检索结果-内蒙古大学图书馆

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Wang, Xiao Liu, Lekai Yang, Bin Ye, Mang Wang, Zheng Xu, Xin School of Computer Science and Technology Wuhan University of Science and Technology China School of Computer Science Wuhan University China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan University of Science and Technology China

ISBN: (纸本)157735897X

Unsupervised visible-infrared person re-identification (US-VI-ReID) seeks to match infrared and visible images of the same individual without the use of annotations. Current methods typically derive cross-modal correspondences through a single global feature matching process for generating pseudo labels and learning modality-invariant features. However, this matching approach is hindered by both intra-modality and inter-modality discrepancies, which result in imprecise measurements. As a consequence, the clustering of individuals with single global feature is often incomplete and unreliable, leading to suboptimal performance in cross-modal clustering tasks. To address these challenges and to extract cross-modality discriminative identity information, we propose a TokenMatcher, which encompasses three key components: Diverse Tokens Matching (DTM), Diverse Tokens Neighbor Learning (DTNL), and the Homogeneous Fusion (HF) Module. DTM utilizes multiple class tokens within the visual transformer framework to capture diverse embedding representations, thereby facilitating the integration of fine-grained information essential for reliable cross-modality correspondences. DTNL enhances the intra-modality and inter-modality consistency among diverse tokens by refining neighborhood sets with insights from neighboring tokens and camera information, promoting robust neighborhood learning and fostering discriminative identity information. Additionally, the HF module consolidates clusters of the same identity while effectively separating those of different identities. Extensive experiments conducted on the publicly available SYSU-MM01 and RegDB datasets demonstrate the efficacy of the proposed method. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

On the Probability of Generating a Primitive Matrix

引用

Journal of systems science & Complexity 2024年第4期37卷 1755-1771页

作者： CHEN Jingwei FENG Yong LIU Yang WU Wenyuan Chongqing Key Laboratory of Automated Reasoning and Cognition Chongqing Institute of Green and Intelligent TechnologyChinese Academy of SciencesChongqing 400714China Chongqing College University of Chinese Academy of SciencesChongqing 400714China Key Laboratory of Advanced Manufacturing Technology of Ministry of Education Guizhou UniversityyGuiyang 550025China Information Science and Engineering Chongqing Jiaotong UniversityChongqing 400074China

Given a k×n integer primitive matrix A(i.e.,a matrix can be extended to an n×n unimodular matrix over the integers)with the maximal absolute value of entries‖A‖bounded by an integer λ from above,the authors study the probability that the m×n matrix extended from A by appending other m-k row vectors of dimension n with entries chosen randomly and independently from the uniform distribution over{0,1,…,λ-1}is still *** authors present a complete and rigorous proof of a lower bound on the probability,which is at least a constant for fixed m in the range[k+1,n-4].As an application,the authors prove that there exists a fast Las Vegas algorithm that completes a k×n primitive matrix A to an n×n unimodular matrix within expected O(n^(ω)log‖A‖)bit operations,where O is big-O but without log factors,ω is the exponent on the arithmetic operations of matrix multiplication.

关键词： Integer matrix matrix completion probabilistic algorithm unimodular matrix

来源：评论

学校读者我要写书评

暂无评论

Scavenger: Better Space-Time Trade-Offs for key-Value Separated LSM-trees 40

Scavenger: Better Space-Time Trade-Offs for Key-Value Separa...

引用

40th IEEE International Conference on Data engineering, ICDE 2024

作者： Zhang, Jianshun Wang, Fang Qiu, Sheng Wang, Yi Ou, Jiaxin Huang, Junxun Li, Baoquan Fang, Peng Feng, Dan School of Computer Science and Technology Huazhong University of Science and Technology Wuhan National Laboratory for Optoelectronics Key Laboratory of Information Storage System Engineering Research Center of Data Storage Systems and Technology Ministry of Education of China China Shenzhen Huazhong University of Science and Technology Research Institute China Bytefrance Inc.

ISBN: (纸本)9798350317152

key-Value Stores (KVS) implemented with log-structured merge-tree (LSM-tree) have gained widespread ac-ceptance in storage systems. Nonetheless, a significant challenge arises in the form of high write amplification due to the compaction process. While KV-separated LSM-trees successfully tackle this issue, they also bring about substantial space am-plification problems, a concern that cannot be overlooked in cost-sensitive scenarios. Garbage collection (GC) holds significant promise for space amplification reduction, yet existing GC strategies often fall short in optimization performance, lacking thorough consideration of workload characteristics. Additionally, current KV-separated LSM-trees also ignore the adverse effect of the space amplification in the index LSM-tree. In this paper, we systematically analyze the sources of space amplification of KV-separated LSM-trees and introduce Scavenger, which achieves a better trade-off between performance and space amplification. Scavenger initially proposes an I/O-efficient garbage collection scheme to reduce I/O overhead and incorporates a space-aware compaction strategy based on compensated size to minimize the space amplification of index LSM-trees. Extensive experiments show that Scavenger significantly improves write performance and achieves lower space amplification than other KV-separated LSM-trees (including BlobDB, Titan, and TerarkDB). © 2024 IEEE.

关键词： Economic and social effects

来源：评论

学校读者我要写书评

暂无评论

Leveraging Structured information from a Passage to Generate Questions

引用

Tsinghua science and technology 2023年第3期28卷 464-474页

作者： Jian Xu Yu Sun Jianhou Gan Mingtao Zhou Di Wu Key Laboratory of Educational Informatization for Nationalities Yunnan Normal UniversityKunming 650500China School of Information Science and Technology Yunnan Normal UniversityKunming 650500China Yunnan Key Laboratory of Smart Education Yunnan Normal UniversityKunming 650500China School of Information Engineering Qujing Normal UniversityQujing 655011China

Question Generation(QG)is the task of utilizing Artificial Intelligence(AI)technology to generate questions that can be answered by a span of text within a given *** research on QG in the educational field struggles with two challenges:the mainstream QG models based on seq-to-seq fail to utilize the structured information from the passage;the other is the lack of specialized educational QG *** address the challenges,a specialized QG dataset,reading comprehension dataset from examinations for QG(named RACE4QG),is reconstructed by applying a new answer tagging approach and a data-filtering strategy to the RACE ***,an end-to-end QG model,which can exploit the intra-and inter-sentence information to generate better questions,is *** our model,the encoder utilizes a Gated Recurrent Units(GRU)network,which takes the concatenation of word embedding,answer tagging,and Graph Attention neTworks(GAT)embedding as *** hidden states of the GRU are operated with a gated self-attention to obtain the final passage-answer representation,which will be fed to the *** show that our model outperforms baselines on automatic metrics and human ***,the model improves the baseline by 0.44,1.32,and 1.34 on BLEU-4,ROUGE-L,and METEOR metrics,respectively,indicating the effectivity and reliability of our *** gap with human expectations also reflects the research potential.

关键词： automatic Question Generation(QG) RACE4QG dataset Answer-Oriented GAT(AO-GAT) attention mechanism structured information

来源：评论

学校读者我要写书评

暂无评论

Effects of Ocean Acidification on Nitrogen Metabolism of Skeletonema costatum

引用

Journal of Ocean University of China 2024年第5期23卷 1359-1370页

作者： WANG Shuxing MI Tiezhu ZHEN Yu ZHU Jianbin Key Laboratory of Marine Environment and Ecology Ministry of EducationCollege of Environmental Science and EngineeringOcean University of ChinaQingdao 266100China Laboratory for Marine Ecology and Environmental Science Qingdao Marine Science and Technology CenterQingdao 266237China Frontiers Science Center for Deep Ocean Multispheres and Earth System Ocean University of ChinaQingdao 266100China

Ocean acidification(OA),caused by the rising concentration of atmospheric CO_(2),leads to changes in the marine carbonate ***,in turn,affects the physiological processes of *** response to increased pCO_(2) levels,marine microalgae modulate their physiological responses to meet their energy and metabolic *** metabolism is a critical metabolic pathway,directly affecting the growth and reproductive capacity of marine *** the molecular mechanisms that regulate nitrogen metabolism in microalgae under OA conditions is therefore *** study aimed to investi-gate how OA affects the expression profiles of key genes in the nitrogen metabolic pathway of the marine diatom Skeletonema *** findings indicate that OA upregulates key genes involved in the nitrogen metabolic pathway,specifically those related to nitrate assimilation and glutamate ***,pCO_(2) has been identified as the predominant factor affecting the expression of these genes,with a more significant impact than pH variations in *** research not only advances our understanding of the adaptive mechanisms of *** in response to OA but also provides essential data for predicting the ecological consequences of OA on marine diatoms.

关键词： Skeletonema costatum ocean acidification nitrogen metabolism gene expression transcriptome

来源：评论

学校读者我要写书评

暂无评论

Large Language Model for Medical Images:A Survey of Taxonomy,systematic Review,and Future Trends

引用

Big Data Mining and Analytics 2025年第2期8卷 496-517页

作者： Peng Wang Wenpeng Lu Chunlin Lu Ruoxi Zhou Min Li Libo Qin School of Computer Science and Engineering Central South UniversityChangsha 410083China Key Laboratory of Computing Power Network and Information Security Affiliated with Ministry of Education Qilu University of Technology(Shandong Academy of Sciences)Jinan 250353China

The advent of Large Language Models(LLMs)has sparked considerable interest in the medical image domain,as they can generalize to multiple tasks and offer outstanding *** LLMs achieve promising results,there is currently a lack of a comprehensive summary of medical images,making it challenging for researchers to understand the progress within this *** fill this gap,we make the first attempt to present a comprehensive survey for LLM on medical *** addition,to better summarize the current progress comprehensively,we further introduce a novel x-stage tuning paradigm for summarization,including zero-stage tuning,one-stage tuning,and multi-stage tuning,offering a unified perspective on LLMs for medical ***,we discuss challenges and future directions in this domain,aiming to spur more breakthroughs in the *** hope this work can pave the way for the broad application of LLMs in medical images and provide a valuable resource for this domain.

关键词： Large Language Model(LLM) x-stage tuning medical images

来源：评论

学校读者我要写书评

暂无评论

BAV-DSS: Blockchain Assisted Verifiable Data Sharing Scheme with Fast Encryption and Outsourced Decryption for IoT 24th

BAV-DSS: Blockchain Assisted Verifiable Data Sharing Scheme ...

引用

24th International Conference on Algorithms and Architectures for Parallel Processing, ICA3PP 2024

作者： Huang, Yao Yu, Zhongyuan Wang, Guijuan Chai, Baobao Zhang, Hongliang Jinan250353 China Shandong Provincial Key Laboratory of Industrial Network and Information System Security Shandong Fundamental Research Center for Computer Science Jinan250353 China School of Information Science and Engineering Lanzhou University Lanzhou730000 China School of Computer Science and Engineering Shandong University of Science and Technology Qingdao266590 China

ISBN: (纸本)9789819615414

Many sophisticated cloud platforms are available to provide services such as storage and computation for Internet of Things (IoT) applications. However, with the concerns about the semi-trusted nature of cloud platforms, data security and privacy have been gaining broad attention. In this paper, we propose a blockchain-assisted verifiable data sharing scheme (BAV-DSS) for IoT. The BAV-DSS features fine-grained access control, fast encryption, and outsourced decryption with verifiability. Specifically, with the application of ciphertext-policy attribute-based encryption (CP-ABE), flexible access control is enabled. Blockchain is employed to store public keys, generate account addresses, and perform data verification. Furthermore, the selective replayable chosen ciphertext attacks (sRCCA) security of BAV-DSS is proved, and the simulation results indicate that BAV-DSS obtains high efficiency and practicality compared to other schemes. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Cloud platforms

来源：评论

学校读者我要写书评

暂无评论

Hardware Software Co-design Approch for ECG Signal Analysis 1

引用

1st international conference on Machine Intelligence and Computer science Applications, ICMICSA 2022

作者： Bendahane, Bouchra Jenkal, Wissam Laaboubi, Mostafa Latif, Rachid Ibn Zohr University National School of Applied Science System Engineering and Information Technology Laboratory Agadir Morocco

ISBN: (数字)9783031293139

ISBN: (纸本)9783031288456

An essential tool for diagnosing heart diseases is the electrocardiogram (ECG) signal. The accuracy of the diagnosis is impacted by the noise that occurs while this signal is being acquired. Denoising turns into a foundational step in this context. DWT-ADTF is an effective ECG signal-denoising method. This work tries to provide an HW/SW co-design solution to this method. The signal is well denoised, according to the simulation results of the developed designs. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Field programmable gate arrays (FPGA)

来源：评论

学校读者我要写书评

暂无评论

From laboratory to Field:Unsupervised Domain Adaptation for Plant Disease Recognition in the Wild

引用

Plant Phenomics 2023年第2期5卷 195-208页

作者： Xinlu Wu Xijian Fan Peng Luo Sruti Das Choudhury Tardi Tjahjadi Chunhua Hu College of Information Science and Technology Nanjing Forestry UniversityNanjing 210037China Institute of Forest Resource Information Techniques Chinese Academy of ForestryBeijing 100091China Key Laboratory of Forestry Remote Sensing and Information System National Forestry and Grassland AdministrationBeijing 100091China Department of Computer Science and Engineering University of Nebraska-LincolnLincolnNE 68588USA School of Engineering University of WarwickCoventry CV47ALUK

Plant disease recognition is of vital importance to monitor plant development and predicting crop ***,due to data degradation caused by different conditions of image acquisition,e.g.,laboratory *** environment,machine learning-based recognition models generated within a specific dataset(source domain)tend to lose their validity when generalized to a novel dataset(target domain).To this end,domain adaptation methods can be leveraged for the recognition by learning invariant representations across *** this paper,we aim at addressing the issues of domain shift existing in plant disease recognition and propose a novel unsupervised domain adaptation method via uncertainty regularization,namely,Multi-Representation Subdomain Adaptation Network with Uncertainty Regularization for Cross-Species Plant Disease Classification(MSUN).Our simple but effective MSUN makes a breakthrough in plant disease recognition in the wild by using a large amount of unlabeled data and via nonadversarial ***,MSUN comprises multirepresentation,subdomain adaptation modules and auxiliary uncertainty *** multirepresentation module enables MSUN to learn the overall structure of features and also focus on capturing more details by using the multiple representations of the source *** effectively alleviates the problem of large interdomain *** adaptation is used to capture discriminative properties by addressing the issue of higher interclass similarity and lower intraclass ***,the auxiliary uncertainty regularization effectively suppresses the uncertainty problem due to domain *** was experimentally validated to achieve optimal results on the PlantDoc,Plant-Pathology,Corn-Leaf-Diseases,and Tomato-Leaf-Diseases datasets,with accuracies of 56.06%,72.31%,96.78%,and 50.58%,respectively,surpassing other state-of-the-art domain adaptation techniques considerably.

关键词： Plant breakthrough details

来源：评论

学校读者我要写书评

暂无评论

Anisotropic phonon dynamics in Dirac semimetal PtTe2 thin films enabled by helicity-dependent ultrafast light excitation

引用

Light(science & Applications) 2024年第9期13卷 1888-1897页

作者： Ziyang Li Yequan Chen Anke Song Jinzhong Zhang Rong Zhang Zongzhi Zhang Xuefeng Wang Key Laboratory of Micro and Nano Photonic Structures(MOE) School of Information Science and TechnologyFudan UniversityShanghaiChina Jiangsu Provincial Key Laboratory of Advanced Photonic and Electronic Materials State Key Laboratory of Spintronics Devices and TechnologiesSchool of Electronic Science and EngineeringCollaborative Innovation Center of Advanced MicrostructuresNanjing UniversityNanjingChina Department of Physics School of Physics and Electronic ScienceEast China Normal UniversityShanghaiChina Department of Physics Xiamen UniversityXiamenChina

Coherent phonons have aroused considerable attention in condensed matter physics owing to their extraordinary capacity of reflecting and controlling the physical properties of ***,the investigation on the interaction between coherent phonons and other microscopic particles on the ultrafast timescale within topological systems continues to be an active and unresolved ***,we show the energy transfer of coherent optical phonons(COP)in Dirac semimetal PtTe2 thin films using ultrafast optical pump-probe ***,the helicitydependent light-driven anisotropic COP signals disclose their direct connection with the light-excited anisotropic spinpolarized electrons via an angular momentum ***,we observe the notable decreases in the COP oscillation frequency and the decay rate with increasing temperatures due to the anharmonic phonon-phonon scattering and electron-phonon scattering in the COP dissipation process,*** work paves the way for uncovering the coherent phonons in Dirac semimetals for the potential applications in optoelectronics and optospintronics.

关键词： spectroscopy phonon Dirac

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：