检索结果-内蒙古大学图书馆

Specificity-preserving RGB-D saliency detection

Computational Visual Media 2023年第2期9卷 297-317页

作者： Tao Zhou Deng-Ping Fan Geng Chen Yi Zhou Huazhu Fu School of Computer Science and Engineering Nanjing University of Science and TechnologyNanjing 210094China Key Laboratory of System Control and Information Processing Ministry of EducationShanghaiChina Computer Vision Lab ETH Z¨urichZ¨urichSwitzerland School of Computer Science and Engineering Northwestern Polytechnical UniversityXi’anChina School of Computer Science and Engineering Southeast UniversityNanjingChina Inception Institute of Artificial Intelligence Abu DhabiUnited Arab Emirates

Salient object detection(SOD)in RGB and depth images has attracted increasing research *** RGB-D SOD models usually adopt fusion strategies to learn a shared representation from RGB and depth modalities,while few methods explicitly consider how to preserve modality-specific *** this study,we propose a novel framework,the specificity-preserving network(SPNet),which improves SOD performance by exploring both the shared information and modality-specific ***,we use two modality-specific networks and a shared learning network to generate individual and shared saliency prediction *** effectively fuse cross-modal features in the shared learning network,we propose a cross-enhanced integration module(CIM)and propagate the fused feature to the next layer to integrate cross-level ***,to capture rich complementary multi-modal information to boost SOD performance,we use a multi-modal feature aggregation(MFA)module to integrate the modalityspecific features from each individual decoder into the shared *** using skip connections between encoder and decoder layers,hierarchical features can be fully *** experiments demonstrate that our SPNet outperforms cutting-edge approaches on six popular RGB-D SOD and three camouflaged object detection *** project is publicly available at https://***/taozh2017/SPNet.

关键词： salient object detection(SOD) RGB-D cross-enhanced integration module(CIM) multi-modal feature aggregation(MFA)

来源：评论

学校读者我要写书评

暂无评论

On Interval Perturbation of the ɑ-Symmetric Implicational Algorithm 2nd

On Interval Perturbation of the ɑ-Symmetric Implicational A...

引用

2nd International Conference on Artificial intelligence Logic and Applications, AILA 2022

作者： Tang, Yiming Han, Jianghui Bao, Guangqing Chen, Rui Anhui Province Key Laboratory of Affective Computing and Advanced Intelligent Machine School of Computer and Information Hefei University of Technology Anhui Hefei230601 China Engineering Research Center of Safety Critical Industry Measure and Control Technology Ministry of Education Hefei University of Technology Anhui Hefei230601 China

ISBN: (纸本)9789811975097

Perturbation is an important property of fuzzy reasoning algorithms. It is an important task to estimate the upper and lower bounds of the output after a perturbation (such as an interval perturbation) is given to the input. In this study, the interval perturbation problem of a fuzzy reasoning algorithm, i.e., the ɑ-symmetric implicational algorithm, is researched systematically. For FMP (Fuzzy Modus Ponens) and FMT (Fuzzy Modus Tollens) problems of fuzzy reasoning, aiming at the case of a single rule, the estimation for the upper and lower bounds are obtained for the input interval disturbance, in which R-implications and (S, N)-implications are mainly employed. Then the stability is verified on account of the upper and lower bounds. Following that, for the multi-rule case, the upper and lower bounds of the output are also given, and the corresponding stability is validated. In conclusion, it is found that the ɑ-symmetric implicational algorithm has good stability. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Fuzzy inference

来源：评论

学校读者我要写书评

暂无评论

Distributed Secure Consensus Estimation for Power Systems Against False Data Injection Attacks

引用

International Journal of Robust and Nonlinear control 2025年第0期

作者： Cheng, Zhijian Ren, Hongru Qin, Jiahu Lu, Renquan School of Automation Guangdong-Hong Kong Joint Laboratory for Intelligent Decision and Cooperative Control and Guangdong Provincial Key Laboratory for Intelligent Decision and Cooperative Control Guangdong University of Technology Guangzhou China Department of Automation University of Science and Technology of China Hefei China Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei China

As a result of the rapid growth of distributed state estimation in modern power systems, power networks are facing increasingly serious security problems, thus requiring the advancement of defense techniques against cyber attacks. This paper is devoted to investigating distributed consensus state estimation with a defense mechanism against false data injection (FDI) attacks for power systems. By introducing a transformation matrix, the local subsystem model associated with the mixed remote terminal unit and phasor measurement unit measurements is constructed. Taking into account historical estimation information on state variables without being attacked, a defense mechanism constructed by secure historical estimation value is presented to protect the estimator against FDI attacks while maintaining accuracy in estimation. Then a distributed Kalman consensus filter (DKCF) is hosted to estimate the dynamic states of power systems under FDI attack protector. Considering scalability in large-scale power systems, a suboptimal DKCF with the designed protector is developed. By means of the Lyapunov-based approach, a sufficient condition is provided to ensure that the proposed estimator equipped with the defense mechanism is stable. Finally, the proposed distributed state estimation algorithms are validated on an IEEE benchmark 14-bus power system. © 2025 John Wiley & Sons Ltd.

关键词： Cyber attacks

来源：评论

学校读者我要写书评

暂无评论

AUTOSIM:Automated Urban Traffic Operation Simulation via Meta-Learning

引用

IEEE/CAA Journal of Automatica Sinica 2023年第9期10卷 1871-1881页

作者： Yuanqi Qin Wen Hua Junchen Jin Jun Ge Xingyuan Dai Lingxi Li Xiao Wang Fei-Yue Wang Zhejiang Lab Hangzhou 310030China ECARX Technology Co. Ltd.Shanghai 201811China IEEE Zhejiang Supcon Information Company Ltd. Hangzhou 310052China the State Key Laboratory for Management and Control of Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China Indiana University-Purdue University Indianapolis(IUPUI) IndianapolisIndiana 46202 USA School of Artificial Intelligence Anhui UniversityHefei 230039China

Online traffic simulation that feeds from online information to simulate vehicle movement in real-time has recently seen substantial advancement in the development of intelligent transportation systems and urban traffic *** has been a challenging problem due to three aspects:1)The diversity of traffic patterns due to heterogeneous layouts of urban intersections;2)The nature of complex spatiotemporal correlations;3)The requirement of dynamically adjusting the parameters of traffic models in a real-time *** cater to these challenges,this paper proposes an online traffic simulation framework called automated urban traffic operation simulation via meta-learning(AUTOSIM).In particular,simulation models with various intersection layouts are automatically generated using an open-source simulation tool based on static traffic geometry *** a meta-learning technique,AUTOSIM enables an automated learning process for dynamic model settings of traffic scenarios featured with different spatiotemporal ***,AUTOSIM is capable of adapting traffic model parameters according to dynamic traffic information in real-time by using a *** computational experiments,we demonstrate the effectiveness of the meta-learningbased framework that is capable of providing reliable supports to real-time traffic simulation and dynamic traffic operations.

关键词： Conditional generative adversarial network signalized urban networks short-term link speed prediction

来源：评论

学校读者我要写书评

暂无评论

Cooperative Classification and Rationalization for Graph Generalization

arXiv

引用

arXiv 2024年

作者： Yue, Linan Liu, Qi Liu, Ye Gao, Weibo Yao, Fangzhou Li, Wenfeng Anhui Province Key Laboratory of Big Data Analysis and Application University of Science and Technology of China State Key Laboratory of Cognitive Intelligence Hefei China Douyin Vision Co. Ltd Beijing China

Graph Neural Networks (GNNs) have achieved impressive results in graph classification tasks, but they struggle to generalize effectively when faced with out-of-distribution (OOD) data. Several approaches have been proposed to address this problem. Among them, one solution is to diversify training distributions in vanilla classification by modifying the data environment, yet accessing the environment information is complex. Besides, another promising approach involves rationalization, extracting invariant rationales for predictions. However, extracting rationales is difficult due to limited learning signals, resulting in less accurate rationales and diminished predictions. To address these challenges, in this paper, we propose a Cooperative Classification and Rationalization (C2R) method, consisting of the classification and the rationalization module. Specifically, we first assume that multiple environments are available in the classification module. Then, we introduce diverse training distributions using an environment-conditional generative network, enabling robust graph representations. Meanwhile, the rationalization module employs a separator to identify relevant rationale subgraphs while the remaining non-rationale subgraphs are de-correlated with labels. Next, we align graph representations from the classification module with rationale subgraph representations using the knowledge distillation methods, enhancing the learning signal for rationales. Finally, we infer multiple environments by gathering non-rationale representations and incorporate them into the classification module for cooperative learning. Extensive experimental results on both benchmarks and synthetic datasets demonstrate the effectiveness of C2R. Code is available at https://***/yuelinan/Codes-of-C2R. Copyright © 2024, The Authors. All rights reserved.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

On Networked Dynamical Systems with Heterogeneous Constraints:Equilibrium Points and Stability 41

On Networked Dynamical Systems with Heterogeneous Constraint...

引用

第41届中国控制会议

作者： Qichao Ma Jiahu Qin Yu Kang Huijun Gao Department of Automation University of Science and Technology of China Institute of Artificial Intelligence Hefei Comprehensive National Science Center Institute of Advanced Technology University of Science and Technology of China Research Institute of Intelligent Control and Systems and the State Key Laboratory of Robotics and System Harbin Institute of Technology

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

In this paper,we investigate multi-agent systems with heterogeneous constraints,which can represent the heuristic beliefs of the agents towards an issue or the physical constraints of the *** typical example is a group of interacting unmanned aerial vehicles in a complex environment with multiple physical *** a result of the heterogeneity of the constraints,an equilibrium point may not exist and is presumably to be a dissensus point when it *** investigate the existence of equilibrium points from the perspective of Kakutani's fixed point theory for a set-valued *** also prove the local/global stability of certain equilibrium ***,a special case that the constraints are homogeneous is taken into *** constrains are assumed to take interval forms with nonempty *** is proved that consensus can be achieved globally and asymptotically for this *** examples are designed to illustrate our theoretical findings.

关键词： Multi-agent systems heterogeneous constraints equilibrium point and its stability constrained consensus

来源：评论

学校读者我要写书评

暂无评论

Reinforcement learning-enhanced dynamic multi-objective evolutionary algorithm for cooperative shovel scheduling in open-pit mining

Reinforcement learning-enhanced dynamic multi-objective evol...

引用

2024 China Automation Congress, CAC 2024

作者： Zhang, Zihao Li, Changhe Yang, Shengxiang School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan430074 China School of Artificial Intelligence Anhui University of Science & Technology Hefei232001 China School of Computer Science and Informatics De Montfort University Leicester United Kingdom

ISBN: (纸本)9798350368604

Aiming at the ore blending problem in the open-pit mining scenario, the optimization objective is to minimize the grade variance of the sliding window of the ore flow, and a cooperative shovel scheduling model for real-time ore blending is established. A reinforcement learning-enhanced dynamic multi- objective evolutionary algorithm is proposed, where a Q-learning operator selection mechanism is introduced to reuse the information from the previous environment for tracking the optimal solution in the dynamic environment. Experimental results show that the proposed method can effectively control the grade fluctuation of the ore flow and dynamically respond to external events, and can find a better solution in real time compared with the traditional operator selection algorithm. © 2024 IEEE.

关键词： Open pit mining

来源：评论

学校读者我要写书评

暂无评论

Video Corpus Moment Retrieval with Query-specific Context Learning and Progressive Localization

引用

IEEE Transactions on Circuits and Systems for Video technology 2025年

作者： Zhang, Long Song, Peipei Duan, Zhangling Wang, Shuo Chang, Xiaojun Yang, Xun School of Information Science and Technology Hefei230026 China Hefei Comprehensive National Science Center Institute of Artificial Intelligence Hefei230026 China University of Science and Technology of China School of Information Science and Technology Hefei230026 China Department of Computer Vision Abu Dhabi United Arab Emirates University of Science and Technology of China MoE Key Laboratory of Brain-inspired Intelligent Perception and Cognition China

Video corpus moment retrieval (VCMR) aims to retrieve a moment from a large corpus of untrimmed videos corresponding to a given language query. However, existing methods often fall short due to their reliance on simple cross-modal attention mechanisms and one-stop localization, which fail to handle the complex multimodal information and large search space effectively. To address these challenges, we propose a novel VCMR method with Query-specific Context Learning and Progressive Localization (QCLPL). First, we construct query-specific multimodal contexts that capture complementary and consistent semantics across subtitles and frames, ensuring informative and efficient context building. We further introduce a semantic contrastive loss to refine these multimodal contexts, filtering out query-irrelevant information. Additionally, we introduce a progressive localization strategy that transforms the moment localization task into a two-stage process. By classifying frames into foreground and background regions, we present a simplified binary classification problem before boundary prediction, constrained by a region-aware loss. This progressive approach leverages region priors to improve subsequent moment localization. Extensive experiments on the TVR and DiDeMo datasets demonstrate that our method significantly outperforms existing approaches, setting a new state of the art for VCMR. © 1991-2012 IEEE.

关键词： Structured Query Language

来源：评论

学校读者我要写书评

暂无评论

Chinese Text Classification Using BERT and Flat-Lattice Transformer 11th

Chinese Text Classification Using BERT and Flat-Lattice Tran...

引用

11th International Conference on Artificial intelligence and Mobile Services, AIMS 2022 held as Part of the Services Conference Federation, SCF 2022

作者： Lv, Haifeng Ning, Yishuang Ning, Ke Ji, Xiaoyu He, Sheng Guangxi Key Laboratory of Machine Vision and Intelligent Control WuZhou University Wuzhou China Kingdee Research Kingdee International Software Group Company Limited Shenzhen China Guangxi Colleges and Universities Key Laboratory of Industry Software Technology Wuzhou University Wuzhou543002 China

ISBN: (纸本)9783031235030

Recently, large scale pre-trained language models such as BERT and models with lattice structure that consisting of character-level and word-level information have achieved state-of-the-art performance in most downstream natural language processing (NLP) tasks, including named entity recognition (NER), English text classification and sentiment analysis. For Chinese text classification, the existing methods have also tried such kinds of models. However, they cannot obtain the desired results since these pre-trained models are based on characters, which cannot be applied for Chinese language that is based on words. To address this problem, in this paper, we propose BFLAT which a simple but efficient model for Chinese text classification. Specifically, BFLAT utilizes BERT and word2vec to learn character-level and word-level vector representations, and then adopts the flat-lattice transformer to integrate both of the two-level vector representations. Experimental results on two datasets demonstrate that our proposed method outperforms the baseline methods over 1.38–21.82% and 3.42–20.7% in terms of relative F1-measure on two Chinese text classification benchmarks, respectively. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

A distributed fixed-time optimal consensus algorithm over second-order multi-agent systems

A distributed fixed-time optimal consensus algorithm over se...

引用

Fully Actuated System Theory and Applications (CFASTA), Conference on

作者： Xiasheng Shi Tianju Sui The School of Artificial Intelligence Anhui University Hefei China Key Laboratory of Intelligent Control and Optimization for Industrial Equipment (Dalian University of Technology) Ministry of Education Dalian China

ISBN: (数字)9798350373691

ISBN: (纸本)9798350373707

With the rapid development of artificial intelligence technology and communication technology, the distributed optimization problem for distributed second-order multi-agent systems has received extensive attention. In this paper, a specified time convergence optimization algorithm is designed for the distributed optimization problem of multi-agent systems under undirected networks. Firstly, the sliding mode theory is used to achieve fixed-time convergence of the agent speed to the target value, transforming the second-order agent-distributed optimization problem into a first-order agent-distributed optimization problem. Secondly, with the help of the sliding mode theory, the agent realizes that the gradient sum is zero at a fixed time. Then, this paper uses the second derivative information of the cost function to design an initialization-free fixed-time convergent algorithm. Finally, the effectiveness of the algorithm designed in this paper is illustrated by case simulation.

关键词： Consensus algorithm Cost function Communications technology Artificial intelligence Multi-agent systems Convergence

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：