检索结果-内蒙古大学图书馆

2025 IEEE International Conference on Acoustics, Speech, and signal processing, ICASSP 2025

作者： Wang, Xiao Fu, Yongsheng Wang, Wei Liu, Wei 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 China

ISBN: (纸本)9798350368741

Underwater image enhancement (UIE) focuses on mitigating image quality degradation due to light absorption and scattering. However, most existing methods enhance images via a global and uniform manner, neglecting the inherent semantic information in different regions, which may cause the network to easily deviate from the region's original color. Moreover, these methods typically rely on clear images to guide network convergence, a process constrained by the limited availability of real-world datasets, making it extremely challenging to train enhancement models for various degradations. To address these challenges, this paper introduces a semantic guidance and region contrastive constraints network (SRCNet). Initially, we propose a semantic-aware RWKV (Receptance Weighted key Value) block and a semantic prompt regularization module. These components leverage intra-target semantic correlations to preserve image details and colors within a global perceptual framework, while employing focal loss to emphasize the restoration of severely degraded regions. Subsequently, we introduce a region contrastive learning method that effectively utilizes negative samples to precisely capture features sensitive to degradation factors, thereby fostering robust feature distributions. Finally, experimental results demonstrate that our method outperforms existing state-of-the-art (SOTA) approaches. © 2025 IEEE.

关键词： contrastive learning rwkv semantic prompt Underwater image enhancement

来源：评论

学校读者我要写书评

暂无评论

Dual-notch Ultra-wideband Bandpass Filter Based On Folded Dual-mode Resonator

Dual-notch Ultra-wideband Bandpass Filter Based On Folded Du...

引用

2022 International Applied Computational Electromagnetics Society Symposium, ACES-China 2022

作者： Li, Qingqing Wu, Xianliang Huang, Zhixiang Anhui University Hefei230601 China Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Hefei230601 China

ISBN: (纸本)9781665452366

Aiming at the problem that ultra-wideband systems are easily interfered by narrowband signals, In this paper, a novel ultra-wideband (UWB) bandpass filter with dual-notch characteristics. This filter is mainly composed of Composition of a multimode resonator (MMR)and a folded dual-mode step-impedance resonator. Paralleling T-shaped SIR stubs in the basic MMR structure realizes the introduction of transmission zeros within the passband. At the same time, a pair of high-impedance stubs are also loaded to extend the upper stopband of the filter, and a folded dual-mode stepped impedance resonator is coupled below the filter to generate dual-notch frequencies. Through the electromagnetic simulation software HFSS for simulation optimization, the simulation results show that the passband of the filter is 3.4211.21GHz and its notch frequencies are 8.8GHz and 9.5GHz respectively. Insertion loss below 0.5dB and stopband up to 20GHz (S21 © 2022 IEEE.

关键词： Electromagnetic simulation

来源：评论

学校读者我要写书评

暂无评论

Determination of Continuous Dielectric Properties of Clothing Materials Using Hybrid Method

Determination of Continuous Dielectric Properties of Clothin...

引用

2023 IEEE International Workshop on Electromagnetics: Applications and Student Innovation Competition, iWEM 2023

作者： Chen, Manni Chung, Kwok L. Huang, Zhining Wen, Jiating Li, Yingsong Huizhou University School of Computer Science and Engineering Guangdong516007 China Huizhou University Glorious Sun Guangdong School of Fashion Guangdong516007 China Ministry of Education Anhui University Key Laboratory of Intelligent Computing and Signal Processing China

ISBN: (纸本)9798350336740

This paper presents a hybrid method for determination of continuous dielectric properties of clothing materials. The dielectric constant and loss tangent of three types of materials are firstly investigated using open-ended coaxial probe from 0.5 to 20 GHz. The average measured values are input into the CST simulation of two CPW lines to obtain the two-port S-parameters. Finally, more reasonable yet reliable results are obtained by using two retrieval algorithms (TRACE and ABCD) for validation and comparative purposes. © 2023 IEEE.

关键词： Dielectric properties

来源：评论

学校读者我要写书评

暂无评论

Point Pattern Matching Based on Spectra of Directed Graphs

引用

Chinese Journal of Electronics 2023年第4期20卷 662-666页

作者： LIANG Dong ZHU Ming FAN Yizheng YAN Pu Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Anhui University Hefei China

We present a novel algorithm for point pattern matching by means of spectra of directed graphs. Given a feature point-set, we construct a weighted directed graph and skew-symmetric matrix associated with the graph. By using spectral decomposition of the matrix, we give a spectral representation of the feature points with half of the eigenvectors. We theoretically analyze that our method can well deal with the matching problem under affine transformation. The expreiments applied to synthetic data and real-world images show the effectiveness of our method.

关键词： Technological innovation Directed graphs Medical services Matrix decomposition Pattern matching Synthetic data

来源：评论

学校读者我要写书评

暂无评论

Mixture of experts for audio-visual learning 24

Mixture of experts for audio-visual learning

引用

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

作者： Ying Cheng Yang Li Junjie He Rui Feng School of Computer Science Fudan University and Shanghai Key Laboratory of Intelligent Information Processing and Shanghai Collaborative Innovation Center of Intelligent Visual Computing School of Computer Science Fudan University and Shanghai Key Laboratory of Intelligent Information Processing

ISBN: (纸本)9798331314385

With the rapid development of multimedia technology, audio-visual learning has emerged as a promising research topic within the field of multimodal analysis. In this paper, we explore parameter-efficient transfer learning for audio-visual learning and propose the Audio-Visual Mixture of Experts (AVMoE) to inject adapters into pre-trained models flexibly. Specifically, we introduce unimodal and cross-modal adapters as multiple experts to specialize in intra-modal and intermodal information, respectively, and employ a lightweight router to dynamically allocate the weights of each expert according to the specific demands of each task. Extensive experiments demonstrate that our proposed approach AVMoE achieves superior performance across multiple audio-visual tasks, including AVE, AVVP, AVS, and AVQA. Furthermore, visual-only experimental results also indicate that our approach can tackle challenging scenes where modality information is missing. The source code is available at https://***/yingchengy/AVMOE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Gene Expression Data Classification Using Laplacian Eigenmap Based on Improved Maximum Margin Criterion

引用

Chinese Journal of Electronics 2023年第3期22卷 521-524页

作者： WANG Nian WANG Junsheng GE Fang Education Ministry Key Laboratory of Intelligent Computing and Signal Processing Anhui University Hefei China

To deal with the insufficiency problem of Laplacian eigenmap (LE) method and Maximum margin criterion (MMC) method in feature extraction, a new dimensionality reduction method called Laplacian eigenmap based on Improved maximum margin criterion (LE/IMMC) is proposed with applications in gene expression data classification. The LE/IMMC intends to constrain similar data points as close to each other as possible and maximize the margin regions between different pattern classes simultaneously. The proposed LE/IMMC by introducing IMMC into the cost function of LE retains the characteristic of local neighborhood relationship of LE. Meanwhile, it emphasizes the discriminative information by incorporating IMMC, which can maximize the between-class scatter and minimize the within-class scatter. Gene expression data classification experiments on four public datasets demonstrate our method is effective for feature extraction,

关键词： Laplace equations Education Medical services Feature extraction Cost function Manifold learning Gene expression

来源：评论

学校读者我要写书评

暂无评论

"study on the Grammatical Function of "la dhon"as Function Words in the Tibetan Language processing" 6

"study on the Grammatical Function of "la dhon"as Function W...

引用

6th International Conference on Machine Learning and Natural Language processing, MLNLP 2023

作者： Suonan, Cairang Gongque, Duojie Computer College of Qinghai Normal University Qinghai Xining810016 China Key Laboratory of Tibetan Information Processing Ministry of Education Qinghai Xining810008 China Tibetan Intelligent Information Processing and Machine Translation Key Laboratory Qinghai Xining810008 China

ISBN: (纸本)9798400709241

The study of Tibetan function words is an indispensable basic work in Tibetan natural language processing and has a wide range of practical application value. It is the core of Tibetan information processing and the basis of Tibetan natural language understanding, and has wide application prospects in Tibetan proofreading, information retrieval, bilingual translation, automatic classification and other technologies. On the basis of previous studies, this paper discusses the grammatical functions of Tibetan function words la dhon from the perspective of information processing, classification system and formal description of unfree function words, focuses on the grammatical functions of Tibetan function words la dhon, and puts forward the preliminary conception and processing methods of Tibetan function words. © 2023 ACM.

关键词： Natural language processing systems

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

Heterogeneous Domain Adaptation via Correlative and Discriminative Feature Learning

引用

IEEE Transactions on Multimedia 2025年 27卷 3447-3461页

作者： Lu, Yuwu Lin, Dewei Shen, Linlin Zhou, Yicong Pan, Jiahui South China Normal University School of Artificial Intelligence Foshan528225 China Shenzhen University College of Computer Science and Software Engineering Shenzhen518055 China Shenzhen University Guangdong Key Laboratory of Intelligent Information Processing Shenzhen518060 China University of Nottingham Ningbo China Department of Computer Science Ningbo315100 China University of Macau Department of Computer and Information Science China

Heterogeneous domain adaptation seeks to learn an effective classifier or regression model for unlabeled target samples by using the well-labeled source samples but residing in different feature spaces and lying different distributions. Most recent works have concentrated on learning domain-invariant feature representations to minimize the distribution divergence via target pseudo-labels. However, two critical issues need to be further explored: 1) new feature representations should be not only domain-invariant but also category-correlative and discriminative, and 2) alleviating the negative transfer caused by the incorrect pseudo-labeling target samples could boost the adaptation performance during the iterative learning process. To address these issues, in this paper, we put forward a novel heterogeneous domain adaptation method to learn category-correlative and discriminative representations, referred to as correlative and discriminative feature learning (CDFL). Specifically, CDFL aims to learn a feature space where class-specific feature correlations between the source and target domains are maximized, the divergences of marginal and conditional distribution between the source and target domains are minimized, and the distances of inter-class distribution are forced to be maximized to ensure the discriminative ability. Meanwhile, a selective pseudo-labeling procedure based on the correlation coefficient and classifier prediction is introduced to boost class-specific feature correlation and discriminative distribution alignment in an iteration way. Extensive experiments certify that CDFL outperforms the state-of-the-art algorithms on five standard benchmarks. © 1999-2012 IEEE.

关键词： Contrastive Learning

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

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：