检索结果-内蒙古大学图书馆

7th Asian Conference on Pattern Recognition, ACPR 2023

作者： Wang, Yangbo Zhou, Jie Lin, Qingshui Lu, Jianglin Gao, Can National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China SZU Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518060 China Basic Teaching Department Liaoning Technical University Huludao125105 China College of Engineering Northeastern University BostonMA02115 United States

ISBN: (纸本)9783031476648

Self-expression learning methods often obtain a coefficient matrix to measure the similarity between pairs of samples. However, directly using all points to represent a fixed sample in a class under the self-expression framework may not be ideal, as points from other classes participate in the representing process. To alleviate this issue, this study attempts to achieve representation learning between points only coming from the same class. In practice, it is easier for data points from the same class to represent each other than that from different classes. So, when reconstructing a point, if the number of non-zero elements in the coefficient vector is limited, a model is more likely to select data points from the class where the reconstructed point lies to complete the reconstruction work. Based on this idea, we propose Sparse Subspace Clustering with the l0 inequality constraint (SSC- l0 ). In SSC- l0, the l0 inequality constraint determines the maximum number of non-zero elements in the coefficient vector, which helps SSC- l0 to conduct representation learning among the points in the same class. After introducing the simplex constraint to ensure the translation invariance of the model, an optimization method concerning l0 inequality constraint is formed to solve the proposed SSC- l0, and its convergence is theoretically analyzed. Extensive experiments on well-known datasets demonstrate the superiority of SSC- l0 compared to several state-of-the-art methods. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

A Load Balancing Algorithm with Minimum Links Scheduling 5

A Load Balancing Algorithm with Minimum Links Scheduling

引用

5th International Conference on Computer Information Science and Application Technology, CISAT 2022

作者： Zhang, Weiping Chen, YanLing Liu, Zhonghao Chen, Yansheng Educational Affairs Department Guangdong Industry Polytechnic Guangzhou510300 China School of Art and Design Guangdong Industry Polytechnic Guangzhou510300 China Dept. of Computing Hong Kong Polytechnic University 999077 Hong Kong Institute of Big Data and Artificial Intelligence Applications Guangdong Industry Polytechnic Guangzhou510300 China

ISBN: (纸本)9781510660076

In the limited resource scenario of the public computer room, the FTP service resource sharing platform cannot bear the computing requirements required for the rapid growth of access, data capacity, network traffic, etc. based on an independent server. Based on the Least Link Scheduling (LVS) strategy, designed and implemented the minimum link load balancing scheduling algorithm. In the normal experimental environment of the public computer room, we increase the backup scheduling server and intensively schedule the server redundant resources of the shared platform to evaluate the performance of the load balancing scheduling algorithm in terms of transmission speed, the maximum number of users, and the read speed of the server disk. The experimental results show that the performance of the resource sharing platform based on the minimum link load balancing scheduling algorithm is significantly improved, achieving 2.21 times, 3.00 times and 5.60 times increments, which is of practical significance for promoting the efficient use of computer sharing platform resources under the condition of limited resources. © 2022 SPIE.

关键词： Scheduling

来源：评论

学校读者我要写书评

暂无评论

STSE-xLSTM: A Deep Learning Framework for Automated Seizure Detection in Long Video Sequences Using Spatio-Temporal and Attention Mechanisms

STSE-xLSTM: A Deep Learning Framework for Automated Seizure ...

引用

International Conference on Computer and Communications (ICCC)

作者： Lihui Ding Hongliang Wang Lijun Fu Shenyang Institute of Computing Technology University of Chinese Academy of Sciences Shenyang China Liaoning Province Human-Computer Interaction System Engineering Research Center Based on Digital Twin Shenyang China Laboratory of Big Data and Artificial Intelligence Technology Shandong University Beijing China

ISBN: (数字)9798331507077

ISBN: (纸本)9798331507084

A detailed analysis of seizure semiology, the symptoms and signs that occur during a seizure, is crucial for the management of epilepsy patients. The inter-rater reliability of qualitative visual analysis is often low, highlighting the need for automatic and quantitative analysis of video-recorded seizures for objective assessment. To enhance evaluation accuracy and consistency, computer-aided video analysis of seizures has emerged as a natural direction of development. In the field of medical applications, deep learning and computer vision methods have driven significant advancements. However, analyzing video data presents challenges due to high dimensionality, variations in lighting, posture, and video quality. Additionally, the duration of seizures can range from seconds to minutes. To effectively extract features from seizures, we propose a novel deep learning model, STSE-xLSTM, designed to learn deep representations of arbitrarily long seizure videos. This model integrates a Spatio-Temporal Convolutional Network (STCNN) for feature extraction, a Squeeze-and-Excitation (SE) attention mechanism to enhance relevant features, and an extended Long Short-Term Memory network (xLSTM) to process long video sequences. The SE mechanism adaptively recalibrates channel weights, improving recognition of minority classes and reducing information redundancy. The xLSTM introduces scalar and matrix memory units, optimizing memory capacity and multi-scale feature extraction, thereby enhancing detection accuracy. When evaluated on the GESTURES dataset, our model outperformed state-of-the-art epilepsy detection methods in classification performance. Key contributions include the integration of STCNN, SE attention mechanism, and xLSTM to address data imbalance issues and improve the handling of complex sequential data in epilepsy detection.

关键词： Deep learning Adaptation models Visualization Attention mechanisms Accuracy Video sequences Epilepsy Feature extraction Reliability Long short term memory

来源：评论

学校读者我要写书评

暂无评论

Smoothed Multi-view Subspace Clustering 1

引用

2nd International Conference on Neural computing for Advanced Applications, NCAA 2021

作者： Chen, Peng Liu, Liang Ma, Zhengrui Kang, Zhao Jangsu Automation Research Institute Lianyungang Jiangsu China University of Electronic Science and Technology of China Chengdu Sichuan China Trusted Cloud Computing and Big Data Key Laboratory of Sichuan Province Chengdu Sichuan China

ISBN: (数字)9789811651885

ISBN: (纸本)9789811651878

In recent years, multi-view subspace clustering has achieved impressive performance due to the exploitation of complementary information across multiple views. However, multi-view data can be very complicated and are not easy to cluster in real-world applications. Most existing methods operate on raw data and may not obtain the optimal solution. In this work, we propose a novel multi-view clustering method named smoothed multi-view subspace clustering (SMVSC) by employing a novel technique, i.e., graph filtering, to obtain a smooth representation for each view, in which similar data points have similar feature values. Specifically, it retains the graph geometric features through applying a low-pass filter. Consequently, it produces a "clustering-friendly" representation and greatly facilitates the downstream clustering task. Extensive experiments on benchmark datasets validate the superiority of our approach. Analysis shows that graph filtering increases the separability of classes. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Low pass filters

来源：评论

学校读者我要写书评

暂无评论

Parallel Rectangle Flip Attack: A Query-based Black-box Attack against Object Detection

arXiv

引用

arXiv 2022年

作者： Liang, Siyuan Wu, Baoyuan Fan, Yanbo Wei, Xingxing Cao, Xiaochun Institute of Information Engineering Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China School of Data Science The Chinese University of Hong Kong Shenzhen China Secure Computing Lab of Big Data Shenzhen Research Institute of Big Data Shenzhen China Tencent Shenzhen China Institute of Artificial Intelligence Hangzhou Innovation Institute Beihang University Beijing China

Object detection has been widely used in many safety-critical tasks, such as autonomous driving. However, its vulnerability to adversarial examples has not been sufficiently studied, especially under the practical scenario of black-box attacks, where the attacker can only access the query feedback of predicted bounding-boxes and top-1 scores returned by the attacked model. Compared with black-box attack to image classification, there are two main challenges in black-box attack to detection. Firstly, even if one bounding-box is successfully attacked, another suboptimal bounding-box may be detected near the attacked bounding-box. Secondly, there are multiple bounding-boxes, leading to very high attack cost. To address these challenges, we propose a Parallel Rectangle Flip Attack (PRFA) via random search. We explain the difference between our method with other attacks in Fig. 1. Specifically, we generate perturbations in each rectangle patch to avoid sub-optimal detection near the attacked region. Besides, utilizing the observation that adversarial perturbations mainly locate around objects' contours and critical points under white-box attacks, the search space of attacked rectangles is reduced to improve the attack efficiency. Moreover, we develop a parallel mechanism of attacking multiple rectangles simultaneously to further accelerate the attack process. Extensive experiments demonstrate that our method can effectively and efficiently attack various popular object detectors, including anchor-based and anchor-free, and generate transferable adversarial examples. Copyright © 2022, The Authors. All rights reserved.

关键词： Geometry

来源：评论

学校读者我要写书评

暂无评论

Rediscovering BCE Loss for Uniform Classification

arXiv

引用

arXiv 2024年

作者： Li, Qiufu Jia, Xi Zhou, Jiancan Shen, Linlin Duan, Jinming National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Computer Vision Institute Shenzhen University SZU Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society China School of Computer Science University of Birmingham United Kingdom Aqara Lumi United Technology Co. Ltd China

This paper introduces the concept of uniform classification, which employs a unified threshold to classify all samples rather than adaptive threshold classifying each individual sample. We also propose the uniform classification accuracy as a metric to measure the model’s performance in uniform classification. Furthermore, begin with a naive loss, we mathematically derive a loss function suitable for the uniform classification, which is the BCE function integrated with a unified bias. We demonstrate the unified threshold could be learned via the bias. The extensive experiments on six classification datasets and three feature extraction models show that, compared to the SoftMax loss, the models trained with the BCE loss not only exhibit higher uniform classification accuracy but also higher sample-wise classification accuracy. In addition, the learned bias from BCE loss is very close to the unified threshold used in the uniform classification. The features extracted by the models trained with BCE loss not only possess uniformity but also demonstrate better intra-class compactness and inter-class distinctiveness, yielding superior performance on open-set tasks such as face recognition. © 2024, CC BY.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

AONN-2: An adjoint-oriented neural network method for PDE-constrained shape optimization

arXiv

引用

arXiv 2023年

作者： Wang, Xili Yin, Pengfei Zhang, Bo Yang, Chao School of Mathematical Sciences Peking University Beijing100871 China National Engineering Laboratory for Big Data Analysis and Applications Peking University Beijing100871 China PKU-Changsha Institute for Computing and Digital Economy Hunan410006 China

Shape optimization has been playing an important role in a large variety of engineering applications. Existing shape optimization methods are generally mesh-dependent and therefore encounter challenges due to mesh deformation. To overcome this limitation, we present a new adjoint-oriented neural network method, AONN-2, for PDE-constrained shape optimization problems. This method extends the capabilities of the original AONN method [1], which is developed for efficiently solving parametric optimal control problems. AONN-2 inherits the direct-adjoint looping (DAL) framework for computing the extremum of an objective functional and the neural network methods for solving complicated PDEs from AONN. Furthermore, AONN-2 expands the application scope to shape optimization by taking advantage of the shape derivatives to optimize the shape represented by discrete boundary points. AONN-2 is a fully mesh-free shape optimization approach, naturally sidestepping issues related to mesh deformation, with no need for maintaining mesh quality and additional mesh corrections. A series of experimental results are presented, highlighting the flexibility, robustness, and accuracy of AONN-2. Copyright © 2023, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Echoes in Silence: A Technological Leap for Pakistan Sign Language Translation and Recognition

Echoes in Silence: A Technological Leap for Pakistan Sign La...

引用

International Symposium on High Capacity Optical Networks and Enabling Technologies, HONET

作者： Tayyaba Riaz Adeel Anjum Adnan Anjum Muazzam A. Khan Institute of Information Technology Quaid-i-Azam University Islamabad Pakistan IBM Pakistan ICESCO Chair Big Data Analytics and Edge Computing Quaid i Azam University Islamabad Quaid-i-Azam University Islamabad Pakistan

In an endeavor to bridge communication barriers for the Pakistani deaf community, this project presents a robust system capable of translating Pakistani Sign Language (PSL) to text and vice versa. The architecture leverages cutting-edge technologies: the textual and voice inputs are processed using Natural Language Processing (NLP) techniques, with voice-to-text translation facilitated by the WebSpeechToolkit. For the Sign-to-Text (S2T) module, images and videos undergo rigorous preprocessing using OpenCV, followed by hand landmark detection via MediaPipe, ensuring the precise capture of PSL gestures. TensorFlow's neural networks are instrumental in recognizing these gestures, translating them into textual counterparts. The project's unique feature is its flexibility in breaking down non-existent sentences into words and, if needed, further into alphabets. Despite its innovative approach, the system acknowledges limitations in its training data, encompassing a dataset of English words, numbers, Urdu alphabets, and English alphabets, yet still achieving an impressive accuracy of approximately 95 %. Hosted on a user-friendly Django website interface, this system introduces two primary modules: one for translating text to PSL signs and another for the inverse. With its amalgamation of technologies and user-centric design, this project holds promise as a pivotal tool for enhancing the accessibility and interaction of the deaf community in Pakistan.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MAAM:A LIGHTWEIGHT MULTI-AGENT AGGREGATION MODULE FOR EFFICIENT IMAGE CLASSIFICATION BASED ON THE MINDSPORE FRAMEWORK

arXiv

引用

arXiv 2025年

作者： Qin, Zhenkai Zhu, Feng Zeng, Huan Nong, Xunyi School of Computing and Information Guangxi Police College Guangxi Nanning China Network Security Research Center Guangxi Police College Guangxi Nanning China Big Data and Policing Technology Laboratory Guangxi Police College Guangxi Nanning China Institute of Software Chinese Academy of Sciences Beijing China

The demand for lightweight models in image classification tasks under resource-constrained environments necessitates a balance between computational efficiency and robust feature representation. Traditional attention mechanisms, despite their strong feature modeling capability, often struggle with high computational complexity and structural rigidity, limiting their applicability in scenarios with limited computational resources (e.g., edge devices or real-time systems). To address this, we propose the Multi-Agent Aggregation Module (MAAM), a lightweight attention architecture integrated with the MindSpore framework. MAAM employs three parallel agent branches with independently parameterized operations to extract heterogeneous features, adaptively fused via learnable scalar weights, and refined through a convolutional compression layer. Leveraging MindSpore’s dynamic computational graph and operator fusion, MAAM achieves 87.0% accuracy on the CIFAR-10 dataset, significantly outperforming conventional CNN (58.3%) and MLP (49.6%) models, while improving training efficiency by 30%. Ablation studies confirm the critical role of agent attention (accuracy drops to 32.0% if removed) and compression modules (25.5% if omitted), validating their necessity for maintaining discriminative feature learning. The framework’s hardware acceleration capabilities and minimal memory footprint further demonstrate its practicality, offering a deployable solution for image classification in resource-constrained scenarios without compromising accuracy. © 2025, CC0.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Aonn-2: An Adjoint-Oriented Neural Network Method for Pde-Constrained Shape Optimization

SSRN

引用

SSRN 2023年

Shape optimization has been playing an important role in a large variety of engineering applications. Existing shape optimization methods are generally mesh-dependent and therefore encounter challenges due to mesh deformation. To overcome this limitation, we present a new adjoint-oriented neural network method, AONN-2, for PDE-constrained shape optimization problems. This method extends the capabilities of the original AONN method [1], which is developed for efficiently solving parametric optimal control problems. AONN-2 inherits the direct-adjoint looping (DAL) framework for computing the extremum of an objective functional and the neural network methods for solving complicated PDEs from AONN. Furthermore, AONN-2 expands the application scope to shape optimization by taking advantage of the shape derivatives to optimize the shape represented by discrete boundary points. AONN-2 is a fully mesh-free shape optimization approach, naturally sidestepping issues related to mesh deformation, with no needs for maintaining mesh quality and additional mesh corrections. A series of experimental results are presented, highlighting the flexibility, robustness, and accuracy of AONN-2. © 2023, The Authors. All rights reserved.

关键词： Deep neural networks

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：