检索结果-内蒙古大学图书馆

Journal of Network Intelligence 2022年第2期7卷 332-346页

作者： Chen, Ran-Fan Luo, Hao Huang, Kuan-Chun Nguyen, Trong-The Pan, Jeng-Shyang College of Computer Science and Mathematics Fujian University of Technology Fuzhou350118 China School of Aeronautics and Astronautics Zhejiang University HangZhou310000 China Department of Industrial and Systems Engineering Chung Yuan University Taoyuan320-33 Taiwan Multimedia Communications Lab VNUHCM-University of Information Technology Ho Chi Minh City700000 Viet Nam Vietnam National University Ho Chi Minh City700000 Viet Nam Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology Fuzhou350118 China College of Computer Science and Engineering Shandong University of Science and Technology Qingdao266590 China

Multiple electric vehicles simultaneously connected to a distribution load network will significantly impact the stability of the power grid. This paper proposes an improved Honey-badger algorithm (IHBA) through elite reverse learning, spiral update, and wild dog survival strategies to optimize the orderly charging of electric vehicles (EV). Objective functions of EV charge orderly planning are taken by using load fluctuation satisfaction, user cost satisfaction, and user convenience satisfaction to achieve the high efficiency of orderly charging. The benchmark test function and the electric vehicle se-quential charging problem were employed to evaluate the proposed IHBA approach. The obtained results are compared with the other algorithms in the literature, which indicate that the IHBA algorithm does not only provides more accurate outcome but better con-vergence speed than the other competitors. © 2022;Taiwan Ubiquitous Information CO LTD. All rights reserved.

关键词： Food products

来源：评论

学校读者我要写书评

暂无评论

A Survey of Research on Few-Shot Relation Classification

SSRN

引用

SSRN 2024年

作者： Zhang, YaChuan Guo, Yi Department of Computer Science and Engineering East China University of Science and Technology Shanghai200237 China Shanghai Engineering Research Center of Big Data Internet Audience Shanghai China Business Intelligence and Visualization Research Center National Engineering Laboratory for Big Data Distribution and Exchange Technologies Shanghai China

Relation classification is a crucial sub-task of information extraction, playing a significant role in extracting structured information from vast texts and constructing knowledge graphs. However, in practical scenarios, the availability of labeled data is often limited, and some datasets exhibit a long-tail distribution. To address these challenges, few-shot learning relation classification (FSRC) has emerged as a promising approach. The purpose of FSRC is to learn high-quality features with insufficient data for distinguishing the relation between given entities in a sentence. This task presents greater challenges compared to traditional relation classification tasks. Recently, FSRC has gained a lot of attention, prompting numerous researchers to provide innovative methods, datasets, and ideas to tackle this challenge. This paper focuses on relation classification based on few-shot learning and provides a comprehensive review of state-of-the-art techniques. Based on distinct research characteristics, we classified FSRC methods into five categories: metric-based method, optimization-based method, pre-trained and LLMs based method, prompt-based method, and lower source situation. We analyze the advantages and disadvantages of each category, provide a summary of the datasets, metrics, and results obtained by representative models. Finally, the paper concludes the current limitations of the few-shot relation classification and proposes future research directions. © 2024, The Authors. All rights reserved.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

SELF-ATTENTION RECURRENT SUMMARIZATION NETWORK WITH REINFORCEMENT LEARNING FOR VIDEO SUMMARIZATION TASK

SELF-ATTENTION RECURRENT SUMMARIZATION NETWORK WITH REINFORC...

引用

2021 IEEE International Conference on Multimedia and Expo, ICME 2021

作者： Phaphuangwittayakul, Aniwat Guo, Yi Ying, Fangli Xu, Wentian Zheng, Zheng Department of Computer Science and Engineering East China University of Science and Technology China National Engineering Laboratory for Big Data Distribution and Exchange Technologies China Shanghai Engineering Research Center of Big Data and Internet Audience China

ISBN: (纸本)9781665438643

With the exponential growth of video data, video summarization techniques are urgently needed for reducing people's efforts in the videos' content exploration by generating succinct but informative summaries from original lengthy videos. Though supervised video summarization approaches have demonstrated the state-of-the-art performance, unsupervised methods are still highly demanded due to resourcefully expensive human annotations and the subjectiveness of video summarization tasks. In this paper, a novel unsupervised-based Deep Self-attention Recurrent summarization network with Reinforcement Learning (DSR-RL) for video summarization is proposed. The model can learn the input video sequence and suggest the key-shot summary without additional human annotations by integrating self-attention, BRNN, and reinforcement learning mechanisms. The DSR-RL improves not only importance score through the attention map vector of self-attention network but also the diversity of summaries via the reward function of reinforcement learning. Our method outperforms the state-of-the-art unsupervised video summarization methods on both SumMe and TVSum datasets. The source code is available at https://***/phaphuang/DSR-RL. © 2021 IEEE

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

TiGDistill-BEV: Multi-view BEV 3D Object Detection via Target Inner-Geometry Learning Distillation

arXiv

引用

arXiv 2024年

作者： Xu, Shaoqing Li, Fang Huang, Peixiang Song, Ziying Yang, Zhi-Xin State Key Laboratory of Internet of Things for Smart City Department of Electromechanical Engineering University of Macau 999078 China School of Mechanical Engineering Beijing Institute of Technology China College of Engineering Peking University Beijing China School of Computer and Information Technology Beijing Key Lab of Traffic Data Analysis and Mining Beijing Jiaotong University Beijing100044 China

Accurate multi-view 3D object detection is essential for applications such as autonomous driving. Researchers have consistently aimed to leverage LiDAR’s precise spatial information to enhance camera-based detectors through methods like depth supervision and bird-eye-view (BEV) feature distillation. However, existing approaches often face challenges due to the inherent differences between LiDAR and camera data representations. In this paper, we introduce the TiGDistill-BEV, a novel approach that effectively bridges this gap by leveraging the strengths of both sensors. Our method distills knowledge from diverse modalities(e.g., LiDAR) as the teacher model to a camera-based student detector, utilizing the Target Inner-Geometry learning scheme to enhance camera-based BEV detectors through both depth and BEV features by leveraging diverse modalities. Specially, we propose two key modules: an inner-depth supervision module to learn the low-level relative depth relations within objects which equips detectors with a deeper understanding of object-level spatial structures, and an inner-feature BEV distillation module to transfer high-level semantics of different keypoints within foreground targets. To further alleviate the domain gap, we incorporate both inter-channel and inter-keypoint distillation to model feature similarity. Extensive experiments on the nuScenes benchmark demonstrate that TiGDistill-BEV significantly boosts camera-based only detectors achieving a state-of-the-art with 62.8% NDS and surpassing previous methods by a significant margin. The codes is available at: https://***/Public-BOTs/*** Copyright © 2024, The Authors. All rights reserved.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Towards Redefining the Reproducibility in Quantum Computing: A data Analysis Approach on NISQ Devices

Towards Redefining the Reproducibility in Quantum Computing:...

引用

Quantum Computing and engineering (QCE), IEEE International Conference on

作者： Priyabrata Senapati Zhepeng Wang Weiwen Jiang Travis S Humble Bo Fang Shuai Xu Qiang Guan Department of Computer Science Kent State University Department of Electrical and Computer Engineering George Mason University Quantum Science and Engineering Center George Mason University Quantum Science Center Oak Ridge National Laboratory Pacific Northwest National Laboratory HPC Group Department of Computer and Data Sciences Case Western Reserve University

Although the building of quantum computers has kept making rapid progress in recent years, noise is still the main challenge for any application to leverage the power of quantum computing. Existing works addressing noise in quantum devices proposed noise reduction when deploying a quantum algorithm to a specified quantum computer. The reproducibility issue of quantum algorithms has been raised since the noise levels vary on different quantum computers. Importantly, existing works largely ignore the fact that the noise of quantum devices varies as time goes by. Therefore, reproducing the results on the same hardware will even become a problem. We analyze the reproducibility of quantum machine learning (QML) algorithms based on daily model training and execution data collection. Our analysis shows a correlation between our QML models' test accuracy and quantum computer hardware's calibration features. We also demonstrate that noisy simulators for quantum computers are not a reliable tool for quantum machine learning applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Generalized Undersampling of Center Points Based on Granular Ball 7

Generalized Undersampling of Center Points Based on Granular...

引用

7th International Conference on Cloud Computing and Big data Analytics, ICCCBDA 2022

作者： Bai, Hao Wu, Yanmin Qi, Jinli Chen, Yanyi Chongqing University of Posts and Telecommunications Chongqing Key Laboratory of Computer Science and Technology ChongQing China ChongQing College of Electronic Engineering Department of Artificial Intelligence and Big Data ChongQing China ChongQing College of Electronic Engineering Department of General Education and International Studies ChongQing China Chongqing University of Posts and Telecommunications Department of Software Engineering ChongQing China

ISBN: (纸本)9781665487115

In this paper, we propose a new generic sampling classification method based on granular Ball sampling because of good robust noise immunity and possessing properties that can be classified as an undersampling method, called Granular Ball Center-based Common Under-sampling. The method uses adaptively generated Ball to cover the data space, and the sampled data are supported by the centroid properties of the Ball. Unlike the boundary sampling of granular ball sampling, this method mainly uses the center points to smooth out the noise, which not only can clearly represent the attributes, but also can reduce some computational effort, and in most of the time, it can obtain almost the same accuracy as the original model, or even can perform better. Compared with undersampling, it can be better adapted to the task of unbalanced classification as well as non-unbalanced classification. The above can show that the method is able to be generalized without the restriction of specific classifiers and also has a strong adaptability to the dataset. The method can also be effectively used as an undersampling method for unbalanced classification because it is supported by the centroid property, and the method has a speedup effect for most classifiers. These advantages form a strong advantage of the method in improving classifier performance. © 2022 IEEE.

关键词： Cloud computing Adaptation models Computational modeling Big data Task analysis

来源：评论

学校读者我要写书评

暂无评论

Adaptive-Non-Dominated Sorting Genetic Algorithm Based Multi-Objective Optimization Energy-Balanced Opportunistic Network Routing Strategy

SSRN

引用

SSRN 2023年

作者： Song, Ming Tang, Qi Xu, Gang Zhang, Feng Hao, Xinyu Huang, Baoqi College of Computer Science Inner Mongolia University Inner Mongolia Hohhot China Inner Mongolia A.R. Key Laboratory of Data Mining and Knowledge Engineering China Computer Science and Information Technology Shanxi University Shanxi Province Taiyuan China

In opportunistic networks, the uneven energy consumption of nodes and the polarization of cache utilization are important factors that impact network sustainability and overall performance. To address these issues, this paper proposes a multi-objective optimization energy-balanced routing strategy for opportunistic networks based on adaptive non-dominated sorting algorithm (ANMOR). The strategy aims to maximize the forwarding capability of nodes while achieving energy balance. The algorithm can find all Pareto-optimal solutions in the entire search space, which represent the trade-off relationships between different objectives and can provide a range of feasible solutions for routing. Experimental results show that this strategy can significantly improve the energy balance and cache utilization of opportunistic networks, enhance network performance, and prolong network lifetime. © 2023, The Authors. All rights reserved.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

A method of fundamental matrix estimation based on nsga-ii and improved quasi-affine transform

Journal of Network Intelligence

引用

Journal of Network Intelligence 2021年第2期6卷 313-327页

作者： Fan, Yi-Kai Liu, Shi-Jian Kong, Ling-Ping Pan, Jeng-Shyang College of Computer Science and Mathematics Fujian University of Technology Fuzhou350118 China VSB-Technical University of Ostrava Czech Republic Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology Fuzhou350118 China College of Computer Science and Engineering Shandong University of Science and Technology Qingdao266590 China Department of Information Management Chaoyang University of Technology Taiwan

The fundamental matrix is the mainstream solution to computer vision problems such as 3D reconstruction, real-time location and map building. Accuracy and efficiency are two main measurement indexes in fundamental matrix estimation. When the accuracy is not enough, it often needs to be corrected through back-end optimization and other costly ways, and low efficiency will affect the real-time performance of the system. In order to solve this problem, this paper proposes a new estimation method of fundamental matrix based on improved quasi affine transformation. Specifically, based on the QUATRE algorithm, this method first proposes a population cooperation method based on a specific "gene-chromosome" pattern. Secondly, combining the advantages of NSGA-II in solving multi-objective problems, the Pareto dominance relationship of the population chromosome was firstly calculated according to the objective function of mean polarity distance and internal points in the way of NSGA-II, and the crowding degree was also calculated. The operations of population initialization, mutation and crossover in the discrete solution space represented by the homogeneous coordinate system are redefined. The selection operation is then performed according to the elite policy of NSGA-II. In addition, a confidence-based method to determine the number of iterations is proposed to accelerate the algorithm. Experimental results show that the proposed method can effectively eliminate noise and mismatching, and is superior to the current mainstream methods in accuracy and efficiency, and can effectively solve the problem of fundamental matrix estimation. © 2021 Global Research Online. All rights reserved.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Like an Ophthalmologist: Dynamic Selection Driven Multi-View Learning for Diabetic Retinopathy Grading 39

Like an Ophthalmologist: Dynamic Selection Driven Multi-View...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Luo, Xiaoling Xu, Qihao Wu, Huisi Liu, Chengliang Lai, Zhihui Shen, Linlin Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University Shenzhen China Shenzhen Key Laboratory of Visual Object Detection and Recognition Harbin Institute of Technology Shenzhen China Department of Computer Science and Engineering Hong Kong University of Science and Technology Hong Kong National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China Guangdong Provincial Key Laboratory of Intelligent Information Processing China

ISBN: (纸本)157735897X

Diabetic retinopathy (DR), with its large patient population, has become a formidable threat to human visual health. In the clinical diagnosis of DR, multi-view fundus images are considered to be more suitable for DR diagnosis because of the wide coverage of the field of view. Therefore, different from the previous single-view DR grading methods, we design a dynamic selection-driven multi-view DR grading method to fit clinical scenarios better. Since lesion information plays a key role in DR diagnosis, previous methods usually boost the model performance by enhancing the lesion feature. However, during the actual diagnosis, ophthalmologists not only focus on the crucial parts, but also exclude irrelevant features to ensure the accuracy of judgment. To this end, we introduce the idea of dynamic selection and design a series of selection mechanisms from fine granularity to coarse granularity. In this work, we first introduce an Ophthalmic Image Reader (OIR) agent to provide the model with pixel-level prompts of suspected lesion areas. Moreover, we design a Multi-View Token Selection Module (MVTSM) that prunes redundant feature tokens and dynamically selects key information. In the final decision stage, we dynamically fuse multi-view features through the novel Multi-View Mixture of Experts Module (MVMoEM), to enhance key views and reduce the impact of conflicting views. Extensive experiments on a large multi-view fundus image dataset with 34,452 images prove that our method performs favorably against state-of-the-art models. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Ophthalmology

来源：评论

学校读者我要写书评

暂无评论

LFNAT 2023 Challenge on Light Field Depth Estimation: Methods and Results

LFNAT 2023 Challenge on Light Field Depth Estimation: Method...

引用

2023 IEEE/CVF Conference on computer Vision and Pattern Recognition Workshops, CVPRW 2023

作者： Sheng, Hao Liu, Yebin Yu, Jingyi Wu, Gaochang Xiong, Wei Guo, Longzhao Xie, Yanlin Zhang, Shuo Chang, Song Lin, Youfang Chao, Wentao Wang, Xuechun Wang, Guanghui Duan, Fuqing Wang, Tun Yang, Da Cui, Zhenglong Wang, Sizhe Zhao, Mingyuan Wang, Qiong Chen, Qianyu Liang, Zhengyu Wang, Yingqian Yang, Jungang Yang, Xueting Deng, Junli Cong, Ruixuan Chen, Rongshan State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University China Beihang Hangzhou Innovation Institute Yuhang China Faculty of Applied Sciences Macao Polytechnic University China Tsinghua University China Shanghaitech University China State Key Laboratory of Synthetical Automation for Process Industries Northeastern University China Beijing Meet Yuan Co. Ltd China Beijing Key Laboratory of Traffic Data Analysis and Mining School of Computer and Information Technology Beijing Jiaotong University China Beijing Normal University China Toronto Metropolitan University Canada College of Computer Science and Technology Zhejiang University of Technology China National University of Defense Technology China School of Information and Communication Engineering Communication University of China China

ISBN: (纸本)9798350302493

This paper reviews the 1st LFNAT challenge on light field depth estimation, which aims at predicting disparity information of central view image in a light field (i.e., pixel offset between central view image and adjacent view image). Compared to multi-view stereo matching, light field depth estimation emphasizes efficient utilization of the 2D angular information from multiple regularly varying views. This challenge specifies UrbanLF [20] light field dataset as the sole data source. There are two phases in total: submission phase and final evaluation phase, in which 75 registered participants successfully submit their predicted results in the first phase and 7 eligible teams compete in the second phase. The performance of all submissions is carefully reviewed and shown in this paper as a new standard for the current state-of-the-art in light field depth estimation. Moreover, the implementation details of these methods are also provided to stimulate related advanced research. © 2023 IEEE.

关键词： Stereo image processing

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：