检索结果-内蒙古大学图书馆

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

作者： Kaijun Deng Dezhi Zheng Jindong Xie Jinbao Wang Weicheng Xie Linlin Shen Siyang Song Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Guangdong Provincial Key Laboratory of Intelligent Information Processing Department of Computer Science University of Exeter

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Accurately synthesizing talking face videos and capturing fine facial features for individuals with long hair presents a significant challenge. To tackle these challenges in existing methods, we propose a decomposed per-embedding Gaussian fields (DEGSTalk), a 3D Gaussian Splatting (3DGS)-based talking face synthesis method for generating realistic talking faces with long hairs. Our DEGSTalk employs Deformable Pre-Embedding Gaussian Fields, which dynamically adjust pre-embedding Gaussian primitives using implicit expression coefficients. This enables precise capture of dynamic facial regions and subtle expressions. Additionally, we propose a Dynamic Hair-Preserving Portrait Rendering technique to enhance the realism of long hair motions in the synthesized videos. Results show that DEGSTalk achieves improved realism and synthesis quality compared to existing approaches, particularly in handling complex facial dynamics and hair preservation. Our code is available at https://***/CVI-SZU/DEGSTalk.

关键词： Hair Training Three-dimensional displays Dynamics Signal processing Rendering (computer graphics) Noise measurement Speech processing Faces Videos

来源：评论

学校读者我要写书评

暂无评论

ARNET: ACTIVE-REFERENCE NETWORK FOR FEW-SHOT IMAGE SEMANTIC SEGMENTATION

ARNET: ACTIVE-REFERENCE NETWORK FOR FEW-SHOT IMAGE SEMANTIC ...

引用

2021 IEEE International Conference on Multimedia and Expo, ICME 2021

作者： Shi, Guangchen Wu, Yirui Palaiahnakote, Shivakumara Pal, Umapada Lu, Tong College of Computer and Information Hohai University China Department of Computer System and Information Technology University of Malaya Malaysia Computer Vision and Pattern Recognition Unit Indian Statistical Institute India National Key Lab for Novel Software Technology Nanjing University China

ISBN: (纸本)9781665438643

To make predictions on unseen classes, few-shot segmentation becomes a research focus recently. However, most methods build on pixel-level annotation requiring quantity of manual work. Moreover, inherent information on same-category objects to guide segmentation could have large diversity in feature representation due to differences in size, appearance, layout, and so on. To tackle these problems, we present an active-reference network (ARNet) for few-shot segmentation. The proposed active-reference mechanism not only supports accurately co-occurrent objects in either support or query images, but also relaxes high constraint on pixel-level labeling, allowing for weakly boundary labeling. To extract more intrinsic feature representation, a category-modulation module (CMM) is further applied to fuse features extracted from multiple support images, thus forgetting useless and enhancing contributive information. Experiments on PASCAL-5i dataset show the proposed method achieves a m-IOU score of 56.5% for 1-shot and 59.8% for 5-shot segmentation, being 0.5% and 1.3% higher than current state-of-the-art method. © 2021 IEEE

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

SCALABLE LINK PREDICTION IN TWITTER USING SELF-CONFIGURED FRAMEWORK

arXiv

引用

arXiv 2022年

作者： Daud, Nur Nasuha Hamid, Siti Hafizah Ab Seri, Chempaka Saadoon, Muntadher Anuar, Nor Badrul Department of Software Engineering Faculty of Computer Science and Information Technology University of Malaya Kuala Lumpur50603 Malaysia Department of Computer System and Technology Faculty of Computer Science and Information Technology University of Malaya Kuala Lumpur50603 Malaysia

Link prediction analysis becomes vital to acquire a deeper understanding of events underlying social networks interactions and connections especially in current evolving and large-scale social networks. Traditional link prediction approaches underperformed for most large-scale social networks in terms of its scalability and efficiency. Spark is a distributed open-source framework that facilitate scalable link prediction efficiency in large-scale social networks. The framework provides numerous tunable properties for users to manually configure the parameters for the applications. However, manual configurations open to performance issue when the applications start scaling tremendously, which is hard to set up and expose to human errors. This paper introduced a novel Self-Configured Framework (SCF) to provide an autonomous feature in Spark that predicts and sets the best configuration instantly before the application execution using XGBoost classifier. SCF is evaluated on the Twitter social network using three link prediction applications: Graph Clustering (GC), Overlapping Community Detection (OCD), and Redundant Graph Clustering (RGD) to assess the impact of shifting data sizes on different applications in Twitter. The result demonstrates a 40% reduction in prediction time as well as a balanced resource consumption that makes full use of resources, especially for limited number and size of clusters. © 2022, CC BY.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Improved Mutation Testing Framework by Augmenting Codeannotation for Android Applications

SSRN

引用

SSRN 2023年

作者： Ahmad, Johanna Saedudin, Rd. Rohmat Jie, Lim Jing Hassan, Rohayanti binti Kasim, Shahreen binti Telkom University Telekomunikasi Terusan Buah Batu Indonesia Bandung40257 Indonesia Department of Software Engineering Faculty of Computing Universiti Teknologi Malaysia UTM Skudai Johor81310 Malaysia Department of Information Security and Web Technology Faculty of Computing Science and Information Technology Universiti Tun Hussein Onn Malaysia UTHM Parit Raja Johor86400 Malaysia

This study is conducted in software testing based on the problem arising from mutation testing in Android applications. Although researchers show massive interest in searching for better Android testing approaches, there is still an insufficiency of usable and practical techniques to deliver a reasonable number of effective tests, especially in Android applications. Mutation testing injects code changes to check whether tests can identify the differences. Due to the challenges of the Android application, this research aimed to propose a set of mutation operators that can discover more faults and simulate more categories during the mutation testing processes. This study suggested an Android-based code annotation that combined Java code annotation and Android code annotation to generate more variety of mutant operators. These mutant operators were then merged with the mutant operators that had been developed earlier using the standard Android code testing. This improved set of mutant operators was tested using three different groups of Android applications: Insta Material, Telecine, and Leafpic. The proposed method generated fewer non-compliable mutants in the Leafpic application, with an average mutation score of 97.1% and more mutants in the Telecine application, with an average mutation score of 98.6%. In conclusion, the effectiveness of the improved mutation testing performance in Android applications was encouraging. The proposed method is likely to discover more bugs in Android applications and improve the overall effectiveness of mutation testing. © 2023, The Authors. All rights reserved.

关键词： software testing

来源：评论

学校读者我要写书评

暂无评论

A Lightweight CNN-Based Pothole Detection Model for Embedded systems Using Knowledge Distillation 21

A Lightweight CNN-Based Pothole Detection Model for Embedded...

引用

21st International Conference on New Trends in Intelligent software Methodologies, Tools and Techniques, SoMeT 2022

作者： Musa, Aminu Hassan, Mohammed Hamada, Mohamed Kakudi, Habeebah Adamu Amin, Md. Faizul Ibne Watanobe, Yutaka Department of Computer Science Federal University Dutse Nigeria Faculty of Computer Sci. & Info. Technology Bayero University Kano Nigeria Software Engineering Lab University of Aizu Japan Graduate School of Computer Science University of Aizu Japan Division of Information System University of Aizu Japan

ISBN: (纸本)9781643683164

Recent breakthroughs in computer vision have led to the invention of several intelligent systems in different sectors. In transportation, this advancement led to the possibility of proposing autonomous vehicles. This recent technology relies heavily on wireless sensors and Deep learning. For an autonomous vehicle to navigate safely on highways, the vehicle needs equipment to aid with detecting road anomalies such as potholes ahead of time. The massive improvement in computer vision models such as Deep Convolutional Neural networks (DCNN) or vision transformers (ViT) resulted in many success stories and tremendous breakthroughs in object detection tasks;this enabled the use of such models in different application areas. But many of the reported results are theoretical and unrealistic in real-life. Usually, the nature of these models is extensive;they are trained on High-performance computers or cloud computing environments with GPUs, which challenge their usage on edge devices. However, to come up with a light model that can fit into embedded devices, the model size has to be reduced significantly so that the performance will not be affected. Therefore, this paper proposes a lightweight model of pothole detection for an embedded device. The model achieved a state-of-the-art accuracy of 98%, with the number of parameters reduced to more than 70% compared with a deep CNN model;the model can be trained and deployed on embedded devices such as smartphones efficiently. © 2022 The authors and IOS Press. All rights reserved.

关键词： Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

An Overview Analysis of Authentication Mechanism in Microservices-Based software Architecture: A Discussion Paper

An Overview Analysis of Authentication Mechanism in Microser...

引用

International Conference on software Engineering and Computer systems (ICSECS)

作者： Chang Hoong Jack See Kwee Teck Lim Tong Ming Ding Ying Hong Department of Software Engineering And Technology Tunku Abdul Rahman University of Management and Technology Kuala Lumpur Malaysia Department of Information System And Security Tunku Abdul Rahman University of Management and Technology Kuala Lumpur Malaysia Department of Centre For Business Incubation And Entrepreneurial Venture Tunku Abdul Rahman University of Management and Technology Kuala Lumpur Malaysia

Microservices-based software architecture promotes scalability and flexibility by breaking down a software application into smaller modules and making it more independent and loosely coupled services compared to monolith systems. However, securing microservices in a distributed nature has become one of the challenges. Authentication is one of the most critical components that should be focused in the microservices security measures. It helps to identify that only authenticated personnel and services can access sensitive information and secure the trust between microservices. This discussion paper aims to provide an overview analysis and extensive understanding on the authentication mechanism in microservices-based software architecture. In this study, we explore different authentication mechanisms including Mutual Transport Layer Security (mTLS), Token based authentication and API Gateway authentication. This study examines the strengths and limitations of different authentication mechanisms in microservices-based software architecture. It also emphasizes the importance of authentication and the need for having a well-designed authentication mechanism to ensure the integrity and security of microservices-based software architecture is crucial.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Rethinking Causal Relationships Learning in Graph Neural Networks

arXiv

引用

arXiv 2023年

作者： Gao, Hang Yao, Chengyu Li, Jiangmeng Si, Lingyu Jin, Yifan Wu, Fengge Zheng, Changwen Liu, Huaping Science and Technology on Integrated Information System Laboratory Institute of Software Chinese Academy of Sciences China University of Chinese Academy of Sciences China State Key Laboratory of Intelligent Game China Department of Computer Science and Technology Tsinghua University China

Graph Neural Networks (GNNs) demonstrate their significance by effectively modeling complex interrelationships within graph-structured data. To enhance the credibility and robustness of GNNs, it becomes exceptionally crucial to bolster their ability to capture causal relationships. However, despite recent advancements that have indeed strengthened GNNs from a causal learning perspective, conducting an in-depth analysis specifically targeting the causal modeling prowess of GNNs remains an unresolved issue. In order to comprehensively analyze various GNN models from a causal learning perspective, we constructed an artificially synthesized dataset with known and controllable causal relationships between data and labels. The rationality of the generated data is further ensured through theoretical foundations. Drawing insights from analyses conducted using our dataset, we introduce a lightweight and highly adaptable GNN module designed to strengthen GNNs' causal learning capabilities across a diverse range of tasks. Through a series of experiments conducted on both synthetic datasets and other real-world datasets, we empirically validate the effectiveness of the proposed module. The codes are available at https://***/yaoyao-yaoyao-cell/CRCG. © 2023, CC BY.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Analytical Models for QoT Estimations in Super-C and Super-C + L Bands Optical Transmission systems

Analytical Models for QoT Estimations in Super-C and Super-C...

引用

2023 Conference on Lasers and Electro-Optics, CLEO 2023

作者： Yan, Baoluo Sun, Yijun Zhou, Ziwen Liu, Hong Wang, Hongya Huan, Chen Zhao, Zhiyong Feng, Lipeng Zhang, Anxu Feng, Zhenhua Shi, Hu WDM System Department Wireline Product R&D Institute ZTE Corp. Beijing100029 China State Key Laboratory of Mobile Network and Mobile Multimedia Technology 518055 China School of Software Engineering Chongqing University of Posts and Telecommunications Chongqing400065 China School of Optical and Electronic Information Wuhan National Laboratory for Optoelectronics Optics Valley Laboratory Huazhong University of Science and Technology Wuhan China China Telecom Research Institute Beijing102209 China

We propose a novel physical model-based QoT estimation with achieved OSNR estimation error 1.5 dB in primary paths and OSNR prediction error 1.76 dB in unestablished lightpaths for both super-C bands and super-C+L ban... 详细信息

ISBN: (纸本)9781957171258

关键词： Light transmission

来源：评论

学校读者我要写书评

暂无评论

Flying sensor network optimization using bee intelligence for internet of things

Flying sensor network optimization using bee intelligence fo...

引用

Intelligent systems Conference, IntelliSys 2020

作者： Salam, Abdu Javaid, Qaisar Ali, Gohar Ahmad, Fahad Ahmad, Masood Wahid, Ishtiaq Department of Computer Science and Software Engineering International Islamic University Islamabad Islamabad Pakistan Department of Information System and Technology Sur University Sur Oman Department of Computer Science Abdul Wali Khan University Mardan Mardan Pakistan

ISBN: (纸本)9783030551896

Flynig sensor network (FSN) for internet of things (IoT) consist of flying nodes called sensors and ground segments. The flying nodes may be operated manually or it may be automated devices. The flying segment of IoT has different nature compared to ordinary mobile sensor network. The flying speed and diverse directions of nodes make it harder to route the sensor information in a desired way. The data may be collected on the basis of contract opportunities. Here the timely delivery may not be guaranteed. To ensure the desired operation of the FSN, the delivery of data to the base station either deployed in the air or on the ground segment must be ensured in an efficient manner. In this paper, the mating intelligence of bees is used to ensure the delivery of data. The energy consumption is reduced by reducing the amount of control messages and transmitting redundant information. The network lifetime is increased. Simulation is conducted to evaluate the performance of the proposed scheme. The simulation results show that the proposed scheme outperforms existing schemes under consideration. © Springer Nature Switzerland AG 2021.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Digital forensics for the socio-cyber world (DF-SCW): A novel framework for deepfake multimedia investigation on social media platforms

引用

Egyptian Informatics Journal 2024年 27卷

作者： Ayub Khan, Abdullah Chen, Yen-Lin Hajjej, Fahima Ahmed Shaikh, Aftab Yang, Jing Soon Ku, Chin Yee Por, Lip Department of Computer Science and Information Technology Benazir Bhutto Shaheed University Lyari Sindh Karachi75660 Pakistan Department of Computer Science Sindh Madressatul Islam University Sindh Karachi74000 Pakistan Department of Computer Science and Information Engineering National Taipei University of Technology Taipei106344 Taiwan Department of Software Engineering College of Computer and Inf. Sci. Princess Nourah bint Abdulrahman University P.O. Box 84428 Riyadh11671 Saudi Arabia Department of Computer System and Technology Faculty of Computer Science and Information Technology Universiti Malaya Kuala Lumpur50603 Malaysia Department of Computer Science Universiti Tunku Abdul Rahman Kampar31900 Malaysia

Owing to the major development of social media platforms, the usage of technological adaptation increases by means of editing software tools. Posting media in social communication environments has become one of our common daily routines. Before posting, various editing generators are used to manipulate pixel values, such as for enhancing brightness and contrast. Undoubtedly, this software helps bring posting media from ordinary to outstanding. But such a type of editing crosses the line in terms of creating fakes—anything that comes from anywhere and does not retain its originality anyway. It poses a series of issues in the process of multimedia forensics investigation and chain of custody. In order to restrict the attempts at deep faking and make the investigation hierarchy more effective, efficient, and reliable in the socio-cyber space (SCS), this paper presents a novel framework called DF-SCW. A digital forensics-enabled socio-cyber world with artificial intelligence (AI), especially deep neural networks (DNNs), for detecting and analyzing deep fake media investigations on social media platforms. It compares pixels with their neighboring values in the same media (such as images and videos) to identify information about the original one. There is a media flag designed to filter out malicious and dangerous attempts, like a powerful leader declaring war. Putting flags on such fakes helps digital investigators resist sharing the posts. In addition, the other prospect of this research is to make the digital forensics ecosystem more appropriate to take qualitative judgments in real-time while media is uploaded on social media platforms. The simulation of the proposed DF-SCW is tested on three different platforms, such as Instagram, Facebook, and Twitter. Through the experiment, the DF-SCW outperformed in terms of detection, identification, and analysis of deepfake media by an increased rate of 3.77%. © 2024

关键词： Social networking (online)

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：