检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Zhang, Zhihao Chen, Yiwei Zhang, Weizhan Yan, Caixia Zheng, Qinghua Wang, Qi Chen, Wangdu School of Computer Science and Technology Xi'an Jiaotong University Key Laboratory of Intelligent Networks and Network Security Ministry of Education Xi'an Jiaotong University Xi’an China School of Computer Science and Technology Xi'an Jiaotong University & National Engineering Lab for Big Data Analytics Xi'an Jiaotong University Xi’an China MIGU Video Shanghai China

Viewport prediction is a crucial aspect of tile-based 360◦ video streaming system. However, existing trajectory based methods lack of robustness, also oversimplify the process of information construction and fusion between different modality inputs, leading to the error accumulation problem. In this paper, we propose a tile classification based viewport prediction method with Multi-modal Fusion Transformer, namely MFTR. Specifically, MFTR utilizes transformer-based networks to extract the long-range dependencies within each modality, then mine intra- and inter-modality relations to capture the combined impact of user historical inputs and video contents on future viewport selection. In addition, MFTR categorizes future tiles into two categories: user interested or not, and selects future viewport as the region that contains most user interested tiles. Comparing with predicting head trajectories, choosing future viewport based on tile's binary classification results exhibits better robustness and interpretability. To evaluate our proposed MFTR, we conduct extensive experiments on two widely used PVS-HM and Xu-Gaze dataset. MFTR shows superior performance over state-of-the-art methods in terms of average prediction accuracy and overlap ratio, also presents competitive computation efficiency. © 2023, CC BY.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Multi-classification of Android Applications Based on Convolutional Neural networks 20

Multi-classification of Android Applications Based on Convol...

引用

4th International Conference on computer Science and Application Engineering, CSAE 2020

作者： Wang, Zhiqiang Li, Gefei Chi, Yaping Beijing Electronic Science and Technology Institute Beijing China and State Information Center and Key Lab of Information Network Security Ministry of Public Security Beijing China State Information Center Beijing China Beijing Electronic Science and Technology Institute Beijing China

ISBN: (纸本)9781450377720

Google Play App Store, Huawei App Market, Xiaomi App Store, etc. are the main sources for users to download applications. The application category classification is usually based on the category specified by the developer when uploading or by analyzing the description provided by the developer. However, the process is easily manipulated by malicious developers to evade detection. With the popularity of Android phones, the number of Android applications has exploded. How to quickly and accurately classify applications automatically and improve management efficiency is crucial. This paper proposed a multi-classification framework for Android applications based on convolutional neural networks. By extracting multiple static features, we combined natural language processing and deep learning to achieve a classification accuracy of 99.9064%, and the training time was only 158s. © 2020 ACM.

关键词： Static analysis

来源：评论

学校读者我要写书评

暂无评论

Graph Structure Guided Transformer for Semantic Segmentation

Graph Structure Guided Transformer for Semantic Segmentation

引用

International Conference on Tools for Artificial Intelligence (ICTAI)

作者： Luyang Qian Canlong Zhang Zhixin Li Zhiwen Wang School of Computer Science and Engineering Guangxi Normal University Guilin China Guangxi Key Lab of Multi-source Information Mining & Security Guilin China School of Computer Science and Technology Guangxi University of Science and Technology Liuzhou China

Segmentation is an essential operation of image processing, and utilizing long-range context information is the key for pixel-wise prediction tasks such as semantic segmentation. Convolutional Neural networks (CNNs) are good at modeling local relationships through convolutional operations, but they are often inefficient in capturing global relationships between distant regions and require stacking multiple convolutional lay-ers. Utilizing the advantages of transformer in modeling long-range dependency, this paper proposes a novel Graph Structure Guided Transformer (GSGT) to realize semantic segmentation. Different from the previous methods that hard-divide the image in a regular grid manner, our graph projection method maps the two-dimensional feature map into a graph structure according to certain semantic relevance, so as to meet the data structure form required by the transformer. Meanwhile, to fully utilize the graph structure information, we also propose a graph embedding attention module, which utilizes the local topology of the graph structure to complement the global context of transformer. Moreover, GSGT is easy to be incorporated with various CNN backbones and transformer model variants to significantly improve the segmentation accuracy and convergence speed. Experiments on Cityscapes, VOC and ADE20K datasets demonstrate that the proposed method performs well in semantic seamentation task.

关键词： Semantic segmentation Semantics Stacking network architecture Transformers Data structures Robustness

来源：评论

学校读者我要写书评

暂无评论

Identifying driver genes in cancer based on Pareto optimality consensus

Identifying driver genes in cancer based on Pareto optimalit...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Zheng Deng Jingli Wu Xiaorong Chen Gaoshi Li College of Computer Science Information Technology Guangxi Normal University Guilin China Guangxi Key Lab of Multi-source Information Mining & Security Guangxi Normal University Guilin China Guangxi Key Laboratory of Machine Vision Intelligent Control Wuzhou University Wuzhou China

ISBN: (数字)9781665468190

ISBN: (纸本)9781665468206

An important issue in cancer genomics is the identification of driver genes. It is significant for the discovery of key biomarkers and the development of effective personalized therapies. In this paper, a computated method PGScore is proposed. It scores genes at multilayer and integrates the scores to identify cancer driver genes based on Pareto Optimality Consensus(POC) strategy. PGScore uses random walks to reevaluate gene mutations, and integrates differential expression of mRNA and miRNA in normal and cancer samples. It measures the centrality of the gene in the network according to the weight of its direct and indirect neighbors, and finally integrates the above layers to get the final priority of the genes. We compare PGScore with state-of-the-art cancer driver genes prioritization methods on two real cancer datasets. The results show that PGScore can obtain better performance in identification accuracy and the partial area under the ROC(pAUC) curve on multiple reference databases.

关键词： Weight measurement Databases Medical treatment Genomics Pareto optimization Biomarkers Nonhomogeneous media

来源：评论

学校读者我要写书评

暂无评论

Deepfake Detection: A Comprehensive Survey from the Reliability Perspective

arXiv

引用

arXiv 2022年

作者： Wang, Tianyi Liao, Xin Chow, Kam Pui Lin, Xiaodong Wang, Yinglong Department of Computer Science The University of Hong Kong Hong Kong College of Computer Science and Electronic Engineering Hunan University China School of Computer Science University of Guelph Canada Key Laboratory of Computing Power Network and Information Security Ministry of Education Qilu University of Technology Shandong Academy of Sciences China

The mushroomed Deepfake synthetic materials circulated on the internet have raised a profound social impact on politicians, celebrities, and individuals worldwide. In this survey, we provide a thorough review of the existing Deepfake detection studies from the reliability perspective. We identify three reliability-oriented research challenges in the current Deepfake detection domain: transferability, interpretability, and robustness. Moreover, while solutions have been frequently addressed regarding the three challenges, the general reliability of a detection model has been barely considered, leading to the lack of reliable evidence in real-life usages and even for prosecutions on Deepfake-related cases in court. We, therefore, introduce a model reliability study metric using statistical random sampling knowledge and the publicly available benchmark datasets to review the reliability of the existing detection models on arbitrary Deepfake candidate suspects. Case studies are further executed to justify the real-life Deepfake cases including different groups of victims with the help of the reliably qualified detection models as reviewed in this survey. Reviews and experiments on the existing approaches provide informative discussions and future research directions for Deepfake detection. Copyright © 2022, The Authors. All rights reserved.

关键词： Data reliability

来源：评论

学校读者我要写书评

暂无评论

Motion compensation and object detection for neuromorphic camera

Motion compensation and object detection for neuromorphic ca...

引用

2021 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2021

作者： Wan, Yuxin Fei, Rong Tang, Yu Bai, Xueru Xie, Guo Li, Aimin Xi'An University of Technology School of Computer Science and Engineering Xi'an China Xi'An University of Technology Shaanxi Key Laboratory for Network Computing and Security Technology School of Computer Science and Engineering Xi'an China Xidian University Guangzhou Institute Guangzhou China Xi'An University of Technology School of Computer Science and Engineering Xi'an China Xi'An University of Technology School of Automation and Information Engineering Xi'an China

ISBN: (纸本)9781665401265

Compared to conventional cameras, the new type of vision camera-neuromorphic cameras, which can avoid motion blur and have the advantages of high spatiotemporal resolution, high dynamic range, low latency, etc. In this paper, two motion compensation methods are introduced for operating event flow based on differential neuromorphic camera, one is motion compensation based on event counting image and time image, another is motion compensation based on image of warped events. Comprehensive experimental study is carried on two datasets, the motion compensation method based on event counting image and time image is better at generating clear motion compensation images, highlighting moving objects inconsistent with the background motion, while the motion compensation method based on image of warped events tends to generate motion compensated images of moving objects with more prominent or clearer edges. Simultaneously, two motion compensation methods are further applied to realize the object detection method based on threshold or maximum contrast. The former method can be adapted in many cases, while the latter method can well detect the translational moving target. © 2021 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

ATEDU-NET: An Attention-Embedded Deep Unet for multi-disease diagnosis in chest X-ray images, breast ultrasound, and retina fundus

引用

computers in Biology and Medicine 2025年 186卷 109708-109708页

作者： Ejiyi, Chukwuebuka Joseph Qin, Zhen Agbesi, Victor K. Ejiyi, Makuachukwu Bennedith Chikwendu, Ijeoma A. Bamisile, Oluwatoyosi F. Onyekwere, Favour Ezinne Bamisile, Olusola O. College of Nuclear Technology and Automation Engineering Chengdu University of Technology Sichuan 610059 China Network and Data Security Key Laboratory of Sichuan Province University of Electronic Science and Technology of China Sichuan Chengdu China School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China Pharmacy Department University of Nigeria Nsukka Enugu State Nsukka Nigeria School of Information and Communication Engineering University of Electronic Science and Technology of China Chengdu China

In image segmentation for medical image analysis, effective upsampling is crucial for recovering spatial information lost during downsampling. This challenge becomes more pronounced when dealing with diverse medical image modalities, which can significantly impact model performance. Plain and standard skip connections, widely used in most models, often fall short of maintaining high segmentation accuracy across different modalities, because essential spatial information transferred from the encoder to the decoder is lost. Inspired by these limitations, the Attention-Embedded Deep UNet (ATEDU-Net) is presented here, an innovative framework designed and tested on diverse medical image modalities, including X-ray, breast ultrasound, and retinal fundus images. ATEDU-Net features a unique architecture that combines progressive context refinement modules (PCRM) and global context modules (GCM) within a U-shaped network structure with Convgroup blocks which facilitate the integration of convolutional operations. This allows ATEDU-Net to autonomously capture rich spatial details and crucial contextual information from input images. The GCM captures essential contextual information for informed decision-making, while the PCRM enhances feature attention, resulting in precise and robust segmentation. The experimentation and analysis demonstrate that ATEDU-Net promises to be a powerful tool for medical professionals, aiding in the early detection of chest-related diseases, accurate localization of breast tumors, and early identification of eye diseases. This, in turn, contributes significantly to the formulation of optimal therapeutic strategies, enhancing patient care and outcomes. The versatility of ATEDU-Net is further highlighted by its ability to analyze medical images across various modalities, making it well-suited for the complex task of medical image analysis in diverse clinical scenarios. © 2025 Elsevier Ltd

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

An edge enhancement-based fusion method of infrared and visible images in low light

An edge enhancement-based fusion method of infrared and visi...

引用

Signal, information and Data Processing (ICSIDP), IEEE International Conference on

作者： Xiang Gao Xiyan Wang Hanbin Bao Qian Li Guohua Lv Faculty of Comupter Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Bresee Technology Co. Ltd. Jinan China Shandong Grain Group Co. Ltd. Jinan China Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (数字)9798331515669

ISBN: (纸本)9798331515676

The combination of infrared and visible images can result in the generation of a single image with a high degree of detail and important targets in a variety of scenes, which is beneficial for human recognition. However, in low-light environments, low-intensity visible images tend to blur valuable information, which is often overlooked. This results in the loss of important information. While existing methods address the issue of low illumination and highlight the illumination, a considerable amount of structural information is lost when adjusting illumination, resulting in the omission of texture details. To solve aforementioned problems, we proposes a method for edge enhancement in low-illumination scenes. This approach aims to minimise the loss of edge information while simultaneously enhancing the illumination, thereby producing fusion images with enhanced texture detail. The initial step involves the design of an illumination enhancement module, which is employed to segregate the compromised illumination present from the scene information. Given the fact that image edge information has the capacity for effective structural modeling, a low-light visible image edge extraction network is designed to model structural information, which can accurately highlight important structural information and insert it in fused images. The results produced by this method have better visual perception and minimize structural loss. Extensive experiments demonstrate that the method outperforms SOTA methods in term of visual quality and quantitative metrics.

关键词： Reflectivity Measurement Visualization Target recognition Image edge detection Lighting Data mining Image reconstruction Image fusion Visual perception

来源：评论

学校读者我要写书评

暂无评论

Multi-keyword Cipher-text Retrieval Method for Smart Grid Edge Computing 3

Multi-keyword Cipher-text Retrieval Method for Smart Grid Ed...

引用

2020 3rd International Symposium on Power Electronics and Control Engineering, ISPECE 2020

作者： Zhu, Jing Wu, Tao Li, Jintao Liu, Yanbin Jiang, Qixin School of Communication and Information Engineering Chongqing University of Posts and Telecommunications China School of Cybersecurity and Information Law Chongqing University of Posts and Telecommunications Chongqing China School of Computer Science Chongqing University of Posts and Telecommunications Chongqing China Guangdong Provincial Key Laboratory of Power System Network Security Guangzhou China Electric Power Institute CSG Guangzhou China

With the continuous deepening of China's power grid intelligent upgrading and the rise of edge computing technology, power grid terminals can carry out data storage and intelligent calculation at the edge of the power grid. However, the generated data by users may cause the leakage of user privacy information. The power grid edge system can retrieve the user's electricity data on demand, so as to improve the level of privacy protection and reduce the demand of transmission and computing resources through the localized storage of data. Therefore, how to carry out privacy protection and on-demand retrieval is a key problem to realize the intelligent power grid edge. In this paper, a multi-keyword cipher-text retrieval scheme (MCR- SGEC) for smart grid edge computing is proposed, which can achieve accurate matching of index and trap door, and has low spatial complexity. At the same time, on this basis, a multi-keyword fuzzy cipher-text retrieval method for smart grid edge computing (MFSE-SGEC) is proposed, which allows users to have spelling errors, which makes the user experience better. © Published under licence by IOP Publishing Ltd.

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

A Parallelizable Counterfactual Generation Method Based on Gradient Optimization

A Parallelizable Counterfactual Generation Method Based on G...

引用

International Conference on Parallel and Distributed Systems (ICPADS)

作者： Haorun Ding Xuesong Jiang Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China Quan Cheng Laboratory Jinan China State Key Laboratory of High-end Server & Storage Technology Jinan China

Post-hoc explanations are important for people to understand the predictions of explanation models. One class of methods in post-hoc explanation is the generation of counterfactuals, where a hypothetical example is obtained by perturbing the inputs to show how one could obtain a different prediction from the decision model. Counter-factual explanations should satisfy several properties: One is that counterfactuals generated under specific scenarios and constraints should be feasible for users, i.e., they should accommodate different causal constraints. The other is that it is more desirable for users to have a wider variety of viable examples, i.e., counterfactual diversity. To this end, we propose a parallelizable method based on gradient optimization. We partition the input feasible domains, perform counterfactual generation independently for each feasible domain, and then parallelize the counterfactual generation process for each feasible domain. Experimental results show that our approach effectively improves the diversity, sparsity, and proximity of the generated counterfactual instances on the public datasets Adult-Income, Lending-Club, German-Credit, and COMPAS compared to other models.

关键词：

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：