检索结果-内蒙古大学图书馆

Uncertainty-Guided Diffusion Model for Camouflaged Object Detection

IEEE Transactions on Multimedia 2025年

作者： Yang, Jinsheng Zhong, Bineng Liang, Qihua Mo, Zhiyi Zhang, Shengping Song, Shuxiang Guangxi Normal University Key Lab of Education Blockchain and Intelligent Technology Ministry of Education Guilin541004 China Guangxi Normal University Guangxi Key Lab of Multi-Source Information Mining & Security China Wuzhou University Guangxi Key Laboratory of Machine Vision and Intelligent Control Wuzhou543002 China Harbin Institute of Technology School of Computer Science and Technology Weihai264209 China

Recently, diffusion models have significantly improved the performance of Camouflaged Object Detection (COD) by adding noise to a mask and iteratively denoising it to match the target distributions. Due to the direct extraction of features from noisy masks and the lack of conditional constraints on a prediction area, the diffusion model may deviate from a correct prediction range and produces mispredictions in regions with high uncertainty. To address this issue, we propose an uncertainty-guided diffusion model (UGDNet) for COD, which explicitly quantifies uncertainty and integrates it as an anchor condition into the diffusion models to provide an initialization of the diffusion regions. The core idea is first to utilize a probability representation and transformer to explicitly model uncertainty, aiming to identify areas where a model may generate overconfident mispredictions. Then, we use the uncertainty as an anchor condition to provide a reference prediction range for the diffusion model, guiding each step of the diffusion process. Furthermore, we use uncertainty to guide feature aggregation, prompting the model to pay extra attention to the semantic features of regions with high uncertainty to refine the segmentation results further. The experimental results indicate that our proposed UGDNet achieves higher accuracy than existing state-of-the-art models on five COD benchmarks, including COD10K, NC4K, CAMO, CHAMELEON, and CDS2K. © 1999-2012 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

SIEVL-Track: Exploring Semantic Information Enhancement for Visual-Language Object Tracking

引用

IEEE Transactions on Circuits and Systems for Video technology 2025年

作者： Li, Ning Zhong, Bineng Liang, Qihua Mo, Zhiyi Nong, Jian Song, Shuxiang Ministry of Education Guangxi Normal University Key Laboratory of Education Blockchain and Intelligent Technology Guilin541004 China Guangxi Normal University Guangxi Key Lab of Multi-Source Information Mining and Security Guilin541004 China Wuzhou University Guangxi Key Laboratory of Machine Vision and Intelligent Control Wuzhou543002 China

With the assistance of language descriptions, Visual-Language (VL) object tracking can obtain more accurate semantic information compared to traditional Visual-Only object tracking. However, the ability of current VL trackers to obtain target semantic information has not been fully developed due to limitations such as wasted modeling capabilities and insufficient utilization of historical temporal information. On the one hand, the modeling output from Transformer shallow encoders often does not directly participate in the prediction of tracking results, resulting in a certain degree of model capability waste. On the other hand, the semantic information of historical tracking results has also not been fully utilized in the tracking process, resulting in a certain degree of lack of semantic assistance capability. Therefore, we propose a novel hierarchical multi-stage VL tracker called SIEVL-Track to enhance target semantic information. Specifically, we first design a multi-stage visual language tracking framework for modeling multi-scale semantic information in Visual-Language tracking pipeline. Secondly, we propose a selective deep and shallow semantic information fusion module (S-DSFM) that explicitly integrates shallow output features into deep output features, so to reduce the waste of modeling capabilities and obtain more high-frequency semantic information related to the target. Finally, we design a temporal cue modeling module based on linguistic classification and multi-frame historical information(MHLS-TCM), with the aim of more comprehensive utilization of historical temporal semantic information. Benefit from the above designs, our VL tracker can obtain stronger target semantic information. Competitive performance from extensive experimental results on five popular vision-language tracking benchmarks, including LaSOT, OTB99-Lang, WebUAV-3M, LaSOText and TNL2K, have demonstrated the superiority and effectiveness of our SIEVL-Track. © 1991-2012 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Design and implement of wireless measure and control system for greenhouse

Design and implement of wireless measure and control system ...

引用

作者： Du, Xiaodong Wang, Jun Ji, Ping Gan, Kaifeng Key Lab of Machine Vision and Intelligence Control Technology Hefei University Hefei 230601 China

ISBN: (纸本)9789881725592

With the rapid development of computer technology, MEMS technology, network technology, and so on, sensors are becoming miniaturization, intelligence, and integration, and has bring out a new networkWireless Sensor Networks(WSN). Based on the existent CAN-bus measure and control system which can achieve automatic measure and control of the greenhouse environment and nutrient solution in our lab, this paper studies wireless sensor networks, mainly including multifunctional wireless sensor nodes, wireless control nodes, main node, and system integration demonstration. We design and study the wireless sensor networks node's hardware platform deeply, consider low-power characteristics in node hardware and software design, analyze the consumption of the node generally and give out the corresponding energy-saving strategies supplied with solar power and battery, and compose star networks. The results of the experiment in the greenhouse environment show that the wireless sensor network will bring a lot of convenience for the greenhouse environment monitoring and control. © 2011 Chinese Assoc of Automati.

关键词： Solar energy

来源：评论

学校读者我要写书评

暂无评论

Maximal η-clique maintenance over uncertain graph streams

引用

Information Sciences 2025年 717卷

作者： Ma, Ziyi Wang, Liqing Yang, Jianye Zhou, Xu Li, Kenli Gao, Cuiyun School of Artificial Intelligence Hebei University of Technology Tianjin300401 China Chinacoal Beijing Coal Mining Machinery Co. Ltd. Beijing102400 China Guangxi Key Laboratory of Machine Vision and Intelligent Control Wuzhou University Wuzhou543002 China Department of New Networks PengCheng Laboratory Shenzhen518055 China Cyberspace Institute of Advanced Technology Guangzhou University Guangzhou510006 China College of Computer Science and Electronic Engineering Hunan University Changsha410082 China Shenzhen518055 China

Maximal clique enumeration is a critical task for analyzing graph data and has a wide range of applications, such as community detection, protein complex identification, and group recommendation. Although many efficient algorithms have been proposed, most of them are designed for static or deterministic graphs. However, in many real-life applications, graphs are often highly dynamic and nondeterministic. In this paper, we study the problem of maximal η-clique maintenance (shorted as MCM) over uncertain graph streams. Given an uncertain graph G and a probability threshold η, MCM reports all incremental η-cliques in G for each update edge of G. To the best of our knowledge, we are the first to systematically study this problem. We first develop a local pivot-based enumeration technique that utilizes the pivot priority of candidates to achieve effective pruning during the maximal η-clique enumeration procedure. Based on the technique, we propose a competitive baseline approach LPMCM, which finds newly generated maximal η-cliques and internal maximal η-cliques. Although LPMCM avoids repeated enumeration of the same maximal η-cliques, it still requires expensive costs in terms of η-clique maximality determination. To further enhance maintenance efficiency, we introduce an approach HLPMCM using the hash-based maximality determination technique and an improved internal maximal η-clique enumeration technique. Extensive experiments show that HLPMCM can achieve 1.1x-19.0x speedup over the competitors and consumes slightly more memory. © 2025 Elsevier Inc.

关键词： Maintenance

来源：评论

学校读者我要写书评

暂无评论

Adaptive inverse optimal control for a class of nonlinear system

Adaptive inverse optimal control for a class of nonlinear sy...

引用

作者： Wang, Jun Ji, Ping Chu, Zhong Liu, Wei Key Lab of Machine Vision and Intelligence Control Technology Hefei University Hefei 230601 China

ISBN: (纸本)9789881725592

This paper introduces the basic idea of adaptive inverse optimal control, gives the solvable theorem of inverse optimal gain assignment problem, design inverse optimal controller using Backstepping algorithm and an adaptive update law for strict-feedback nonlinear continuous system with unknown time-varing bounded disturbance and constant unknown parameters, which is nonlinear, continuous and easier to realize. The adaptive control law and the parameter update laws can be obtained at the same time by this design scheme. The results designed show simultaneously that inverse optimal systems yield stability margins, namely, achieving locally robustness, which is a nonlinear analog of Kalman's margins for the linear quadratic regulator. © 2011 Chinese Assoc of Automati.

关键词： Adaptive control systems

来源：评论

学校读者我要写书评

暂无评论

Theoretical investigation of noble metal (Rh- and Pd-) doped Janus ZrSSe monolayer application for XLPE decomposition gas detection

引用

Environmental Research 2025年 282卷 122034页

作者： Liang Cao Hailong Wu Hao Cui College of Engineering and Technology Southwest University Chongqing 400715 China Guangxi Key Laboratory of Machine Vision and Intelligent Control Wuzhou University Wuzhou 543002 China College of Artificial Intelligence Southwest University Chongqing 400715 China

This study involves a first-principles theory-based investigation of the adsorption performance of Rh- and Pd-doped Janus ZrSSe (Rh- and Pd-ZrSSe) monolayers toward four cross-linked polyethylene (XLPE) decomposition gases (HCHO, C 2 H 4 , C 3 H 6 O, and C 6 H 6 ) for application in power cable condition assessment via advanced gas sensors. Herein, the doping characteristics of Rh and Pd in ZrSSe were investigated, followed by a detailed analysis of their gas adsorption behavior. Specifically, adsorption energy, charge transfer, and adsorption distance were evaluated to analyze geometric interactions, while charge density difference, band structure, and orbital density of states were investigated and compared to elucidate the electronic properties of the two monolayers upon gas adsorption. Furthermore, both resistive-type and Schottky diode-based sensing mechanisms were explored to evaluate multi-gas discrimination selectivity; resultantly, a superior resistive response of the Rh-ZrSSe monolayer over that of the Pd-ZrSSe one was revealed, as well as the sensitivity and selectivity of the Schottky diode gas sensor based on the combination of the two doped monolayers. These results highlight not only the promising potential of Janus transition-metal dichalcogenides, particularly ZrSSe monolayers, for XLPE decomposition gas detection, but also the critical role of dopant selection in surface decoration for effective gas detection.

关键词： First-principles theory Rh and Pd atoms XLPE ZrSSe monolayer gas sensors

来源：评论

学校读者我要写书评

暂无评论

Research and design of mobile robot moving object tracking system on hierarchical control

Research and design of mobile robot moving object tracking s...

引用

2010 International Conference on Computer Application and System Modeling, ICCASM 2010

作者： Liuwei Tanmin Wang, Lian-Ping Zhang, Chongwei Wangjun School of Electrical Engineering and Automation Hefei University of Technology Hefei China Hefei University Key Laboratory of Machine Vision and Intelligence Control Technology Hefei China

ISBN: (纸本)9781424472369

A intelligent control model structure of double-level- three-stage is presented to deal with the moving robot detecting and tracking system. According to basic ideas of imitation of human intelligence control, it includes Decision-making level and Execution level, each level is decomposed into 3 stages. In the process of tracking, the moving objects state forecast and two-step increment tracking algorithm based on Kalman filter are adopted to drive the mobile robot quickly and smoothly. The robot system to detect and track moving objects with the model structure is designed and its application in automobile stake is illustrated. © 2010 IEEE.

关键词： Kalman filters

来源：评论

学校读者我要写书评

暂无评论

Parameter-Free Shifted Laplacian Reconstruction for Multiple Kernel Clustering

引用

IEEE/CAA Journal of Automatica Sinica 2024年第4期11卷 1072-1074页

作者： Xi Wu Zhenwen Ren F.Richard Yu the School of National Defence Science and Technology Southwest University of Science and TechnologyMianyang 621010China the School of National Defence Science and Technology Southwest University of Science and TechnologyMianyang 621010 the Guangxi Key Laboratory of Machine Vision and Intelligent Control Wuzhou UniversityWuzhou 543002 the Guangdong Laboratory of Artificial Intelligence and Digital Economy(SZ) Shenzhen 518060China

Dear Editor,This letter proposes a parameter-free multiple kernel clustering(MKC)method by using shifted Laplacian *** MKC can effectively cluster nonlinear data,but it faces two main challenges:1)As an unsupervised method,it is up against parameter problems which makes the parameters intractable to tune and is unfeasible in real-life applications;2)Only considers the clustering information,but ignores the interference of noise within Laplacian.

关键词： parameter letter Parameter

来源：评论

学校读者我要写书评

暂无评论

Robust stabilization for uncertain singular Markovian jump systems

Robust stabilization for uncertain singular Markovian jump s...

引用

作者： Li, Yafeng Kang, Yu Hu, Yong Wang, Jun Department of Automation University of Science and Technology of China Hefei 230026 China Key Lab. of Machine Vision and Intelligence Control Technology Hefei University Hefei Anhui 230601 China

ISBN: (纸本)9787894631046

In this paper, the problems of robust stability and stabilization for singular Markovian jump systems with uncertainties are considered. In the system, the uncertainties are unknown time-varying but norm bounded. The system is transformed into an equivalent one by premultiplying and postmultiplying matrices. Sufficient conditions are given and the controllers are designed such that the system is regular, impulse-free and stochastically stable in mean square sense for the uncertainty. Finally, numerical examples are given to demonstrate the effectiveness of the proposed methods.

关键词： Stabilization

来源：评论

学校读者我要写书评

暂无评论

Multiple feature sample classification via joint sparse representation

引用

Journal of Computational Information Systems 2015年第14期11卷 5125-5133页

作者： Zha, Changjun Xu, Tailong Key Laboratory of Machine Vision and Intelligence Control Technology Hefei University Hefei China

Based on the characteristics of wireless monitoring networks and profiling sensors, we present a method of acquiring the profile of moving objects. First, principal component analysis is used to extract profile sample features, and then a sink node collects all of the nodes' sample features to give a signal fusion model. This model enables a novel algorithm to be proposed that identifies test signals containing multiple sample features. Using profile feature information, the algorithm constructs a dictionary from which test samples can be sparsely represented. Then, according to the error in the sparse reconstruction, the algorithm identifies the class of profile samples acquired by the monitoring node. Unlike traditional classification algorithms, which rely on single feature samples, our approach can identify test samples consisting of multiple sample features. A numerical simulation and experimental results demonstrate that the proposed algorithm is superior to traditional methods. ©, 2015, Journal of Computational Information Systems. All right reserved.

关键词： Classification (of information)

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：