关键词： Sorting

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：