检索结果-内蒙古大学图书馆

IEEE International Conference on Robotics and Automation (ICRA)

作者： Yu Han Ziwei Long Yanting Zhang Jin Wu Zhijun Fang Rui Fan School of Computer Science and Technology Donghua University Shanghai P. R. China Shanghai Research Institute for Intelligent Autonomous Systems the State Key Laboratory of Intelligent Autonomous Systems and Frontiers Science Center for Intelligent Autonomous Systems Machine Intelligence & Autonomous Systems (MIAS) Group the College of Electronics & Information Engineering Tongji University Shanghai P. R. China Department of Electronics and Computer Engineering The Hong Kong University of Science and Technology P. R. China

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

Correspondence matching plays a crucial role in numerous robotics applications. In comparison to conventional hand-crafted methods and recent data-driven approaches, there is significant interest in plug-and-play algorithms that make full use of pre-trained backbone networks for multi-scale feature extraction and leverage hierarchical refinement strategies to generate matched correspondences. The primary focus of this paper is to address the limitations of deep feature matching (DFM), a state-of-the-art (SoTA) plug-and-play correspondence matching approach. First, we eliminate the pre-defined threshold employed in the hierarchical refinement process of DFM by leveraging a more flexible nearest neighbor search strategy, thereby preventing the exclusion of repetitive yet valid matches during the early stages. Our second technical contribution is the integration of a patch descriptor, which extends the applicability of DFM to accommodate a wide range of backbone networks pre-trained across diverse computer vision tasks, including image classification, semantic segmentation, and stereo matching. Taking into account the practical applicability of our method in real-world robotics applications, we also propose a novel patch descriptor distillation strategy to further reduce the computational complexity of correspondence matching. Extensive experiments conducted on three public datasets demonstrate the superior performance of our proposed method. Specifically, it achieves an overall performance in terms of mean matching accuracy of 0.68, 0.92, and 0.95 with respect to the tolerances of 1, 3, and 5 pixels, respectively, on the HPatches dataset, outperforming all other SoTA algorithms. Our source code, demo video, and supplement are publicly available at ***/GCM.

关键词： Performance evaluation Accuracy Semantic segmentation Source coding Image matching Supervised learning Pose estimation

来源：评论

学校读者我要写书评

暂无评论

Classification Models and Variable Selection for SME Credit Risk Assessment in Balance the Data Set 10

Classification Models and Variable Selection for SME Credit ...

引用

10th International Conference on Digital Arts, Media and technology and 8th ECTI Northern Section Conference on Electrical, Electronics, computer and Telecommunications engineering, ECTI DAMT and NCON 2025

作者： Intharasompong, Sornthun Jitpattanakul, Anuchit Mekruksavanich, Sakorn Wongwiwat, Piyada Phaphan, Wikanda King Mongkut's University of Technology North Bangkok Faculty of Applied Science Department of Applied Statistics Bangkok10800 Thailand King Mongkut's University of Technology North Bangkok Faculty of Applied Science Department of Mathematics Bangkok10800 Thailand Intelligent and Nonlinear Dynamic Innovations Research Center Thailand University of Phayao School of Information and Communication Department of Computer Engineering 56000 Thailand Suansunandha Rajabhat University Faculty of Science and Technology Bangkok10800 Thailand Research Group in Statistical Learning and Inference Thailand

ISBN: (纸本)9798331543273

Small and medium-sized enterprises (SMEs) are frequently considered high credit risk, making it difficult to obtain loans from banks. A viable substitute for assessing borrower creditworthiness more impartially is using machine learning-based credit risk assessment (CRA) algorithms. This study evaluated the performance of five machine learning techniques: decision tree, support vector machine, gradient boosting, K-nearest neighbor, and Naïve Bayes. We evaluated each model with K-fold cross-validation and utilized the Stepwise selection method for the variable selection. To address the underlying data imbalance, we balanced the dataset with the SMOTE technique, which showed that normal loans were more widespread than Non-Performing Loans (NPLs). After balancing the data, the Gradient Boosting model displayed the best accuracy, F-measure, and robustness without variable selection, making it the most effective model for predicting SME loans. © 2025 IEEE.

关键词： Risk assessment

来源：评论

学校读者我要写书评

暂无评论

Xiezhi: An Ever-Updating Benchmark for Holistic Domain Knowledge Evaluation

arXiv

引用

arXiv 2023年

作者： Gu, Zhouhong Zhu, Xiaoxuan Ye, Haoning Zhang, Lin Wang, Jianchen Zhu, Yixin Jiang, Sihang Xiong, Zhuozhi Li, Zihan Wu, Weijie He, Qianyu Xu, Rui Huang, Wenhao Liu, Jingping Wang, Zili Wang, Shusen Zheng, Weiguo Feng, Hongwei Xiao, Yanghua Shanghai Key Laboratory of Data Science School of Computer Science Fudan University China School of Information Science and Engineering East China University of Science and Technology China School of Data Science Fudan University China Fudan-Aishu Cognitive Intelligence Joint Research Center China Research Group of Computational and AI Communication Institute for Global Communications and Integrated Media Fudan University China

New Natural Langauge Process (NLP) benchmarks are urgently needed to align with the rapid development of large language models (LLMs). We present Xiezhi, the most comprehensive evaluation suite designed to assess holistic domain knowledge. Xiezhi comprises multiple-choice questions across 516 diverse disciplines ranging from 13 different subjects with 249,587 questions and accompanied by Xiezhi-Specialty with 14,041 questions and Xiezhi-Interdiscipline with 10,746 questions. We conduct evaluation of the 47 cutting-edge LLMs on Xiezhi. Results indicate that LLMs exceed average performance of humans in science, engineering, agronomy, medicine, and art, but fall short in economics, jurisprudence, pedagogy, literature, history, and management. © 2023, CC BY.

关键词： Domain Knowledge

来源：评论

学校读者我要写书评

暂无评论

Correction to: Multi-agent-based approach for generation expansion planning in isolated micro-grid with renewable energy sources and battery storage

引用

The Journal of Supercomputing 2022年第1期79卷 1156-1157页

作者： Paliwal, Priyanka Webber, Julian L. Mehbodniya, Abolfazl Haq, Mohd Anul Kumar, Anil Chaurasiya, Prem Kumar Department of Electrical Engineering MANIT Bhopal India Department of Electronics and Communication Engineering Kuwait College of Science and Technology (KCST) Doha Area Kuwait Department of Computer Science College of Computer and Information Sciences Majmaah University AlMajmaah Saudi Arabia Data Science Research Group School of Computing DIT University Dehradun India Department of Mechanical Engineering Bansal Institute of Science and Technology Bhopal India

In this article the affiliation details for Julian L. Webber were incorrectly assigned.

关键词：

来源：评论

学校读者我要写书评

暂无评论

10 GHz Robust polarization modulation towards high-speed satellite-based quantum communication

arXiv

引用

arXiv 2024年

作者： Wang, Zexu Xu, Huaxing Li, Ju Huang, Jinquan Han, Hui Wang, Changlei Zhang, Ping Yin, Feifei Xu, Kun Liu, Bo Dai, Yitang State Key Laboratory of Information Photonics and Optical Communications Beijing University of Posts and Telecommunications Beijing100876 China National Engineering Research Center for Public Safety Risk Perception and Control by Big Data China Academy of Electronics and Information Technology Beijing100041 China CETC Academy of Electronics and Information Technology Group Co. Ltd. Beijing100041 China College of Advanced Interdisciplinary Studies National University of Defense Technology Changsha410073 China School of Electronics and Communication Engineering Sun Yat-sen University Guangdong Shenzhen518107 China College of Computer National University of Defense Technology Changsha4100730 China

In practical satellite-based quantum key distribution (QKD) systems, the preparation and transmission of polarization-encoding photons suffer from complex environmental effects and high channel-loss. Consequently, the hinge to enhancing the secure key rate (SKR) lies in achieving robust, low-error and high-speed polarization modulation. Although the schemes that realize self-compensation exhibit remarkable robustness. Their modulation speed is constrained to approximately 2 GHz to avoid the interaction between the electrical signal and the reverse optical pulses. Here we utilize the non-reciprocity of the lithium niobate modulators and eliminate the modulation on the reverse optical pulses. As this characteristic is widely available in the radio-frequency band, the modulation speed is no longer limited by the self-compensating optics and can be further increased. The measured average intrinsic QBER of the different polarization states at 10 GHz system repetition frequency is as low as 0.53% over 10 min without any compensation. And the experiment simulation shows that the proposed scheme extends the transmission distance to more than 350 km. Our work can be be efficient performed to the high-speed and high-loss satellite-based quantum communication scenario. © 2024, CC BY.

关键词： Quantum communication

来源：评论

学校读者我要写书评

暂无评论

Towards Faster Fully Homomorphic Encryption Implementation with Integer and Floating-point Computing Power of GPUs

Towards Faster Fully Homomorphic Encryption Implementation w...

引用

International Symposium on Parallel and Distributed Processing (IPDPS)

作者： Guang Fan Fangyu Zheng Lipeng Wan Lili Gao Yuan Zhao Jiankuo Dong Yixuan Song Yuewu Wang Jingqiang Lin State Key Laboratory of Information Security Institute of Information Engineering Chinese Academy of Sciences Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Data Assurance and Communication Security Research Center Chinese Academy of Sciences Beijing China School of Cryptography University of Chinese Academy of Sciences Beijing China Department of Computer and Software Nanjing University of Information Science and Technology Nanjing China Ant Group Hangzhou China School of Computer Science Nanjing University of Posts and Telecommunications Nanjing China School of Cyber Security University of Science and Technology of China Hefei China

Fully Homomorphic Encryption (FHE) allows computations on encrypted data without knowledge of the plaintext message and currently has been the focus of both academia and industry. However, the performance issue hinders its large-scale application, highlighting the urgent requirements of high-performance FHE *** noticing the tremendous potential of GPUs in the field of cryptographic acceleration, this paper comprehensively investigates how to convert the available computing resources residing in GPUs into FHE workhorses, and implement a full set of low-level and middle-level FHE primitives based on two arithmetic units (i.e., INT32 and FP64 units) with three types of data precision (i.e., INT32, INT64 and FP64). This paper gives a comprehensive evaluation and comparison based on each road-map. Our implementations of fundamental functions outperform the implementations on the same platform by 1.7× to 16.7×. Taking CKKS FHE schemes as a case study, our implementation of homomorphic multiplication achieves 3.2× speedup over the state-of-the-art GPU-based implementation, even considering the difference of platforms. The detailed evaluation and comparison of this paper would offer a vital reference for the follow-up work to choose appropriate underlying arithmetic units and important primitive optimizations in GPU-based FHE implementations.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing Local Feature Learning Using Diffusion for 3D Point Cloud Understanding

arXiv

引用

arXiv 2022年

作者： Xiu, Haoyi Liu, Xin Wang, Weimin Kim, Kyoung-Sook Shinohara, Takayuki Chang, Qiong Matsuoka, Masashi Department of Architecture and Building Engineering Tokyo Institute of Technology Tokyo Japan Artificial Intelligence Research Center AIST Tokyo Japan DUT-RU International School of Information Science and Engineering Dalian University of Technology Dalian China Innovation Technology Office Research Center PASCO Corporation Tokyo Japan Department of Computer Science Tokyo Institute of Technology Tokyo Japan

Learning point clouds is challenging due to the lack of connectivity information, i.e., edges. Although existing edge-aware methods can improve the performance by modeling edges, how edges contribute to the improvement is unclear. In this study, we propose a method that automatically learns to enhance/suppress edges while keeping the its working mechanism clear. First, we theoretically figure out how edge enhancement/suppression works. Second, we experimentally verify the edge enhancement/suppression behavior. Third, we empirically show that this behavior improves the performance. In general, we observe that the proposed method achieves competitive performance in point cloud classification and segmentation tasks. Copyright © 2022, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Enhancing Local Geometry Learning for 3D Point Cloud via Decoupling Convolution

arXiv

引用

arXiv 2022年

作者： Xiu, Haoyi Liu, Xin Wang, Weimin Kim, Kyoung-Sook Shinohara, Takayuki Chang, Qiong Matsuoka, Masashi Department of Architecture and Building Engineering Tokyo Institute of Technology Tokyo Japan Artificial Intelligence Research Center AIST Tokyo Japan DUT-RU International School of Information Science and Engineering Dalian University of Technology Dalian China Department of Computer Science Tokyo Institute of Technology Tokyo Japan Innovation Technology Office Research Center PASCO Corporation Tokyo Japan

Modeling the local surface geometry is challenging in 3D point cloud understanding due to the lack of connectivity information. Most prior works model local geometry using various convolution operations. We observe that the convolution can be equivalently decomposed as a weighted combination of a local and a global component. With this observation, we explicitly decouple these two components so that the local one can be enhanced and facilitate the learning of local surface geometry. Specifically, we propose Laplacian Unit (LU), a simple yet effective architectural unit that can enhance the learning of local geometry. Extensive experiments demonstrate that networks equipped with LUs achieve competitive or superior performance on typical point cloud understanding tasks. Moreover, through establishing connections between the mean curvature flow, a further investigation of LU based on curvatures is made to interpret the adaptive smoothing and sharpening effect of LU. The code will be available. Copyright © 2022, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Genetic Algorithms for Swarm UAV-Assisted Edge Content Delivery Optimisation Problem

Genetic Algorithms for Swarm UAV-Assisted Edge Content Deliv...

引用

IEEE International Conference on research, Innovation and Vision for the Future

作者： Thuong C. Lam Nguyen-Son Vo Minh-Phung Bui De-Thu Huynh Thanh-Dung Tran Ha Duy Hung HUTECH Institute of Engineering HUTECH University Ho Chi Minh City Vietnam Institute of Fundamental and Applied Sciences Duy Tan University Ho Chi Minh City Vietnam Faculty of Information Technology School of Technology Van Lang University Ho Chi Minh City Vietnam School of Computer Science & Engineering The Saigon International University Ho Chi Minh City Vietnam Wireless Communications Research Group Faculty of Electrical and Electronics Engineering Ton Duc Thang University Ho Chi Minh City Vietnam

ISBN: (数字)9798331505073

ISBN: (纸本)9798331505080

Swarm unmanned aerial vehicles (UAV) have been increasingly studied for delivering the contents in 6G networks. In this paper, we propose an energy-aware capacity and trajectory (ECT) optimisation solution for swarm UAV-assisted edge content delivery networks (eCDN). The ECT optimisation solution enables a swarm UAV system to cooperatively fly 1) to the optimal set of stops and serve the user equipments in different clusters at maximum content delivery capacity and 2) in the optimal trajectory planning at minimum distance, under the constraint of energy resource. However, the ECT optimisation problem is challenging due to multiple objectives with respect to different optimisation variable types and complicated constraints. Genetic algorithms (GA) are therefore modified to address the challenge of solving the so-called multi-objective optimisation problem feasibly. Simulation results are shown to demonstrate the feasibility of GA and the benefits of ECT method for swarm UAV-assisted eCDN.

关键词： 6G mobile communication Trajectory planning Energy resources Content distribution networks Simulation Autonomous aerial vehicles Trajectory Time complexity Optimization Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Handcrafted local feature descriptor-based point cloud registration and its applications: A review

引用

IEEE Transactions on Visualization and computer Graphics 2025年

作者： Tao, Wuyong Wang, Ruisheng Hua, Xianghong Liu, Jingbin Chen, Xijiang Zang, Yufu Chen, Dong Xu, Dong Zhao, Bufan Nanchang University School of Mathematics and Computer Sciences Nanchang330031 China Shenzhen University School of Architecture & Urban Planning Shenzhen518060 China University of Calgary Department of Geomatics Engineering CalgaryT2N 1N4 Canada Wuhan University School of Geodesy and Geomatics Wuhan430079 China Wuhan University State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing Wuhan430079 China Finnish Geospatial Research Institute Department of Remote Sensing and Photogrammetry Masala02430 Finland Wuhan University of Technology School of Safety Science and Emergency Management Wuhan430079 China Nanjing University of Information Science & Technology School of Remote Sensing & Geomatics Engineering Nanjing210000 China Nanjing Forestry University College of Civil Engineering Nanjing210037 China Guangzhou Urban Planning & Design Survey Research Institute Guangzhou51100 China

Point cloud registration serves as a fundamental problem across multiple fields including computer vision, computer graphics, and remote sensing. While local feature descriptors (LFDs) have long been established as a cornerstone for point cloud registration and the LFD-based approach has been extensively studied, the field has witnessed significant advancements in recent years. Despite these developments, the research community lacks a systematic review to consolidate these contributions, leaving many researchers unaware of recent progress in LFD-based registration. To address this gap, we present a comprehensive review that critically examines both state-of-the-art and widely referenced methods across all subtasks of LFD-based registration. Our work provides: (1) an extensive survey of existing methodologies, (2) in-depth analysis of their respective strengths and limitations, (3) insightful observations and practical recommendations, and (4) a thorough summary of relevant applications and publicly available datasets. This systematic overview offers valuable guidance for researchers pursuing future investigations in this domain. © 1995-2012 IEEE.

关键词： Three dimensional computer graphics

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：