检索结果-内蒙古大学图书馆

29th International Joint Conference on Artificial Intelligence, IJCAI 2020

作者： Huang, Rongzhou Huang, Chuyin Liu, Yubao Dai, Genan Kong, Weiyang Sun Yat-Sen University Guangzhou China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China

ISBN: (纸本)9780999241165

Traffic prediction is a classical spatial-temporal prediction problem with many real-world applications such as intelligent route planning, dynamic traffic management, and smart location-based applications. Due to the high nonlinearity and complexity of traffic data, deep learning approaches have attracted much interest in recent years. However, few methods are satisfied with both long and short-term prediction tasks. Target at the shortcomings of existing studies, in this paper, we propose a novel deep learning framework called Long Short-term Graph Convolutional Networks (LSGCN) to tackle both traffic prediction tasks. In our framework, we propose a new graph attention network called cosAtt, and integrate both cosAtt and graph convolution networks (GCN) into a spatial gated block. By the spatial gated block and gated linear units convolution (GLU), LSGCN can efficiently capture complex spatial-temporal features and obtain stable prediction results. Experiments with three real-world traffic datasets verify the effectiveness of LSGCN. © 2020 Inst. Sci. inf., Univ. Defence in Belgrade. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Learning Summary-Worthy Visual Representation for Abstractive Summarization in Video

arXiv

引用

arXiv 2023年

作者： Xu, Zenan Meng, Xiaojun Wang, Yasheng Su, Qinliang Qiu, Zexuan Jiang, Xin Liu, Qun School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Noah’s Ark Lab Huawei Technologie The Chinese University of Hong Kong Hong Kong Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China

Multimodal abstractive summarization for videos (MAS) requires generating a concise textual summary to describe the highlights of a video according to multimodal resources, in our case, the video content and its transcript. Inspired by the success of the large-scale generative pre-trained language model (GPLM) in generating high-quality textual content (e.g., summary), recent MAS methods have proposed to adapt the GPLM to this task by equipping it with the visual information, which is often obtained through a general-purpose visual feature extractor. However, the generally extracted visual features may overlook some summary-worthy visual information, which impedes model performance. In this work, we propose a novel approach to learning the summary-worthy visual representation that facilitates abstractive summarization. Our method exploits the summary-worthy information from both the cross-modal transcript data and the knowledge that distills from the pseudo summary. Extensive experiments on three public multimodal datasets show that our method outperforms all competing baselines. Furthermore, with the advantages of summary-worthy visual information, our model can have a significant improvement on small datasets or even datasets with limited training data. Copyright © 2023, The Authors. All rights reserved.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

EG-KGR: A Knowledge Graph Reasoning Model Based on Enhanced Graph Sample and Aggregate Inductive Learning Algorithm

EG-KGR: A Knowledge Graph Reasoning Model Based on Enhanced ...

引用

International Conference on Tools for Artificial Intelligence (ICTAI)

作者： Yuejia Wu Jian-Tao Zhou Inner Mongolia Key Laboratory of Discipline Inspection and Supervision Big Data Inner Mongolia Engineering Laboratory for Big Data Analysis Technology Ministry of Education Inner Mongolia Engineering Laboratory for Cloud Computing and Service Software Inner Mongolia Key Laboratory of Social Computing and Data Processing College of Computer Science Inner Mongolia University National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian Engineering Research Center of Ecological Big Data Hohhot China

Knowledge Graph is an important research field that involves the storage and management of knowledge, but the incompleteness and sparsity of Knowledge Graphs hinder their application in many fields. Knowledge Graph Reasoning aims to alleviate this problem by completing missing paths or identifying wrong paths between entities. Graph Convolution Network (GCN) based methods are one of the state-of-the-art approaches to this work. However, it is difficult to directly generalize to unknown nodes and utilizes valid information from the local neighborhood which results in poor flexibility and extensibility and will loss of important information. This paper presents EG-KGR, a plug-and-play knowledge reasoning model based on enhanced graph sampling and aggregate inductive learning algorithm to relieve the above problems and enhance existing GCN-based methods. Specifically, EG-KGR supports incremental characteristics, uses inductive learning to replace transductive learning, and designs random sampling and local information sampling optimization methods to improve the model's generalization ability, prediction accuracy, and running speed. Extensive experimental results show that our EG-KGR can achieve optimal results.

关键词： Training Knowledge engineering Convolution Aggregates Optimization methods Knowledge graphs Learning (artificial intelligence)

来源：评论

学校读者我要写书评

暂无评论

An Improved 2P-CFAR Method for Ship Detection in SAR Images

An Improved 2P-CFAR Method for Ship Detection in SAR Images

引用

IEEE International Conference on Radar

作者： Jiahui Chang Qing Wang Jianhui Zhao Ning Li Henan Key Laboratory of Big Data Analysis and Processing (of Henan University) College of Computer and Information Engineering (of Henan University) Kaifeng China Air Force Research Institute Beijing China

ISBN: (纸本)9781665468893

Synthetic Aperture Radar (SAR) systems can be used for discovery and surveillance. According to the current requirements, accurate ship detection is becoming more and more important. However, the interference factors such as coherent speckle noise and strong target sidelobes will reduce the detection accuracy. In this paper, an improved two-parameter Constant False Alarm Rate (2P-CFAR) method is proposed to solve this problem. After using the non-local means (NLM) filtering method to suppress coherent speckle noise, the 2P-CFAR method is performed to obtain candidate targets, and an equal proportion segmentation procedure is carried out to optimize the aspect ratios of the candidate targets and weaken the sidelobes. Experimental results based on the SAR images acquired by the Gaofen-3 satellite verify the performance of the proposed method.

关键词： Image segmentation Satellites Filtering Spaceborne radar Surveillance Radar detection Speckle

来源：评论

学校读者我要写书评

暂无评论

A Multi-direction Prediction Multi-objective Hybrid Chemical Reaction Optimization Algorithm for Dynamic Multi-objective Optimization 16th

A Multi-direction Prediction Multi-objective Hybrid Chemical...

引用

16th International Conference on Bio-Inspired Computing: Theories and Applications, BIC-TA 2021

作者： Li, Hongye Pan, Xiaoying Gan, Wei Wang, Lei School of Computer Science and Technology Xi’an University of Posts and Telecommunications Shaanxi Xi’an710121 China Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Shaanxi Xi’an710121 China Xi’an Key Laboratory of Big Data and Intelligent Computing Shaanxi Xi’an710121 China Xi’an Shiyou University Shaanxi Xi’an710065 China School of Computer Science and Engineering Xi’an University of Technology Xi’an710048 China Shaanxi University of Technology Shaanxi Han Zhong723001 China

ISBN: (纸本)9789811912559

The challenge of solving dynamic multi-objective optimization problems is to trace the varying Pareto optimal front and/or Pareto optimal set quickly and efficiently. This paper proposes a multi-direction prediction strategy using a hybrid chemical reaction optimization, aimed at finding the dynamic Pareto optimal front and/or Pareto optimal set as quickly and accurately as possible before the next environmental change occurs. The proposed method, multi-direction prediction multi-objective hybrid chemical reaction optimization algorithm which mainly includes a hybrid chemical reaction optimization algorithm is proposed for solving dynamic multi-objective problems, which can guide population trace the optimum. When the environment has changed, the population is divided into several subpopulations. In subpopulation, a center point was found to construct multi-direction prediction model. As a result, this approach enhances the diversity of algorithm. While the environment has not changed, the hybrid chemical reaction algorithm with particle swarm optimization algorithm can efficiency find the optimal solution, it can achieve good diversity as well as guarantee the avoidance of local optimal solutions. The proposed algorithm is measured on several benchmark test suites with various dynamic characteristics and different difficulties. Experimental results show that this algorithm is very competitive in dealing with dynamic multi-objective optimization problems when compared with four state-of-the-art approaches. © 2022, Springer Nature Singapore Pte Ltd.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Enhancing Event Tagger with Automatic Speech Recognizer for Audio Multi-task Scenarios by Distillation with Pre-Trained Large Models

Enhancing Event Tagger with Automatic Speech Recognizer for ...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Jianfeng Cheng Ye Liu Jian Yin Liangdao Wang Yan Pan Artificial Intelligence Department Lizhi Inc. Beijing & Guangzhou China School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China School of Artificial Intelligence Sun Yat-sen University Zhuhai China

ISBN: (数字)9781665410205

ISBN: (纸本)9781665410212

With the continuous expansion of robotics and digital humans in practical applications, the demand for the auditory system is becoming deeper, usually requiring more efficient speech recognition framework capabilities to handle multiple tasks and use fewer resources. In previous audio processing frameworks, each type of audio processing task typically requires constructing a standalone deep network model for training, which results in more training data and higher training time when constructing models for multi-task audio scenarios simultaneously. The recent improvement of audio models based on transformers have brought about methods that can handle multiple audio tasks concurrently. However, recent related methods still require retraining multi-task targets with an amount of data, and achieve the general effect after training for multi-task scenarios than the simple combination of standalone methods processed separately. In order to better build a model that can handle multiple audio tasks, we propose a novel framework of distillation through pre-trained large models for enhancing event tagger with automatic speech recognizer. Through multiple rounds of experiments on several audio datasets, it has been verified that the proposed framework can achieve better results than the baseline for multitasking, and comparative results with less parameters compared to the baselines for single-task scenarios.

关键词： Training Adaptation models Analytical models Training data Speech recognition Speech enhancement Multitasking Transformers data models Robots

来源：评论

学校读者我要写书评

暂无评论

Periodic Response analysis of A Jeffcott-Rotor System By The Integral Equation Method

Research Square

引用

Research Square 2021年

作者： Zhang, Wenxin Chen, Yueli Henan Academy of Big Data School of Mathematics and Statistics Zhengzhou University Henan Zhengzhou450001 China Zhengzhou Key Laboratory of Big Data Analysis and Application Henan Academy of Big Data Zhengzhou University Henan Zhengzhou450001 China

In this paper, two modified nonlinear saturation-based controllers and negative velocity feedback controllers are integrated to suppress the horizontal and vertical vibrations of a horizontally supported Jeffcott-rotor system at primary resonance excitation and the presence of 1:1 and 1:2 internal resonances. The second order approximations and the amplitude equations are obtained by applying the integral equation method to analyze the nonlinear behavior of this model. The stability of the steady-state solutions is ascertained based on the Floquet theory. The necessity of adding a negative velocity feedback to the main system is stated. The effects of different control parameters on the frequency-response curves and the force-response curves are investigated. Time histories of the whole system are included to show the response with and without control. It is shown that the saturation-based controller can reduce the system response to almost zero and the negative velocity feedback can suppress the transient vibrations and prevent the main system having the large amplitude vibration. The analyses show that analytical solutions are in excellent agreement with the numerical simulations. Finally, a comparison with previously published works is included. © 2021, CC BY.

关键词： Controllers

来源：评论

学校读者我要写书评

暂无评论

An Orbital Angular Momentum Mode Estimation Method with an Unknown Beam Axis

An Orbital Angular Momentum Mode Estimation Method with an U...

引用

IEEE SENSORS

作者： Gaofeng Shu Bingxu Chen Ning Li School of Computer and Information Engineering Henan University Henan Engineering Research Center of Intelligent Technology and Application Henan University Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng China

Orbital angular momentum (OAM) beam is very difficult to receive due to the divergence of the beam. The position of the beam axis must be known by the existing receiving methods, including the single point method and the phase gradient method. This article proposes an OAM mode estimation method with an unknown beam axis. This method first estimates the position of the beam axis according to the phase characteristics and then uses the phase gradient method to estimate the OAM mode. The simulation results verify the effectiveness of the method.

关键词： Gradient methods Simulation Estimation Orbits Sensors

来源：评论

学校读者我要写书评

暂无评论

Padding Adversarial Training: Enhancing Robustness with Adversarial Space Hypothesis

SSRN

引用

SSRN 2022年

作者： Sun, Jiaze Wen, Sulei School of Computer Science and Technology Xi’an University of Posts and Telecommunications Xi’an710121 China Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Xi’an710121 China Xi 'an Key Laboratory of Big Data and Intelligent Computing Xi’an710127 China

Adversarial training, represented by the projected gradient descent(PGD) adversarial training, effectively improves adversarial robustness within the upper bound of perturbation to the deep neural network(DNN) by applying adversarial examples to model retraining. When the perturbation is beyond the pale, though, the defense it provides to the model is invalid. Furthermore, it is also vulnerable to adaptive attacks and novel attacks uninvolved in adversarial training. To solve these problems, we propose the adversarial space hypothesis based on the manifold theory to explain the existence of adversarial examples from a feature space perspective. We further introduce padding adversarial training, a technique enhancing adversarial training with the adversarial space hypothesis. Padding adversarial training improves the generalization of the standard adversarial training’s robustness by 20% and provides an additional detection defense for adversarial examples with high perturbation. Moreover, we propose trap smoothing, which optimizes the target manifold’s distribution and establishes the inducing relationship between the target manifold and the feature space labelled by the padding classes. On MNIST and CIFAR-10, padding adversarial training is robust to white, black and adaptive attacks in low perturbation conditions and provides the 80%~98% detection rate of adversarial examples in high perturbation conditions. The code is available at:https://***/Ccsk-Xian/Padding-adversarial-training. © 2022, 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

Reversible adversarial information hiding based on the interpretation of neural network

引用

Digital Signal processing: A Review Journal 2025年 165卷

作者： Li, Ruiping Wang, Xi Cui, Qingchen Li, Ming Information Construction and Management Office Henan Normal University Xinxiang453007 China School of Artificial Intelligence and Software Engineering Nanyang Normal University Nanyang473061 China Henan Engineering Research Center of Intelligent Processing for Big Data of Digital Image Henan Nanyang473000 China College of Information Engineering Zhoukou Vocational College of Arts and Science Zhoukou466000 China College of Computer and Information Engineering Henan Normal University Xinxiang453007 China Key Laboratory of Artificial Intelligence and Personalized Learning in Education of Henan Province Xinxiang453007 China

The emerging technology of adversarial information hiding can generate adversarial example by embedding useful information instead of meaningless noise into the host image. The obtained image can deceive classification models and therefore equip the function of privacy protection. However, existing research mainly focuses on the effectiveness of attack rather than preserving the integrity of the protected image. It cannot meet the requirements in the fields such as medical imaging, financial transactions, and copyright protection where users' raw data should not be damaged. Therefore, we propose a novel reversible adversarial information hiding based on interpretability of neural networks. The Grad-CAM-generated heatmap is employed to identify a minimal set of high-impact pixels for embedding, ensuring that minor modifications can induce significant misclassification. Then, the user-defined secret bits are embedded into the identified pixels by using difference expansion. After extraction, the original image can be perfectly restored. The technologies of adversarial example and reversible information hiding are combined to accommodate wider applications. The proposed method is tested on CIFAR-10 with three different neural architectures (NiN, AlexNet, ResNet). Experimental results show that the proposed method can completely restore the cover image while ensuring the extraction of the embedded data and misleading the neural network. © 2025 Elsevier Inc.

关键词： Adversarial attacks Adversarial information hiding Neural network interpretability Reversibility

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：