检索结果-内蒙古大学图书馆

27th International Conference on pattern recognition, ICPR 2024

作者： Hu, Quan Chen, Li Feng, Zhida Chen, Yaojie School of Computer Science and Technology Wuhan University of Science and Technology Wuhan China Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System Wuhan University of Science and Technology Wuhan China

ISBN: (纸本)9783031781124

A growing body of research indicates that employing large models for adaptation to downstream tasks often yields remarkable performance. However, in the domain of ship detection, the potential of these large models is frequently underutilized due to domain shift issues. This paper introduces the Cross-Modal Ship Grounding (CSG) model, which leverages an efficient Cross-Modal Adapter (CMA) technology to transfer the general detection capabilities of large models to ship images, addressing domain shift with minimal training costs. To mitigate the challenges posed by complex and variable background interference, the Water-Land Separation (WLS) module is proposed to focus specifically on the water area. This module effectively addresses the issue of background target interference, thereby enhancing the model’s accuracy in complex scenes. Empirical evaluations on both private and public datasets demonstrate that the CSG model surpasses all state-of-the-art models in performance. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Feature Selection Based on 3-D Feature Decision Graph for High-dimensional Data 5

Unsupervised Feature Selection Based on 3-D Feature Decision...

引用

5th International Conference on Algorithms, Computing and Artificial Intelligence, ACAI 2022

作者： Jia, Hong Weng, Yubin Guangdong Key Laboratory of Intelligent Information Processing China and College of Electronics and Information Engineering Shenzhen University Shenzhen China

ISBN: (纸本)9781450398343

Feature selection is aimed at reducing the dimensionality of data sets and obtaining a feature subset with better performance for the target learner. Unsupervised feature selection is more challenging because of the lack of label information. In this paper, the idea of decision graph is applied to unsupervised feature selection. Specifically, a 3-D decision graph model of features is proposed to reveal the characteristics of each feature and the relationship between them. Then, a movable hyperplane is constructed to select specified number of features from the original feature space to form the final feature subset. Experiments in comparison with both traditional and novel algorithms on benchmark data sets reveal that the proposed method is able to select feature subset with both of lower redundancy and higher performance. © 2022 ACM.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Topological phases in photonic microring lattices with projective symmetry

引用

Physical Review A 2024年第1期109卷 013516-013516页

作者： Yang Liu Chuang Jiang Wanting Wen Yiling Song Xiaohong Li Peixiang Lu Shaolin Ke Hubei Key Laboratory of Optical Information and Pattern Recognition Wuhan Institute of Technology Wuhan 430205 China Department of Physics Wenzhou University Zhejiang 325035 China Guangdong Intelligent Robotics Institute Dongguan 523808 China

Symmetry plays a key role in classifying topological phases, which can be enriched by the projective symmetry group in the presence of artificial gauge fields (AGFs). Here, we utilize two-dimensional (2D) photonic microring lattices to create three different topological states based on projective symmetry. By engineering link rings, we are able to flexibly manipulate the AGFs and coupling magnitude. As each plaquette carries a π flux, the two translation symmetries of a rectangle microring lattice are projectively represented. By applying different types of dimerization, we tune the spatial space to break translation symmetry and achieve a Möbius topological insulator with twisted edge bands and a graphenelike topological semimetal with flat bands, which we reflect by unique excitation spectra and field distributions. Additionally, by changing the configuration of gauge flux, the mirror and translation operators become anticommutative, leading to the fractal translation of the Brillouin zone. As a result, the band structure of topological edge modes experiences twice the period in momentum space. All results are confirmed by full-wave simulation. Our study has the potential to construct unprecedented photonic topological insulators benefiting from gauge fields.

关键词： Nanophotonics Photonics Topological effects in photonic systems Optical microcavities

来源：评论

学校读者我要写书评

暂无评论

Tokenizing Features for Fast Video Object Segmentation

Tokenizing Features for Fast Video Object Segmentation

引用

2022 IEEE International Conference on Multimedia and Expo, ICME 2022

作者： Meng, Tianfang Zhang, Wei Zhang, Wenqiang Fudan University Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Shanghai China

ISBN: (数字)9781665485630

ISBN: (纸本)9781665485630

This paper investigates how to take full advantage of the tem-poral and spatial information in videos with minimal compu-tational cost in the semi-supervised video object segmentation (VOS) task. Current state-of-the-art methods have achieved remarkable performance by matching features of the current frame with those of past frames to propagate the past segmen-tation masks to the current. However, the inference speeds of such matching-based methods are limited due to the tremen-dous amount of computation on pixel-to-pixel matching. To address this problem, we propose a fast matching mechanism for VOS that extracts essential object information as a handful of token vectors for matching. By extracting succinct but suf-ficient information from the pixel-wise features, we develop a fast VOS model which achieves competitive segmentation performance (81.6% J & F on DAVIS-2017), maintaining a high inference speed (FPS = 42.1). © 2022 IEEE.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Promoting Students' Programming Skills in Constructions for Teaching Materials and Curriculums: Experiments for Comprehensive Application of Programming Methods

Promoting Students' Programming Skills in Constructions for ...

引用

2022 Global Conference on Robotics, Artificial Intelligence and information Technology, GCRAIT 2022

作者： Wu, Yonghui School of Computer Science Fudan University Shanghai Key Laboratory of Intelligent Information Processing Shanghai China

ISBN: (数字)9781665481922

ISBN: (纸本)9781665481922

The goal for experiments for programming languages is to polish students' programming skills solving problems by programming languages. Programming contests are contests solving problems by programming. A programming language experiment based on 'solving problems by programming' consists of the related knowledge background for programming languages and methods, programming contest problems and their analysis and solutions. The paper specifies experiments for programming languages based on 'solving problems by programming': the comprehensive application of programming methods. These experiments enlighten students to solve a problem by programming through comprehensively applying programming methods: offline method, binary search, and real precision processing. © 2022 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Random Fourier Features Based Kernel Risk Sensitive Loss Algorithm with Adaptive Moment Estimation Optimization Technology 22

Random Fourier Features Based Kernel Risk Sensitive Loss Alg...

引用

6th International Conference on Digital Signal processing, ICDSP 2022

作者： Wang, Daili Zheng, Yunfei Cai, Peng Liu, Qiang Shen, Minglin Wang, Shiyuan Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing College of Electronic and Information Engineering Southwest University China

ISBN: (纸本)9781450395809

Random Fourier features based kernel risk sensitive loss (RFFKRSL) is a popular nonlinear adaptive filtering algorithm developed in the random Fourier features space. The most attractive feature of such algorithm is that it would not cause the issue of linearly increasing network structure like the well-known kernel adaptive filtering algorithms, while having the ability to curb the negative influence induced by non-Gaussian noises. The stochastic gradient descent (SGD) method, however, is a default choice to determine the filtering coefficients of RFFKRSL, which can result in an undesirable convergence performance of the algorithm in many cases. To address this issue, two alternative optimization technologies, including adaptive moment estimation (Adam) and its extended version, i. e., Nesterov-accelerated Adam (Nadam), have been adopted to re-derive RFFKRSL. For simplicity, the proposed two algorithms are named as RFFKRSL with Adam (AdamRFFKRSL) and RFFKRSL with Nadam (NadamRFFKRSL), respectively. Although Adam and Nadam are common to deep neural network based learning methods, their applications to adaptive filtering are seldom to be seen, and the combination of them with RFFKRSL may open a new way to design nonlinear adaptive filtering algorithms that have been built with SGD method. Simulations on two time series prediction tasks are reported to demonstrate the desirable performance of the proposed algorithms. © 2022 ACM.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

An Improved Method for Approximating the Infinite-Horizon Value Function of the Discrete-Time Switched LQR Problem

引用

Journal of Systems Science & Complexity 2024年第1期37卷 22-39页

作者： HOU Tan LI Yuanlong LIN Zongli Department of Automation Shanghai Jiao Tong UniversityShanghai 200240China Key Laboratory of System Control and Information Processing Ministry of Education of ChinaShanghai 200240China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai 200240China Charles L.Brown Department of Electrical and Computer Engineering University of VirginiaCharlottesvilleVA 22904-4743USA

This paper considers the problem of approximating the infinite-horizon value function of the discrete-time switched LQR *** particular,the authors propose a new value iteration method to generate a sequence of monotonically decreasing functions that converges exponentially to the value *** method facilitates us to use coarse approximations resulting from faster but less accurate algorithms for further value iteration,and thus,the proposed approach is capable of achieving a better approximation for a given computation time compared with the existing *** numerical examples are presented in this paper to illustrate the effectiveness of the proposed method.

关键词： Optimal control switched linear systems switched LQR problem.

来源：评论

学校读者我要写书评

暂无评论

Multi-view Graph Learning with Fuzzy Linear Discriminant Analysis 5

Multi-view Graph Learning with Fuzzy Linear Discriminant Ana...

引用

5th International Conference on Algorithms, Computing and Artificial Intelligence, ACAI 2022

作者： Jia, Hong Huang, Jian Guangdong Key Laboratory of Intelligent Information Processing China and College of Electronics and Information Engineering Shenzhen University Shenzhen China

ISBN: (纸本)9781450398343

The multi-view clustering method based on graph learning has been extensively studied because of its good clustering effect. However, most of the graph learning methods are based on the original data features, which often contain noise and outliers, and using them directly may lead to learning suboptimal graph. To address the above problems, we propose a multi-view graph learning method based on linear discriminant analysis. On the one hand, the manifold structure obtained using the global graph guides the learning of the discriminative projections for each view, and on the other hand, the common graph is learned using the projection data of each view. Then, an efficient solution is proposed by dividing the problem into two sub-problems. Finally, experiments are conducted on some public multi-view datasets to verify the effectiveness of the method. © 2022 ACM.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Ranking the Spreading Influence of Nodes in Complex Networks by Combining Local Average Weight and Average Normalized Link Entropy 4

Ranking the Spreading Influence of Nodes in Complex Networks...

引用

4th International Conference on Big Data, Artificial Intelligence and Internet of Things Engineering, ICBAIE 2023

作者： Fan, Kaiyu Yang, Fan Tu, Dexin Tang, Xinlai Mao, Xiuyong Guangxi University of Science and Technology School of Computer Science and Technology Liuzhou545006 China Guangxi University of Science and Technology Key Laboratory of Intelligent Information Processing and Graph Processing Liuzhou545006 China

ISBN: (纸本)9798350343618

Ranking the spreading influence of nodes is of great importance for controlling the spreading process on networks. Although a few measures are proposed for ranking nodes in weighted networks, it is still a challenge in accurately and efficiently ranking the spreading influence of nodes in weighted networks. In this paper, by utilizing both of the local and global topological structure information, a novel method is proposed. First, we define a local average weight (LAW) to describe the local topological structure information of nodes. Second, partly based on the link diversity, we define an average normalized link entropy (ANLE) to describe the global topological structure information of nodes. Further, by combining the LAW and ANLE, we propose a novel ranking measure termed as LAW-ANLE (LA) centrality. The proposed LA is verified by extensive experiments on a series of networks, and the results show that the LA is feasible and effective in accurately ranking the spreading influence of nodes. © 2023 IEEE.

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

FIMD: Fusion-Inspired Modality Distillation for Enhanced MRI Segmentation in Incomplete Multi-Modal Scenarios 24

FIMD: Fusion-Inspired Modality Distillation for Enhanced MRI...

引用

7th International Conference on Image and Graphics processing, ICIGP 2024

作者： Yang, Rui Wang, Xiao Xu, Xin Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System Wuhan University of Science and Technology China School of Computer Science and Technology Wuhan University of Science and Technology China Hubei Provincial Key Laboratory of Multimedia and Network Communication Engineering Wuhan China

ISBN: (纸本)9798400716720

Magnetic Resonance Imaging (MRI) is an invaluable tool for brain tumor segmentation. However, in clinical practice, certain modalities might be unavailable, leading to potential performance degradation in prediction tasks. According to current implementations, different modalities are treated as independent entities during the feature extraction phase, ignoring their inherent complementary nature. In this paper, inspired by knowledge distillation techniques, we introduce the Fusion-Inspired Modality Distillation (FIMD) framework. FIMD leverages the output from a fused multi-modal model as a teacher to guide the training of individual modalities. Each modality benefits from the collective knowledge of all modalities, enhancing its performance. Our FIMD method, devoid of specific architectural constraints, seamlessly integrates into existing multi-modal brain tumor segmentation frameworks. Notably, extensive experiments on BraTS2020, BraTS2018, and BraTS2015 datasets indicate that FIMD can enhance the performance of current state-of-the-art (SOTA) algorithms on Dice by an average of 0.55-1.60%. Especially in the case of missing modalities, the effectiveness of the FIMD framework in enhancing the robustness and accuracy of brain tumor segmentation is demonstrated. © 2024 ACM.

关键词： Semantic Segmentation

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：