检索结果-内蒙古大学图书馆

Proceedings of the 38th International Conference on Neural information processing Systems

作者： Shangshang Yang Mingyang Chen Ziwen Wang Xiaoshan Yu Panpan Zhang Haiping Ma Xingyi Zhang Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Anhui University Hefei Anhui P. R. China and Anhui Province Key Laboratory of Intelligent Computing and Applications Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Anhui University Hefei Anhui P. R. China and Department of Information Materials and Intelligent Sensing Laboratory of Anhui Province Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Anhui University Hefei Anhui P. R. China

ISBN: (纸本)9798331314385

Existing graph learning-based cognitive diagnosis (CD) methods have made relatively good results, but their student, exercise, and concept representations are learned and exchanged in an implicit unified graph, which makes the interaction-agnostic exercise and concept representations be learned poorly, failing to provide high robustness against noise in students' interactions. Besides, lower-order exercise latent representations obtained in shallow layers are not well explored when learning the student representation. To tackle the issues, this paper suggests a meta multigraph-assisted disentangled graph learning framework for CD (DisenGCD), which learns three types of representations on three disentangled graphs: student-exercise-concept interaction, exercise-concept relation, and concept dependency graphs, respectively. Specifically, the latter two graphs are first disentangled from the interaction graph. Then, the student representation is learned from the interaction graph by a devised meta multigraph learning module; multiple learnable propagation paths in this module enable current student latent representation to access lower-order exercise latent representations, which can lead to more effective nad robust student representations learned; the exercise and concept representations are learned on the relation and dependency graphs by graph attention modules. Finally, a novel diagnostic function is devised to handle three disentangled representations for prediction. Experiments show better performance and robustness of DisenGCD than state-of-the-art CD methods and demonstrate the effectiveness of the disentangled learning framework and meta multigraph module. The source code is available at https://***/BIMK/intelligent-Education/tree/main/DisenGCD.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optimizing Parameter Design with Frequency and Clock Drift Constraints in Microgrids∗ 63

Optimizing Parameter Design with Frequency and Clock Drift C...

引用

63rd IEEE Conference on Decision and Control, CDC 2024

作者： Yu, Chang Lu, Xiaoqing Wuhan University of Science and Technology School of Information Science and Engineering Wuhan430081 China Huazhong University of Science and Technology Ministry of Education Key Laboratory of Image Processing and Intelligent Control Wuhan430074 China Wuhan University School of Electrical Engineering and Automation Wuhan430000 China

ISBN: (纸本)9798350316339

Microgrids subjected to secondary cooperative control encounter significant challenges, including operational constraints and clock drifts, adversely affecting their stability and efficiency. This paper provides conditions that assure optimal microgrid performance in both transient and steady-state scenarios, focusing on the effects of clock drifts and fluctuations in load. Furthermore, we introduce a novel approach for designing secondary control parameters, specifically engineered to minimize steady-state discrepancies attributable to clock drifts while ensuring adherence to standards for transient operations. Comprehensive experimental validations corroborate the effectiveness of our proposed solutions. © 2024 IEEE.

关键词： Microgrids

来源：评论

学校读者我要写书评

暂无评论

Temporal Transformation Network Based On Scale Sequences for Cloth-Changing Person Re-Identification in Video Datasets 9

Temporal Transformation Network Based On Scale Sequences for...

引用

9th International Conference on Computer and Communications, ICCC 2023

作者： Zhu, Xiaoke Zhao, Bo Dong, Zhiwei Dong, Lingyun Li, Danyang School of Computer and Information Engineering Henan University Kaifeng China Henan University Henan Engineering Research Center of Intelligent Technology and Application China Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng China

ISBN: (纸本)9798350317251

This paper introduces the Temporal Transform Network based on Scale Sequences (TTS) for cloth-changing person re-identification in video datasets. The TTS network is designed to capture multi-scale temporal cues within video sequences. It accomplishes this by initially modeling short-term temporal cues between adjacent frames, followed by capturing long-term relationships between non-consecutive frames. In more detail, short-term temporal cues are modeled through parallel inflated convolutions with different time dilation rates, enabling the representation of pedestrian movement and appearance dynamics. Long-term relationships are effectively captured using a temporal self-attention model, mitigating challenges such as occlusion and noise within the video sequence. The TTS network outperforms existing methods across cloth-changing video ReID datasets such as CCVID. For instance, under general settings, our approach exhibits a 1.1% improvement in top-1 accuracy and a corresponding 1.1% increase in mAP compared to the baseline. In cloth-changing settings, we observe a 0.2% enhancement in top-1 accuracy and a notable 1.3% increase in mAP relative to the baseline. © 2023 IEEE.

关键词： Video recording

来源：评论

学校读者我要写书评

暂无评论

Computing Flow Experience Based on Physiological Signals: A Systematic Literature Review

Computing Flow Experience Based on Physiological Signals: A ...

引用

2025 CHI Conference on Human Factors in Computing Systems, CHI EA 2025

作者： Hong, Yichen Zhou, Chao Liu, Zelu Zifeng, Ni Liu, Juan Li, Xiangxian Yang, Chenglei Bian, Yulong Shandong University Weihai China Human Computer Interaction Technology and Intelligent Information Processing Laboratory Institute of Software Chinese Academy of Sciences Beijing China Shandong University School of Mechanical Electrical & Information Engineering Weihai China Shandong University Jinan China School of Software Shandong University Jinan China Shandong Key Laboratory of Intelligent Electronic Packaging Testing and Application Shandong University Shandong Weihai China Shandong Key Laboratory of Intelligent Electronic Packaging Testing and Application China

ISBN: (纸本)9798400713958

Flow experience is a key user experience in human-computer interaction (HCI). Compared with traditional subjective measurements, physiological signal-based methods (i.e. physiological computation of flow experience) can measure flow experience in a more objective and real-time way without interrupting the ongoing activity of the user. Despite scattered studies, a systematic review of research in this field is absent. Synthesizing key aspects of this field, including the conceptualization of flow experience, prevalent theoretical models, foundational research steps for experiment, computerized tasks for inducing flow, commonly used physiological signals, methods for analyzing flow state, and application in HCI. Finally, we discuss the potential of this field to propel HCI and user experience evaluation technologies, while projecting future research avenues. This paper is expected to help researchers grasp existing work in physiological signal-based flow computing and inspire subsequent explorations. © 2025 Copyright held by the owner/author(s).

关键词： Flow simulation

来源：评论

学校读者我要写书评

暂无评论

Quality-Oriented Task Assignment for Heterogeneous Users in Mobile Crowdsensing 26

Quality-Oriented Task Assignment for Heterogeneous Users in ...

引用

26th International Conference on Computer Supported Cooperative Work in Design, CSCWD 2023

作者： Chen, Kang Li, Peng Huang, Weiyi Nie, Lei Bao, Haizhou Liu, Qin Wuhan University of Science and Technology School of Computer Science and Technology China Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System China Wuhan University School of Cyber Science and Engineering China

ISBN: (纸本)9798350331684

Mobile crowdsensing (MCS) is a potential technology for large-scale data collection. This technology requires the platform to recruit users to complete tasks in specific areas. A vital issue in MCS is task assignment, and most existing task assignment efforts consider only a single user type, which is not reasonable in real scenarios. Task assignment becomes more complicated when the platform tries to assign tasks to heterogeneous users with a limited budget in the platform. In this paper, we consider a quality-oriented task assignment for heterogeneous users problem. Professional users have a high sensing quality with a high cost, and normal users have a low sensing quality with a low cost First, we model the sensing capabilities and the costs of different users and formulate the quality-oriented task assignment for heterogeneous users problem. Then, we design the integer linear programming form and prove that the problem is NP-hard. By verifying the submodularity of the objective function, we present a greedy algorithm. Considering the inefficiency of the algorithm, we design two genetic algorithms to improve the total sensing quality. Finally, we evaluate the proposed algorithms under different cost cases based on a real dataset The results show that our proposed algorithm performs well under different cost distribution scenarios. © 2023 IEEE.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

On Privacy-Preserving Task Assignment for Heterogeneous Users in Mobile Crowdsensing 26

On Privacy-Preserving Task Assignment for Heterogeneous User...

引用

26th International Conference on Computer Supported Cooperative Work in Design, CSCWD 2023

作者： Zhang, Ji Li, Peng Huang, Weiyi Nie, Lei Bao, Haizhou Liu, Qin Wuhan University of Science and Technology School of Computer Science and Technology China Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System China Wuhan University School of Cyber Science and Engineering China

ISBN: (纸本)9798350331684

Task assignment is a key challenge in mobile crowd-sensing because of the varying capabilities of crowd users. Location-based task assignment schemes require users to upload their location to an untrusted platform, which raises many privacy concerns. However, stronger privacy preservation may lead to lower system utility. It is challenging to maximize system utility under privacy preservation for users. In this paper, we propose a privacy-preserving task assignment for heterogeneous users (PTAH) problem in mobile crowdsensing. Specifically, we divide users into two groups: private users with location privacy requirements and public users without location privacy requirements. We first design a privacy-preserving mechanism to obfuscate the actual location of private users. Then we construct a relationship graph based on the locations between users and tasks. We prove that the PTAH problem is an NP-hard problem, so to maximize the system utility, we propose an approximation algorithm based on the greedy algorithm. Then we propose a multi-thread cooperative simulated annealing algorithm to search for a better approximate solution. Finally, we conducted simulations based on the widely-used real-world Roma dataset. The results show that our proposed algorithm consistently outperforms other baseline algorithms. © 2023 IEEE.

关键词： Location

来源：评论

学校读者我要写书评

暂无评论

Extracting Variable-Depth Logical Document Hierarchy from Long Documents:Method,Evaluation,and Application

引用

Journal of Computer Science & Technology 2022年第3期37卷 699-718页

作者： Rong-Yu Cao Yi-Xuan Cao Gan-Bin Zhou Ping Luo Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences Institute of Computing TechnologyChinese Academy of SciencesBeijing 100190China University of Chinese Academy of Sciences Beijing 100049China WeChat Search Application Department Tencent Holdings Ltd.Beijing 100080China Peng Cheng Laboratory Shenzhen 518066China

In this paper,we study the problem of extracting variable-depth"logical document hierarchy"from long documents,namely organizing the recognized"physical document objects"into hierarchical *** discovery of logical document hierarchy is the vital step to support many downstream applications(e.g.,passage-based retrieval and high-quality information extraction).However,long documents,containing hundreds or even thousands of pages and a variable-depth hierarchy,challenge the existing *** address these challenges,we develop a framework,namely Hierarchy Extraction from Long Document(HELD),where we"sequentially"insert each physical object at the proper position on the current *** whether each possible position is proper or not can be formulated as a binary classification *** further improve its effectiveness and efficiency,we study the design variants in HELD,including traversal orders of the insertion positions,heading extraction explicitly or implicitly,tolerance to insertion errors in predecessor steps,and so *** for evaluations,we find that previous studies ignore the error that the depth of a node is correct while its path to the root is *** such mistakes may worsen the downstream applications seriously,a new measure is developed for a more careful *** empirical experiments based on thousands of long documents from Chinese financial market,English financial market and English scientific publication show that the HELD model with the"root-to-leaf"traversal order and explicit heading extraction is the best choice to achieve the tradeoff between effectiveness and efficiency with the accuracy of 0.972,6,0.729,1 and 0.957,8 in the Chinese financial,English financial and arXiv datasets,***,we show that the logical document hierarchy can be employed to significantly improve the performance of the downstream passage retrieval *** summary,we conduct a systematic study on this task in terms of methods

关键词： logical document hierarchy long documents passage retrieval

来源：评论

学校读者我要写书评

暂无评论

Dehazing Quality Evaluation Algorithm Integrating Dark Channel Theory and Image Depth Estimation

Journal of Network Intelligence

引用

Journal of Network Intelligence 2024年第2期9卷 1119-1133页

作者： Huang, Jia-Yan Xu, Xin-Xin Luo, Shao-Ye Zhao, Wan-Qi Fan, Hao-Yi Grau, Antoni Guerra, Edmundo Wang, Chuan-Sheng Zhang, Fu-Quan New Engineering Industry College Putian University Putian351100 China The University of Sheffield SheffieldS10 2TN United Kingdom School of Computer and Artificial Intelligence Zhengzhou University Zhengzhou450001 China Department of Automatic Control Technical Polytechnic University of Catalonia Barcelona08034 Spain Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou350108 China

Image dehazing is an important research topic and hotspot in the fields of image processing and computer vision. Therefore, evaluating the performance of image dehazing algorithms has become an import research issue. However, current image quality assessment (IQA) algorithms only judge the final dehazed image and do not give an analysis of the capabilities of the image dehazing algorithm. In order to fill this gap, we propose an image dehazing quality assessment method that integrated the dark channel prior with image depth estimation. The proposed method first uses the dark channel prior to estimate the absolute amount of haze removed from each pixel as an indication of the performance of dehazing. Then, a dual-scale variance ratio method is introduced to estimate the scene depth of the image. Finally, the relative dehazing is calculated from the obtained absolute dehazing and the image depth to represent the capability of the dehazing algorithm. The method proposed in this paper first introduces the concepts of relative and absolute dehazing quantities, along with pioneering a pixel-level evaluation of dehazing outcomes. Extensive experiments show that the algorithm proposed in this paper is more in line with human subjective judgment than other IQA algorithms. © 2024, Taiwan Ubiquitous information CO LTD. All rights reserved.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Structured Sparse Coding With the Group Log-regularizer for key Frame Extraction

引用

IEEE/CAA Journal of Automatica Sinica 2022年第10期9卷 1818-1830页

作者： Zhenni Li Yujie Li Benying Tan Shuxue Ding Shengli Xie the School of Automation Guangdong University of TechnologyGuangzhou 510006 the Guangdong-Hong Kong-Macao Joint Laboratory for Smart Discrete Manufacturing Guangdong University of Technology(GDUT)Guangzhou 510006China the School of Artificial Intelligence Guilin University of Electronic TechnologyGuilin 541004China the National Institute of Advanced Industrial Science and Technology TsukubaIbaraki 305-8560Japan IEEE the Key Laboratory of Intelligent Information Processing and System Integration of Io T(GDUT) Ministry of Education Guangdong Key Laboratory of IoT Information Technology(GDUT) Guangzhou 510006China

key frame extraction based on sparse coding can reduce the redundancy of continuous frames and concisely express the entire ***,how to develop a key frame extraction algorithm that can automatically extract a few frames with a low reconstruction error remains a *** this paper,we propose a novel model of structured sparse-codingbased key frame extraction,wherein a nonconvex group log-regularizer is used with strong sparsity and a low reconstruction *** automatically extract key frames,a decomposition scheme is designed to separate the sparse coefficient matrix by *** rows enforced by the nonconvex group log-regularizer become zero or nonzero,leading to the learning of the structured sparse coefficient *** solve the nonconvex problems due to the log-regularizer,the difference of convex algorithm(DCA)is employed to decompose the log-regularizer into the difference of two convex functions related to the l1 norm,which can be directly obtained through the proximal ***,an efficient structured sparse coding algorithm with the group log-regularizer for key frame extraction is developed,which can automatically extract a few frames directly from the video to represent the entire video with a low reconstruction *** results demonstrate that the proposed algorithm can extract more accurate key frames from most Sum Me videos compared to the stateof-the-art ***,the proposed algorithm can obtain a higher compression with a nearly 18% increase compared to sparse modeling representation selection(SMRS)and an 8% increase compared to SC-det on the VSUMM dataset.

关键词： Difference of convex algorithm(DCA) group logregularizer key frame extraction structured sparse coding

来源：评论

学校读者我要写书评

暂无评论

Two-stage Vehicle Pair Dispatch in Multi-hop Ridesharing 26

Two-stage Vehicle Pair Dispatch in Multi-hop Ridesharing

引用

26th International Conference on Computer Supported Cooperative Work in Design, CSCWD 2023

作者： Wei, Xiaobo Li, Peng Huang, Weiyi Liu, Zhiyuan Liu, Qin Wuhan University of Science and Technology School of Computer Science and Technology China Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System China Wuhan University School of Cyber Science and Engineering China

ISBN: (纸本)9798350331684

Ridesharing benefits the economy and the environment. In multi-hop ridesharing, passengers are permitted to switch vehicles within a single trip, extending the flexibility of conventional ridesharing. Nonetheless, vehicle dispatch is a difficult issue in multi-hop ridesharing. We subdivide the vehicle dispatching problem into the vehicle pairing problem and the request selection problem within a vehicle pair. To address these subproblems, we propose a two-stage framework for vehicle pair dispatching. In the initial stage, we model the vehicle pairing problem as a maximum vehicle-vehicle matching problem in a general graph, which differs from the conventional vehicle-request matching problem in a bipartite graph. The vehicle pairing algorithm is proposed to efficiently solve the vehicle pairing problem. In the second stage, we model the request selection problem as a multidimensional knapsack problem (d-KP) and propose an LP-relaxation request selection algorithm with an approximation ratio 1/5. Experiments conducted on a real-world dataset demonstrate the economic benefit of our proposed two-stage framework. © 2023 IEEE.

关键词： Vehicles

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：