检索结果-内蒙古大学图书馆

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Jianwen Gan Wenxin Li Bo Zheng Chengliang Wang Yingbo Wu National Elite Institute of Engineering Chongqing University China AI Lab Chongqing Changan Automobile Co. Ltd. China College of Computer Science Chongqing University China School of Big Data & Software Engineering Chongqing University China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Low-light images are typically characterized by low pixel intensity and color distortion, presenting a significant challenge for accurate 3D reconstruction with 3D Gaussian Splatting (3DGS). Traditional 2D enhancement methods fail to maintain consistent illumination, affecting reconstruction quality. We propose Low-Light Gaussian (LLGS), which can directly leverage low-light images for 3D reconstruction and synthesizing normal-light novel views. LLGS incorporates absorptance to simulate light behavior in low-light conditions, assuming objects maintain normal illumination while reflected light intensity attenuates due to absorptance during rendering. This approach enables the capture of authentic color information in dimly lit scenes. LLGS outperforms current enhancement algorithms and Neural Radiance Fields (NeRF) in image quality and processing efficiency, making it highly effective for low-light 3D scene reconstruction and novel view synthesis.

关键词： Image quality Three-dimensional displays Image color analysis Lighting Signal processing algorithms Modulation Speech enhancement Neural radiance field Rendering (computer graphics) Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Towards High-resolution 3D Anomaly Detection via Group-Level Feature Contrastive Learning 24

Towards High-resolution 3D Anomaly Detection via Group-Level...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Zhu, Hongze Xie, Guoyang Hou, Chengbin Dai, Tao Gao, Can Wang, Jinbao Shen, Linlin National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China Department of Computer Science City University of Hong Kong Hong Kong Hong Kong Department of Intelligent Manufacturing CATL Ningde China Fuzhou Fuyao Institute for Advanced Study Fuyao University of Science and Technology Fuzhou China College of Computer Science and Software Engineering Shenzhen University Shenzhen China Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen China Shenzhen University Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China

ISBN: (纸本)9798400706868

High-resolution point clouds (HRPCD) anomaly detection (AD) plays a critical role in precision machining and high-end equipment manufacturing. Despite considerable 3D-AD methods that have been proposed recently, they still cannot meet the requirements of the HRPCD-AD task. There are several challenges: i) It is difficult to directly capture HRPCD information due to large amounts of points at the sample level;ii) The advanced transformer-based methods usually obtain anisotropic features, leading to degradation of the representation;iii) The proportion of abnormal areas is very small, which makes it difficult to characterize. To address these challenges, we propose a novel group-level feature-based network, called Group3AD, which has a significantly efficient representation ability. First, we design an Intercluster Uniformity Network (IUN) to present the mapping of different groups in the feature space as several clusters, and obtain a more uniform distribution between clusters representing different parts of the point clouds in the feature space. Then, an Intracluster Alignment Network (IAN) is designed to encourage groups within the cluster to be distributed tightly in the feature space. In addition, we propose an Adaptive Group-Center Selection (AGCS) based on geometric information to improve the pixel density of potential anomalous regions during inference. The experimental results verify the effectiveness of our proposed Group3AD, which surpasses Reg3D-AD by the margin of 5% in terms of object-level AUROC on Real3D-AD. We provide the code and supplementary information on our website: https://***/M-3LAB/Group3AD. © 2024 ACM.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Structural Balance Computation of Signed Hypergraphs via Memetic Algorithm

Structural Balance Computation of Signed Hypergraphs via Mem...

引用

data-driven Optimization of Complex Systems (DOCS), International Conference on

作者： Xinchu Han Ruijie Xu Lijia Ma Zengyang Shao Yuan Bai Shanfeng Wang College of Computer Science and Software Engineering Shenzhen University Shenzhen China Laboratory of Data Discovery for Health Limited Hong Kong China School of Electronic Engineering Xidian University Xi'an China

The potential imbalances among entities and connections within complex systems can pose significant threats to their overall functionality. In order to enhance the functional security of these complex systems, it becomes imperative to address and alleviate these underlying imbalances. Structural balance computation has gained attention because of its ability to balance relationships among entities within systems. Traditional methods in structural balance computation aim to minimize imbalances within signed networkss. However, signed networkss have limitations in effectively representing complex data relationships in multi-modal or multi-type data. In order to address this constraint, we propose a novel framework called SHMA (Structural Balance of Signed Hypergraphs based on Memetic Algorithm) which aims to identify and minimize imbalances within signed hypergraphs. More specifically, we formulate the degree of imbalance in signed hypergraphs as an extended energy function, thereby transforming the computation of structural balance of the hypergraphs into an optimization problem. Then, we utilize a multi-level memetic algorithm to optimize the energy function and obtain a solution with the least imbalances. To assess the performance of SHMA, we performed experiments on various real-world datasets and conducted a comparative analysis. The experimental results illustrate that SHMA outperforms the alternative algorithms in terms of structural balance computation of signed hypergraphs. In addition, SHMA exhibits fast convergence, enabling it to reach a balanced state more efficiently.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Cooperative Co-Evolution Algorithm with Variable-Importance Grouping for Large-Scale Optimization 13

A Cooperative Co-Evolution Algorithm with Variable-Importanc...

引用

13th IEEE Congress on Evolutionary Computation, CEC 2024

作者： Li, Yongfeng Zhang, Yuze Ma, Lijia Ji, Junkai Liu, Dugang Leung, Victor C. M. Li, Jianqiang Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen518060 China Guangdong Laboratory of Artificial Intelligence and Digital Economy Shenzhen518123 China College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China Artificial Intelligence Research Institute Shenzhen MSU-BIT University Shenzhen518172 China The University of British Columbia Department of Electrical and Computer Engineering VancouverV6T 1Z4 Canada

ISBN: (纸本)9798350308365

Cooperative co-evolution (CC) is a promising direction in solving large-scale multiobjective optimization problems (LMOPs). However, most existing methods of grouping decision variables face some difficulties when searching in the huge search space. Specifically, the methods of grouping decision variables can be classified into two types, i.e., high-consumption grouping methods and non-consumption grouping methods. On the one hand, the former ones divide the decision variables into different groups based on the correlation analysis between variables, which consume much evaluation. This way may lead to premature convergence within limited computational resources. On the other hand, the later ones allocate the decision variables into sub-groups based on some metrics, e.g., order and size, which consume no evaluation while may cause the search fall into local optima. To alleviate the above issues, this paper proposes a CC-based algorithm with a variable-importance grouping (VIG) method, called VICCA. Firstly, the decision variables are classified into several subgroups according to their importance quantified by a meta-gene construction method. Secondly, a CC strategy is designed to simultaneously optimize all subgroups of decision variables formed by VIG using the differential evolution operator, which aims to accelerate the convergence speed. Thirdly, a global evolutionary strategy is proposed to optimize original decision variable space by the competitive swarm optimizer, aiming to maintain the diversity. Finally, the experiments demonstrate that our proposed VICCA has the significant advantage in solving LMOPs when compared with state-of-the-art evolutionary algorithms. © 2024 IEEE.

关键词： Optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

Kernelized Deep Networks for Speech Signal Segmentation Using Clustering and Artificial Intelligence in Neural Networks

Kernelized Deep Networks for Speech Signal Segmentation Usin...

引用

International Conference on Communication Systems and Network Technologies (CSNT)

作者： S Niveditha S Shreyanth V Kathiroli Priyanka Agarwal S Ram Abishek Department of Biotechnology Rajalakshmi Engineering College Chennai India Data Science and Engineering Birla Institute of Technology and Science Pilani India Automotive Engineering Birla Institute of Technology and Science Pilani India Software Development Engineer Altair Engineering India Pvt Ltd Chennai India

Speech signal segmentation is a key component of speech processing tasks, such as speaker recognition, speech recognition, and emotion recognition. Traditional approaches often have low accuracy and high computational complexity. To address this issue, we propose a novel approach using kernelized deep networks. The method utilizes Mel-Frequency Cepstral Coefficients (MFCC) and Linear Predictive Coding (LPC) for feature extraction, with Spectral subtraction, wavelet denoising and Wiener filtering as preprocessing techniques. Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA) are used for dimensionality reduction. Spectral clustering using the graph Laplacian and normalized Laplacian matrix is then employed to cluster the speech signals into different segments. The Lanczos algorithm, Implicitly Restarted Arnoldi Method and Krylov subspace is used to train the networks and classify the signals. Results on TIMIT and BURN corpus demonstrate that the proposed approach outperforms traditional techniques in terms of segmentation accuracy and reduces computational complexity. This research highlights the potential of kernelized deep networks for speech segmentation and contributes to the field of speech processing.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Category-Prompt Refined Feature Learning for Long-Tailed Multi-Label Image Classification

arXiv

引用

arXiv 2024年

作者： Yan, Jiexuan Huang, Sheng Mu, NanKun Huangfu, Luwen Liu, Bo School of Big Data & Software Engineering Chongqing University Chongqing China College of Computer Science Chongqing University Chongqing China Fowler College of Business San Diego State University San DiegoCA United States School of Computer Science and Information Engineering Hefei University of Technology Hefei China

Real-world data consistently exhibits a long-tailed distribution, often spanning multiple categories. This complexity underscores the challenge of content comprehension, particularly in scenarios requiring Long-Tailed Multi-Label image Classification (LTMLC). In such contexts, imbalanced data distribution and multi-object recognition pose significant hurdles. To address this issue, we propose a novel and effective approach for LTMLC, termed Category-Prompt Refined Feature Learning (CPRFL), utilizing semantic correlations between different categories and decoupling category-specific visual representations for each category. Specifically, CPRFL initializes category-prompts from the pretrained CLIP’s embeddings and decouples category-specific visual representations through interaction with visual features, thereby facilitating the establishment of semantic correlations between the head and tail classes. To mitigate the visual-semantic domain bias, we design a progressive Dual-Path Back-Propagation mechanism to refine the prompts by progressively incorporating context-related visual information into prompts. Simultaneously, the refinement process facilitates the progressive purification of the category-specific visual representations under the guidance of the refined prompts. Furthermore, taking into account the negative-positive sample imbalance, we adopt the Asymmetric Loss as our optimization objective to suppress negative samples across all classes and potentially enhance the head-to-tail recognition performance. We validate the effectiveness of our method on two LTMLC benchmarks and extensive experiments demonstrate the superiority of our work over baselines. The code is available at https://***/jiexuanyan/CPRFL. © 2024, CC BY-NC-SA.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Advancements in Cybersecurity Using Deep Learning Techniques Attack Detection for Trojan Horses

Advancements in Cybersecurity Using Deep Learning Techniques...

引用

Electrical Electronics and Computing Technologies (ICEECT), International Conference on

作者： Hosanna Princye P Ahila A A. Anna Lakshmi N. Ragavendran K. E. Purushothaman G. Uma Maheswari R. Saravanakumar Department of Electronics and Communication Engineering Sri Sairam College of Engineering Bangalore Anekal India Department of Information Technology R.M.K. Engineering College Chennai Tamil Nadu India Department of Artificial Intelligence and Data Science Engineering RMK College of Engineering and Technology Chennai Tamil Nadu India Department of Electronics and Communication Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Tamil Nadu India Department of Computer Science and Engineering RMK College of Engineering and Technology Chennai Tamil Nadu India Software Analyst Iconix Software Solution Tirunelveli Tamil Nadu India

ISBN: (数字)9798350378092

ISBN: (纸本)9798350378108

Today's computer networks are threatened by Trojan horse assaults and other cybersecurity dangers. We propose and evaluate deep learning methods using the Kaggle-hosted Trojan Detection dataset to detect Trojan horse assaults. This project uses these approaches. Our malware detection technology uses CNN classification for accuracy. We clean and enhance the dataset to make the model more versatile. Due to extensive testing and optimization, Trojan horse detection rates reach 98.47%. We found that the deep learning architecture accurately identifies malware. We also discuss CNN model features that illuminate Trojan horse attacks. The technique offers complete cyber security and expands our knowledge of harmful software. Deep learning may boost cybersecurity defenses against emerging attacks like Trojan horses, according to our study.

关键词： Deep learning Training Accuracy Feature extraction Safety Trojan horses Convolutional neural networks Computer crime Testing Python

来源：评论

学校读者我要写书评

暂无评论

A spectrum-enhanced attention model for semantic segmentation of remote sensing images

A spectrum-enhanced attention model for semantic segmentatio...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Li, Xin Xu, Feng Tao, Feifei Tong, Yao Lyu, Xin Zhong, Jianyi Kaup, André College of Computer Science and Software Engineering Hohai University Nanjing China Key Laboratory of Water Big Data Technology Ministry of Water Resources Hohai University Nanjing China School of Computer Engineering Jiangsu Ocean University Lianyungang China School of Artificial Intelligence and Information Technology Nanjing University of Chinese Medicine Nanjing China Multimedia Communications and Signal Processing Friedrich-Alexander University Erlangen-Nuremberg Erlangen Germany

ISBN: (纸本)9798350368741

Semantic segmentation of remote sensing images (RSIs) is essential for applications such as environmental monitoring, urban planning, and disaster management. Convolutional Neural Networks (CNNs) and their variants struggle to capture comprehensive spectral context for learning discriminative representations. In this paper, we propose a Spectrum-Enhanced Network (SPENet) that leverages the Frequency Transformer Block (FTB) to capture rich spectral context. FTB integrates Spectrum-Enhanced Attention (SEA) with Multi-Head Frequency Self-Attention (MH-FSA), incorporating more informative contextual cues. Specifically, SEA aggregates spectral statistics through covariance matrix normalization before applying channel-wise attention. By projecting feature maps onto the frequency domain, MH-FSA provides the network with a broader context, extending beyond the low-frequency focus of standard self-attention mechanisms. Extensive experiments on the ISPRS Potsdam and LoveDA datasets show that SPENet significantly outperforms state-of-the-art methods. Besides, the proposed SEA module notably rises average F1-score/overall accuracy/mean insert over union wiht more than 2.5/2.6%/2.3%, as demonstrated by ablation study. © 2025 IEEE.

关键词： frequency transformer remote sensing images Semantic segmentation spectrum enhancement

来源：评论

学校读者我要写书评

暂无评论

Evolutionary Multitasking With Adaptive Knowledge Transfer for Expensive Multiobjective Optimization

引用

IEEE Transactions on Evolutionary Computation 2024年

作者： Wu, Xunfeng Liu, Songbai Lin, Qiuzhen Tan, Kay Chen Leung, Victor C. M. The Hong Kong Polytechnic University Department of Data Science and Artificial Intelligence Hong Kong Hong Kong Shenzhen University College of Computer Science and Software Engineering Shenzhen518060 China The University of British Columbia Department of Electrical and Computer Engineering VancouverBCV6T 1Z4 Canada

Surrogate-assisted evolutionary algorithms (SAEAs) have shown promising performance in tackling expensive multiobjective optimization problems (EMOPs). However, existing SAEAs solve EMOPs separately, which ignore their optimization experiences earned before. Inspired by multitasking optimization paradigm for multitasking multiobjective optimization problems (MTMOPs), this article designs the first SAEA for tackling expensive MTMOPs (EMTMOPs) with adaptive knowledge transfer. First, a competitive surrogate selection is proposed to improve the generalization ability of approximating various EMOP tasks, where two types of surrogate models are trained and then compete for use to replace real expensive evaluations. Then, an adaptive solution selection is designed, which identifies promising transfer solutions to accelerate the solving of target task and selects promising infill solutions for real expensive evaluations to refine the surrogate models. The performance of our algorithm is validated on three commonly used benchmark suites and some real-world EMTMOPs. The experiments vali-date our superiority over several state-of-the-art SAEAs on most test cases. © 1997-2012 IEEE.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Beamforming Design for Semantic-Bit Coexisting Communication System

arXiv

引用

arXiv 2024年

作者： Zhang, Maojun Zhu, Guangxu Jin, Richeng Chen, Xiaoming Shi, Qingjiang Zhong, Caijun Huang, Kaibin College of Information Science and Electronic Engineering Zhejiang University Hangzhou China Shenzhen Research Institute of Big Data Shenzhen China School of Software Engineering Tongji University Shanghai200092 China Shenzhen Research Institute of Big Data Shenzhen518172 China The University of Hong Kong Hong Kong

Semantic communication (SemCom) is emerging as a key technology for future sixth-generation (6G) systems. Unlike traditional bit-level communication (BitCom), SemCom directly optimizes performance at the semantic level, leading to superior communication efficiency. Nevertheless, the task-oriented nature of SemCom renders it challenging to completely replace BitCom. Consequently, it is desired to consider a semantic-bit coexisting communication system, where a base station (BS) serves SemCom users (sem-users) and BitCom users (bit-users) simultaneously. Such a system faces severe and heterogeneous inter-user interference. In this context, this paper provides a new semantic-bit coexisting communication framework and proposes a spatial beamforming scheme to accommodate both types of users. Specifically, we consider maximizing the semantic rate for semantic users while ensuring the quality-of-service (QoS) requirements for bit-users. Due to the intractability of obtaining the exact closed-form expression of the semantic rate, a data driven method is first applied to attain an approximated expression via data fitting. With the resulting complex transcendental function, majorization minimization (MM) is adopted to convert the original formulated problem into a multiple-ratio problem, which allows fractional programming (FP) to be used to further transform the problem into an inhomogeneous quadratically constrained quadratic programs (QCQP) problem. Solving the problem leads to a semi-closed form solution with undetermined Lagrangian factors that can be updated by a fixed point algorithm. This method is referred to as the MM-FP algorithm. Additionally, inspired by the semi-closed form solution, we also propose a low-complexity version of the MM-FP algorithm, called the low-complexity MM-FP (LP-MM-FP), which alleviates the need for iterative optimization of beamforming vectors. Extensive simulation results demonstrate that the proposed MM-FP algorithm outperforms convention

关键词： Mean square error

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：