检索结果-内蒙古大学图书馆

3rd International Conference on Pattern Recognition and Machine Learning, PRML 2022

作者： Cai, Xiangsheng Tohti, Turdi Hamdulla, Askar Xinjiang University of China Xinjiang Key Laboratory of Signal Detection and Processing School of Information Science and Engineering Urumqi830017 China

ISBN: (数字)9781665499507

ISBN: (纸本)9781665499507

Most of the rumors on social media (e.g., Twitter) revolve around a certain domain or topic, which means that they want to express roughly the same meaning, only the way of expression or the words used are different. Most of the existing rumor detection work focuses on text semantic features, user information features, comment features, and communication structure features, but rarely utilizes the rumor features associated with the original text. Therefore, a GCN-BERT -based rumor detection method is proposed in this paper, which not only utilizes the rumor features of a message itself but also utilizes the rumor features of all the texts and words associated with it when performing rumor detection. Finally, three Twitter datasets are used for comparison experiments, and the results fully demonstrate that the method is more effective than existing rumor detection methods. © 2022 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

COT2DNet: Contextual 2D Attention for Scene Text Recognition 2

COT2DNet: Contextual 2D Attention for Scene Text Recognition

引用

2nd International Conference on Artificial Intelligence, Human-Computer Interaction and Robotics, AIHCIR 2023

作者： Qian, Yefei Ibrayim, Mayire Hamdulla, Askar Zhang, Chunhu Xinjiang Key Laboratory of Signal Detection and Processing Urumqi830017 China School of Computer Science and Technology Xinjiang University Xinjiang China

ISBN: (纸本)9798350360363

Although scene text recognition (STR) methods have made great progress, reading the text of irregularly shaped scenes remains a challenge. The current conversion of two-dimensional (2D) images to one-dimensional (1D) feature maps for sequence recognition may lose a large amount of spatial information and cannot recognize text with a large degree of curvature. In this paper, we propose an network infrastructure to recognize texts of arbitrary shapes, named COT2D Attention Text Recognition Network (COT2Net). Firstly, deformable convolution is added to the feature extraction module, which can perform feature extraction according to the shape of the character and expand the receptive field of feature extraction;Finally, in the Transformer encoding stage, the multi-head attention is changed to Contextual 2D Multi-head Attention (COT2D), which can make full use of the relationship between the input keys Q, K, and V to guide the learning of dynamic attention, thereby enhancing the visual expression ability of text images. The COT2DNet uses COT2D to learn the relevance of each character in a scene text image and achieves excellent results on public datasets. © 2023 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

GRATDet:Smart Contract Vulnerability Detector Based on Graph Representation and Transformer

引用

Computers, Materials & Continua 2023年第8期76卷 1439-1462页

作者： Peng Gong Wenzhong Yang Liejun Wang Fuyuan Wei KeZiErBieKe HaiLaTi Yuanyuan Liao College of Information Science and Engineering Xinjiang UniversityUrumqi830000China Key Laboratory of Signal Detection and Processing in Xinjiang Uygur Autonomous Region Xinjiang UniversityUrumqi830000China Key Laboratory of Multilingual Information Technology in Xinjiang Uygur Autonomous Region Xinjiang UniversityUrumqi830000China

Smart contracts have led to more efficient development in finance and healthcare,but vulnerabilities in contracts pose high risks to their future *** current vulnerability detection methods for contracts are either based on fixed expert rules,which are inefficient,or rely on simplistic deep learning techniques that do not fully leverage contract semantic ***,there is ample room for improvement in terms of detection *** solve these problems,this paper proposes a vulnerability detector based on deep learning techniques,graph representation,and Transformer,called *** method first performs swapping,insertion,and symbolization operations for contract functions,increasing the amount of small sample *** line of code is then treated as a basic semantic element,and information such as control and data relationships is extracted to construct a new representation in the form of a Line Graph(LG),which shows more structural features that differ from the serialized presentation of the ***,the node information and edge information of the graph are jointly learned using an improved Transformer-GP model to extract information globally and locally,and the fused features are used for vulnerability *** effectiveness of the method in reentrancy vulnerability detection is verified in experiments,where the F1 score reaches 95.16%,exceeding stateof-the-art methods.

关键词： Vulnerability detection smart contract graph representation deep learning source code

来源：评论

学校读者我要写书评

暂无评论

Small target detection algorithm for flapping wing UAV based on improved YOLOv8 2

Small target detection algorithm for flapping wing UAV based...

引用

2nd International Symposium on Computer Applications and Information Systems, ISCAIS 2023

作者： Ma, Chen Du, Ketao Hamdulla, Askar School of Information Science and Engineering Xinjiang University Urumqi830046 China Xinjiang Key Laboratory of Signal Detection and Processing Xinjiang Urumqi China

ISBN: (纸本)9781510666665

This paper proposes an algorithm based on an improved version of YOLOv8l, which is designed for small target detection on flapping wing drones. By adding a small object detection layer and introducing Multi-head self-attention (MHSA), the algorithm effectively reduces interference from irrelevant backgrounds and enhances the network’s feature extraction performance. Experimental results on both the flapping wing dataset and the VisDrone dataset demonstrate that compared with the baseline YOLOv8l algorithm, the improved algorithm shows a 4.1% and 3.3% improvement in the mAP@.5 and mAP@.5:.95 indicators, respectively, and a 5.9% and 4% improvement on the VisDrone dataset. Particularly noteworthy is the improved algorithm’s performance on the mAP@.5 index, which achieved 50.1% on the VisDrone dataset, proving its robustness and exceptional performance in small target detection. These results illustrate the algorithm’s effectiveness and practicality, making it a valuable tool for flapping wing UAV vision applications. © 2023 SPIE.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Slice Position-shifting and Multi-scale Inter-frame Proportional fusion Network for video-based pedestrian re-identification 2

Slice Position-shifting and Multi-scale Inter-frame Proporti...

引用

2nd International Symposium on Computer Applications and Information Systems, ISCAIS 2023

作者： Du, Ketao Ma, Chen Hamdulla, Askar School of Information Science and Engineering Xinjiang University Urumqi830046 China Xinjiang Key Laboratory of Signal Detection and Processing Xinjiang Urumqi China

ISBN: (纸本)9781510666665

Different from image-based pedestrian re-identification, video-based pedestrian re-identification has more available information because of more temporal information. However, previous methods are unable to extract detailed features adequately. Although the previous methods adopted the row slicing method to extract the detailed features of the image, the slicing method was too simple and the detailed features extracted were too few. We propose a slice position shifting module (SPM), which adopts a variety of ways to slice the image, to extract the feature of each image patches separately. The feature interaction is carried out by making each patches of the image generate position-shifting. How to make time clues in pedestrian re-identification data set useful is also the research focus in this field. We propose a multi-scale inter-frame proportional fusion module (MIPM) to make the features of frame t fully fuse with the front and back frames, so as to extract more the temporal clues in the data set. We will form the above two modules into Slice position-shifting and Multi-scale inter-frame proportional fusion network(SMnet) .Full experiments on the MARS dataset show that our algorithm is very useful and can reach the leading level. © 2023 SPIE.

关键词： Image processing

来源：评论

学校读者我要写书评

暂无评论

Attention-based Dual-Branch Network for Micro-Expression Recognition with Global-Local Feature Fusion 18

Attention-based Dual-Branch Network for Micro-Expression Rec...

引用

18th IEEE International Joint Conference on Biometrics, IJCB 2024

作者： Qi, Yupeng Ibrayim, Mayire Hamdulla, Askar Xinjiang University School of Computer Science and Technology Urumqi830017 China Xinjiang Key Laboratory of Signal Detection and Processing Urumqi830017 China

ISBN: (纸本)9798350364132

Micro-expression(ME) is an uncontrollable muscle movement that appears on the face when people try to hide or inhibit their real emotions, which has the problems of short duration, small movement amplitude and uneven distribution. In order to solve the problem of localization and asymmetry in the distribution of ME features, this paper proposes a new two-branch attention network to recognize MEs, which utilizes the attention mechanism to capture global and local ME features. The network is mainly divided into three parts: data preprocessing, ME feature learning and feature fusion classification. First, the data preprocessing first extracts the ME optical flow features and then divides them into four regions, which are used as inputs to the two-branch network respectively. Second, the two-branch network uses the Inception-MSFE global multi-scale feature extraction network incorporating the attention mechanism (CBAM) and the Swin Transformer-based local feature extraction network for feature learning, respectively. Finally, MEs are predicted by fusing global and local features of MEs. Experimental validation is carried out on three datasets, CASME II, SAMM, and SMIC, which proves that Acc, UAR, and UF1 are 0.797, 0.702, and 0.698 on the SAMM dataset, respectively;Acc, UAR, and UF1 are 0.734, 0.723, and 0.729 on SMIC, respectively;and on the CASME II dataset, Acc, UAR and UF1 are 0.865, 0.872, and 0.889, respectively, which are competitive with other state-of-the-art methods. © 2024 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Conditional Generative Adversarial Defogging Algorithm Based on Polarization Characteristics 33

Conditional Generative Adversarial Defogging Algorithm Based...

引用

第33届中国控制与决策会议

作者： Jingjing Zhang Kangsheng Bao Xin Zhang Fudong Nian Teng Li Yuzhou Zeng Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education (Anhui university) Key Laboratory of Polarized Light Imaging and Detection Technology in Anhui Province Hefei No.6 High School Hefei University

ISBN: (纸本)9781665431293

To overcome image degradation under the conditions of haze,and fog,a method using conditional generative adversarial defogging algorithm based on polarization characteristic is *** original images with different polarization angles were obtained from the original image,and then the polarization images were characterized using Stokes *** the relationship between Stokes vector and polarization image,each polarization image with different angles is input into the same network to extract *** the same time,the enhanced network is used to extract the characteristics of the fog area in the polarization image,and the polarization information is extracted by layer jump connection,which is fused with the image features of different *** constructing the loss function and obtaining the optimal solution,the fog-free image is finally *** results show that a clear image can be reconstructed in fog situations by using conditional generative adversarial network-based on polarization characteristics,and the structural similarity is improved by about 10%,the peak signal to noise ratio is increased by about 0.5.

关键词： polarization characteristics conditional generative adversarial network image processing image defogging feature fusion enhanced network

来源：评论

学校读者我要写书评

暂无评论

End-to-end Speech Enhancement Using Self-Attention Generative Adversarial Networks 6

End-to-end Speech Enhancement Using Self-Attention Generativ...

引用

6th International Symposium on Computer and Information processing Technology, ISCIPT 2021

作者： Cao, Zhonghui Huang, Zhihua Xinjaing University College of Information Science and Engineering Key Laboratory of Signal Detection and Processing in Xinjiang Uygur Autonomous Region Urumqi830001 China

ISBN: (纸本)9781665441377

Generative adversarial networks (GAN) achieve a good level of success in the speech enhancement (SE) task in recent years. However, traditional GAN for SE generates enhanced speech only as a function of local points, such that the model has difficulity in capturing long-range dependency and non-local information. In this paper, a model named self-attention GAN (ASEGAN) is proposed to estabilish connections between every sample and the rest samples in the time domain. Attention mechanism is used to model long-range dependency modeling for SE tasks. Armed with self-attention, the generator can generate the enhanced speech in which fine details at every sample are carefully coordinated with fine details in distant portions of the speech. Moreover, the discriminator can also more accurately enforce constraints on the global speech structure, thus the quality of enhanced speech by generator is better. Experimental results demonstrate that the proposed approach outperforms the competing methods measured by objective quality and speech intelligibility. © 2021 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

A Lightweight UAV Visual Obstacle Avoidance Algorithm Based on Improved YOLOv8

引用

Computers, Materials & Continua 2024年第11期81卷 2607-2627页

作者： Zongdong Du Xuefeng Feng Feng Li Qinglong Xian Zhenhong Jia College of Computer Science and Technology Xinjiang UniversityUrumqi830046China Signal Detection and Processing Autonomous Region Key Laboratory Xinjiang UniversityUrumqi830046China Xinjiang Uygur Autonomous Region Research Institute of Measurement and Testing Urumqi830000China

The importance of unmanned aerial vehicle(UAV)obstacle avoidance algorithms lies in their ability to ensure flight safety and collision avoidance,thereby protecting people and *** propose UAD-YOLOv8,a lightweight YOLOv8-based obstacle detection algorithm optimized for UAV obstacle *** algorithm enhances the detection capability for small and irregular obstacles by removing the P5 feature layer and introducing deformable convolution v2(DCNv2)to optimize the cross stage partial bottleneck with 2 convolutions and fusion(C2f)***,it reduces the model’s parameter count and computational load by constructing the unite ghost and depth-wise separable convolution(UGDConv)series of lightweight convolutions and a lightweight detection *** on this,we designed a visual obstacle avoidance algorithm that can improve the obstacle avoidance performance of UAVs in different *** particular,we propose an adaptive distance detection algorithm based on obstacle attributes to solve the ranging problem for multiple types and irregular obstacles to further enhance the UAV’s obstacle avoidance *** verify the effectiveness of the algorithm,the UAV obstacle detection(UAD)dataset was *** experimental results show that UAD-YOLOv8 improves mAP50 by 3.4%and reduces GFLOPs by 34.5%compared to YOLOv8n while reducing the number of parameters by 77.4%and the model size by 73%.These improvements significantly enhance the UAV’s obstacle avoidance performance in complex environments,demonstrating its wide range of applications.

关键词： Unmanned aerial vehicle obstacle detection obstacle avoidance algorithm

来源：评论

学校读者我要写书评

暂无评论

Application of multi-classification method of skin cancer based on dermoscopic image 21

Application of multi-classification method of skin cancer ba...

引用

2nd International Symposium on Artificial Intelligence for Medicine Sciences, ISAIMS 2021

作者： Chen, Qian Li, Min Chen, Cheng Chen, Chen Lv, Xiaoyi College of Software Key Laboratory of Software Engineering Technology Key Laboratory of Signal Detection and Processing Xinjiang University Urumqi China College of Information Science and Engineering Xinjiang University Urumqi China

ISBN: (纸本)9781450395588

As a kind of cancer with high incidence, skin cancer seriously threatens people's life and health. Early detection, early diagnosis, and early treatment are one of the effective ways to increase the survival rate of patients with skin diseases. Therefore, this paper used the ResNet50 model as a feature extractor based on deep learning, and combined machine learning algorithms to explore the heterogeneity among multi-type of skin cancer, and tried to construct the best performance computer-aided diagnosis model. The research first used preprocessing techniques such as hair noise removal and data enhancement, and then achieved a classification accuracy of 90.497% on the public data set of ISIC2019. The proposed model effectively relieves the huge work pressure of dermatologists, and provides a reference for the better use of dermoscopic images for intelligent diagnosis and classification of skin cancer. © 2021 ACM.

关键词： Computer aided diagnosis

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：