检索结果-内蒙古大学图书馆

32nd ACM International Conference on Multimedia, MM 2024

作者： Zhu, Hongze Xie, Guoyang Hou, Chengbin Dai, Tao Gao, Can Wang, Jinbao Shen, Linlin National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China Department of Computer Science City University of Hong Kong Hong Kong Hong Kong Department of Intelligent Manufacturing CATL Ningde China Fuzhou Fuyao Institute for Advanced Study Fuyao University of Science and Technology Fuzhou China College of Computer Science and Software Engineering Shenzhen University Shenzhen China Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen China Shenzhen University Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China

ISBN: (纸本)9798400706868

High-resolution point clouds (HRPCD) anomaly detection (AD) plays a critical role in precision machining and high-end equipment manufacturing. Despite considerable 3D-AD methods that have been proposed recently, they still cannot meet the requirements of the HRPCD-AD task. There are several challenges: i) It is difficult to directly capture HRPCD information due to large amounts of points at the sample level;ii) The advanced transformer-based methods usually obtain anisotropic features, leading to degradation of the representation;iii) The proportion of abnormal areas is very small, which makes it difficult to characterize. To address these challenges, we propose a novel group-level feature-based network, called Group3AD, which has a significantly efficient representation ability. First, we design an Intercluster Uniformity Network (IUN) to present the mapping of different groups in the feature space as several clusters, and obtain a more uniform distribution between clusters representing different parts of the point clouds in the feature space. Then, an Intracluster Alignment Network (IAN) is designed to encourage groups within the cluster to be distributed tightly in the feature space. In addition, we propose an Adaptive Group-Center Selection (AGCS) based on geometric information to improve the pixel density of potential anomalous regions during inference. The experimental results verify the effectiveness of our proposed Group3AD, which surpasses Reg3D-AD by the margin of 5% in terms of object-level AUROC on Real3D-AD. We provide the code and supplementary information on our website: https://***/M-3LAB/Group3AD. © 2024 ACM.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Enhanced Second-Harmonic Generation Driven by Dual-Quasi Bound States in the Continuum

Enhanced Second-Harmonic Generation Driven by Dual-Quasi Bou...

引用

2023 International Applied Computational Electromagnetics Society Symposium, ACES-China 2023

作者： Liu, Yuhang Ren, Xingang Niu, Kaikun Huang, Zhixiang School of Electronic and Information Engineer Anhui University Hefei230601 China Engineering Technology Research Center of Specific Power Devices with Novel Semiconductor Materials Anhui Province Chizhou247100 China Anhui University Key Laboratory of Intelligent Computing & Signal Processing Ministry of Education Hefei230601 China

ISBN: (纸本)9781733509657

Bound state in the continuum (BIC) is a dark mode with infinitely high quality factors(Q-factors), it has recently attracted considerable research attention in photonics. Here, we present a metasurface that can support two BICs, which consists of AlGaAs. By breaking the structural symmetry, the two BICs are transformed into quasi-bic modes because they are not protected by the symmetry. Furthermore, it is found that the two quasi-BICs resonate near the fundamental and the second harmonic respectively, which can be used to enhance efficiency of second harmonic generation. By exploiting the high Q characteristics of this structure at both frequencies, we can obtain a second harmonic generation efficiency of nearly 10-3 with 1GW/cm2of pump intensity. Our proposed metasurface will offer good prospects for nonlinear operation. © 2023 Applied Computational Electromagnetics Society (ACES).

关键词： Harmonic generation

来源：评论

学校读者我要写书评

暂无评论

Optimized Service Function Deployment in Edge computing Networks Using Deep Reinforcement Learning

Optimized Service Function Deployment in Edge Computing Netw...

引用

Algorithms, computing and Artificial Intelligence (ACAI), International Conference on

作者： Liuwei Huo Bowen Zhu Dongcheng Zhao Institute of intelligent computing University of Electronic Science and Technology of China Chengdu China School of Communication and Information Engineering University of Electronic Science and Technology of China Chengdu China Tianfu Jiangxi Laboratory Chengdu China

ISBN: (数字)9798331529314

ISBN: (纸本)9798331529321

The deployment of service function chains (SFCs) in integrated edge computing networks presents significant challenges, including optimizing resource utilization, minimizing latency, and reducing energy consumption. These challenges arise from the dynamic nature of workloads, varying network conditions, and complex service function dependencies. Conventional optimization approaches often struggle to handle these complexities, as they depend on static models and assumptions that may not apply in practical situations. This paper introduces an innovative solution using deep reinforcement learning (DRL) to overcome these limitations. By modeling the deployment problem as a Markov decision process, we utilize the DRL's capability to learn optimal policies through iterative trial and error interactions with the environment. Our method adaptively adjusts service function placement in real time, accounting for workload variability, service dependencies, and network conditions. Comprehensive simulations demonstrate that our proposed approach achieves significant improvements in terms of latency reduction, resource utilization, and energy consumption compared to conventional methods, and can provide a new solution for SFC deployment.

关键词： Energy consumption Adaptation models Service function chaining Computational modeling Markov decision processes Deep reinforcement learning Real-time systems Resource management Edge computing Testing

来源：评论

学校读者我要写书评

暂无评论

ExpTopo: Explicit Topological Modeling for Bronchus Segmentation

ExpTopo: Explicit Topological Modeling for Bronchus Segmenta...

引用

IEEE International Symposium on Biomedical Imaging

作者： Mingyue Zhao Xiaolan Qiu S.Kevin Zhou Division of Life Sciences and Medicine School of Biomedical Engineering University of Science and Technology of China (USTC) China Center for Medical Imaging Robotics Analytic Computing & Learning (MIRACLE) Suzhou Institute for Advance Research USTC China Suzhou Key Laboratory of Microwave Imaging Processing and Application Technology Suzhou Aerospace Information Research Institute China Key Laboratory of Precision and Intelligent Chemistry University of Science and Technology of China (USTC) China Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology China

ISBN: (数字)9798331520526

ISBN: (纸本)9798331520533

Airway extraction is paramount in the early diagnosis and treatment of respiratory diseases. As a tree-like structure, both topological-aware learning and voxel-wise classification are equally crucial for the airway. However, existing methods demonstrate insufficient topological learning, emphasizing only the supervision of individual key topological points. Consequently, this paper proposes a Explicit Topological Modeling (ExpTopo) approach to aid airway segmentation. It explicitly introduces topological metric space learning based on semantic segmentation, enhancing the model's structural perception by implementing global skeleton-level sparse topological learning (STL) and local voxel-level dense topological perception (DTP). Extensive experimental results demonstrate that the algorithm achieves competitive performance at both the topological and voxel levels. Code will be available in https://***/MorineZ/ExpTopo.

关键词： Codes Atmospheric modeling Semantic segmentation Pulmonary diseases Biological system modeling Extraterrestrial measurements Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

ReconBoost: boosting can achieve modality reconcilement 24

ReconBoost: boosting can achieve modality reconcilement

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Cong Hua Qianqian Xu Shilong Bao Zhiyong Yang Qingming Huang Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China and School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China Institute of Information Engineering Chinese Academy of Sciences Beijing China and School of Cyber Security University of Chinese Academy of Sciences Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China and Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China and Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China

This paper explores a novel multi-modal alternating learning paradigm pursuing a reconciliation between the exploitation of uni-modal features and the exploration of cross-modal interactions. This is motivated by the fact that current paradigms of multi-modal learning tend to explore multi-modal features simultaneously. The resulting gradient prohibits further exploitation of the features in the weak modality, leading to modality competition, where the dominant modality overpowers the learning process. To address this issue, we study the modality-alternating learning paradigm to achieve reconcilement. Specifically, we propose a new method called ReconBoost to update a fixed modality each time. Herein, the learning objective is dynamically adjusted with a reconcilement regularization against competition with the historical models. By choosing a KL-based reconcilement, we show that the proposed method resembles Friedman's Gradient-Boosting (GB) algorithm, where the updated learner can correct errors made by others and help enhance the overall performance. The major difference with the classic GB is that we only preserve the newest model for each modality to avoid overfitting caused by ensembling strong learners. Furthermore, we propose a memory consolidation scheme and a global rectification scheme to make this strategy more effective. Experiments over six multi-modal benchmarks speak to the efficacy of the method. We release the code at https://***/huacong/ReconBoost.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Large Language Models Are Read/Write Policy-Makers for Simultaneous Generation 39

Large Language Models Are Read/Write Policy-Makers for Simul...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Guo, Shoutao Zhang, Shaolei Ma, Zhengrui Feng, Yang Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences (ICT/CAS) China Key Laboratory of AI Safety Chinese Academy of Sciences China University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)157735897X

Simultaneous generation models write generation results while reading streaming inputs, necessitating a policy-maker to determine the appropriate output timing. Existing simultaneous generation methods generally adopt the traditional encoder-decoder architecture and learn the generation and policy-making capabilities through complex dynamic programming techniques. Although LLMs excel at text generation, they face challenges in taking on the role of policymakers through traditional training methods, limiting their exploration in simultaneous generation. To overcome these limitations, we propose a novel LLM-driven Simultaneous Generation (LSG) framework, which allows the off-the-shelf LLM to decide the generation timing and produce output concurrently. Specifically, LSG selects the generation policy that minimizes latency as the baseline policy. Referring to the baseline policy, LSG enables the LLM to devise an improved generation policy that better balances latency and generation quality, and writes generation results accordingly. Experiments on simultaneous translation and streaming automatic speech recognition tasks show that our method can achieve state-of-the-art performance utilizing the open-source LLMs and demonstrate practicality in real-world scenarios. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Open systems

来源：评论

学校读者我要写书评

暂无评论

Symbol-Level Physical Layer Security Design in Space-Air-Ground Integrated Networks

引用

IEEE Transactions on Vehicular technology 2025年

作者： Xia, Guiyang Shi, Qianmei Hu, Xianxin Zhou, Xiaobo Shu, Feng School of Information and Artificial Intelligence Anhui Provincial Engineering Research Center for Agricultural Information Perception and Intelligent Computing China Anhui Agricultural University Anhui Province Key Laboratory of Smart Agricultural Technology and Equipment Hefei230036 China Hainan University School of Information and Communication Engineering Haikou570228 China

In the down-link secure space-air-ground integrated network (SAGIN) with practical discrete modulation symbols, we consider the joint design of the power of satellite and unmanned aerial vehicle (UAV) swarm beamforming to combat a formidable eavesdropper intercepting both the satellite-to-UAV and UAV-to-ground communication links. Given the challenge posed by the discrete symbols-based joint optimization problem, the security mechanism for SAGIN is developed through alternating optimization. Specifically, the optimal power of satellite is first determined with a fixed UAV beamformer. Based on this power, we propose a pair of solution approaches: convex optimization-based iteration (CObI) and heuristics-based semi-analytic iteration (HbSAI). The former focuses on achieving high performance while the latter emphasizes efficiency. The effectiveness of both CObI and HbSAI methods is validated through simulation results, demonstrating their ability to enhance the achievable secrecy rate. © 2025 IEEE.

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

A Cross-direction Task Decoupling Network for Small Logo Detection

arXiv

引用

arXiv 2023年

作者： Hou, Sujuan Li, Xingzhuo Min, Weiqing Li, Jiacheng Wang, Jing Zheng, Yuanjie Jiang, Shuqiang School of Information Science and Engineering Shandong Normal University Jinan China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China

Logo detection plays an integral role in many applications. However, handling small logos is still difficult since they occupy too few pixels in the image, which burdens the extraction of discriminative features. The aggregation of small logos also brings a great challenge to the classification and localization of logos. To solve these problems, we creatively propose Cross-direction Task Decoupling Network (CTDNet) for small logo detection. We first introduce Cross-direction Feature Pyramid (CFP) to realize cross-direction feature fusion by adopting horizontal transmission and vertical transmission. In addition, Multi-frequency Task Decoupling Head (MTDH) decouples the classification and localization tasks into two branches. A multi-frequency attention convolution branch is designed to achieve more accurate regression by combining discrete cosine transform and convolution creatively. Comprehensive experiments on four logo datasets demonstrate the effectiveness and efficiency of the proposed method. Copyright © 2023, 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

BHJO: A Novel Hybrid Metaheuristic Algorithm Combining the Beluga Whale, Honey Badger, and Jellyfish Search Optimizers for Solving Engineering Design Problems

引用

Computer Modeling in Engineering & Sciences 2024年第10期141卷 219-265页

作者： Farouq Zitouni Saad Harous Abdulaziz S.Almazyad Ali Wagdy Mohamed Guojiang Xiong Fatima Zohra Khechiba Khadidja Â Kherchouche Department of Computer Science and Information Technology Kasdi Merbah UniversityP.O.Box 30000OuarglaAlgeria Department of Computer Science College of Computing and InformaticsUniversity of SharjahP.O.Box 27272SharjahUnited Arab Emirates Department of Computer Engineering College of Computer and Information SciencesKing Saud UniversityP.O.Box 51178Riyadh11543Saudi Arabia Operations Research Department Faculty of Graduate Studies for Statistical ResearchCairo UniversityGiza12613Egypt Applied Science Research Center Applied Science Private UniversityAmman11937Jordan Guizhou Key Laboratory of Intelligent Technology in Power System College of Electrical EngineeringGuizhou UniversityGuiyang550025China

Hybridizing metaheuristic algorithms involves synergistically combining different optimization techniques to effectively address complex and challenging optimization *** approach aims to leverage the strengths of multiple algorithms,enhancing solution quality,convergence speed,and robustness,thereby offering a more versatile and efficient means of solving intricate real-world optimization *** this paper,we introduce a hybrid algorithm that amalgamates three distinct metaheuristics:the Beluga Whale Optimization(BWO),the Honey Badger Algorithm(HBA),and the Jellyfish Search(JS)*** proposed hybrid algorithm will be referred to as *** this fusion,the BHJO algorithm aims to leverage the strengths of each *** this hybridization,we thoroughly examined the exploration and exploitation capabilities of the BWO,HBA,and JS metaheuristics,as well as their ability to strike a balance between exploration and *** meticulous analysis allowed us to identify the pros and cons of each algorithm,enabling us to combine them in a novel hybrid approach that capitalizes on their respective strengths for enhanced optimization *** addition,the BHJO algorithm incorporates Opposition-Based Learning(OBL)to harness the advantages offered by this technique,leveraging its diverse exploration,accelerated convergence,and improved solution quality to enhance the overall performance and effectiveness of the hybrid ***,the performance of the BHJO algorithm was evaluated across a range of both unconstrained and constrained optimization problems,providing a comprehensive assessment of its efficacy and applicability in diverse problem ***,the BHJO algorithm was subjected to a comparative analysis with several renowned algorithms,where mean and standard deviation values were utilized as evaluation *** rigorous comparison aimed to assess the performance of the BHJOalgorithmabout its counterparts,shedd

关键词： Global optimization hybridization of metaheuristics beluga whale optimization honey badger algorithm jellyfish search optimizer chaotic maps opposition-based learning

来源：评论

学校读者我要写书评

暂无评论

A Cross-direction Task Decoupling Network for Small Logo Detection

A Cross-direction Task Decoupling Network for Small Logo Det...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Sujuan Hou Xingzhuo Li Weiqing Min Jiacheng Li Jing Wang Yuanjie Zheng Shuqiang Jiang School of Information Science and Engineering Shandong Normal University Jinan China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China

关键词：

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：