检索结果-内蒙古大学图书馆

IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

作者： Zihan Wang Siyang Song Cheng Luo Yuzhi Zhou Shiling Wu Weicheng Xie Linlin Shen Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen University School of Computing and Mathematical Sciences University of Leicester

This paper presents our Facial Action Units (AUs) detection submission to the fifth Affective Behavior Analysis in-the-wild Competition (ABAW). Our approach consists of three main modules: (i) a pre-trained facial representation encoder which produce a strong facial representation from each input face image in the input sequence; (ii) an AU-specific feature generator that specifically learns a set of AU features from each facial representation; and (iii) a spatio-temporal graph learning module that constructs a spatio-temporal graph representation. This graph representation describes AUs contained in all frames and predicts the occurrence of each AU based on both the modeled spatial information within the corresponding face and the learned temporal dynamics among frames. The experimental results show that our approach outperformed the baseline and the spatio-temporal graph representation learning allows our model to generate the best results among all ablated systems. Our model ranks at the 4th place in the AU recognition track at the 5th ABAW Competition. Our code is publicly available at https://***/wzh125/ABAW-5.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Improved quantum linear system solver via quantum phase discrimination

引用

The European Physical Journal Special Topics 2025年 1-11页

作者： Liu, Zihao Li, Guanzhong Li, Lvzhou Institute of Quantum Computing and Software School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Quantum Science Center of Guangdong-Hong Kong-Macao Greater Bay Area (Guangdong) Shenzhen China

The problem of solving linear systems is of great significance in both theory and practice, for which quantum solvers have been shown to provide an exponential speedup over the best-known classical solvers. Recently, a quantum linear system solver has been developed with the state-of-the-art complexity [1], which combines two techniques, namely, discrete adiabatic evolution and eigenstate filtering. However, the parameters of the quantum circuit for eigenstate filtering need to be precomputed classically via the discrete Fourier transform, which introduces additional computational overhead. In this paper, we improve the solver by presenting a new eigenstate filtering process termed quantum phase discrimination in which the circuit parameters are given directly in a concise and analytical form with negligible classical overhead, while maintaining the same quantum complexity.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Historical trust-based method for internet of things

Historical trust-based method for internet of things

引用

2021 International Conference on Advanced Computer Applications, ACA 2021

作者： Jasim, Zainab Abdullah Alsoufi, Muaadh A. University of Babylon Software Department Information Technology Babylon Iraq Faculty of Engineering School of Computing Johor Malaysia

ISBN: (纸本)9781665435031

The Internet of Things (IoT) defines the universal and embedded actuators and sensors network with limited and heterogeneous capabilities of computation. The trustworthiness of IoT-enabled services raises concerns, since services may be misguided by invalid users via fake or changed sensor data. Nevertheless, an efficient scheme of trust management for IoT applications is primarily challenging due to data inconsistency issues. Existing works perform node reputation calculation by considering the node historical issue, and only node performance in the current range. This shows that node history is highly important to its reputation. In this work, we propose a historical trust-based method for IoTs. The results achieved demonstrate that the proposed method was able to correctly detect invading nodes. Additionally, the actual amount of trust the organization has gained over time was determined in a shorter time (0.83 s), and with consuming a relatively lower amount of energy. © 2021 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Explicitly Diverse Visual Question Generation

SSRN

引用

SSRN 2024年

作者： Xie, Jiayuan Zheng, Jiasheng Fang, Wenhao Cai, Yi Li, Qing School of Software Engineering South China University of Technology Guangzhou China Ministry of Education China Department of Computing Hong Kong Polytechnic University Hong Kong Institute of Software Chinese Academy of Sciences Beijing China

Visual question generation involves the generation of meaningful questions about an image. Although we have made significant progress in automatically generating a single high-quality question related to an image, existing methods often ignore the diversity and interpretability of generated questions, which are important for various daily tasks that require clear question sources. In this paper, we propose an explicitly diverse visual question generation model that aims to generate diverse questions based on interpretable question sources. To explicitly perform question generation, our model first extracts the scene graph from the image using the unbiased scene graph generation method, where questions generated based on the scene graphs have interpretable question sources. To ensure the diversity of generated questions, our model selects different subgraphs from the scene graph as question sources. Specifically, we employ a subgraph selector to learn how humans select multiple subgraphs that are suitable for question generation. Finally, our model generates diverse questions based on different selected subgraphs. Extensive experiments on the VQA v2.0 and COCO-QA datasets show that the proposed model outperforms the baselines and is able to interpretably generate diverse questions. © 2024, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dual-Encoder Attention Fusion Model for Aspect Sentiment Triplet Extraction

Dual-Encoder Attention Fusion Model for Aspect Sentiment Tri...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Yunqi Zhang Songda Li Yuquan Lan Hui Zhao Gang Zhao Software Engineering Institute East China Normal University Shanghai China Shanghai Key Laboratory of Trustworthy Computing Software Engineering Institute East China Normal University Shanghai China Microsoft Beijing China

Aspect sentiment triplet extraction (ASTE) is a crucial sub-task of aspect-based sentiment analysis, which aims to extract each aspect term along with its opinion term and sentiment polarity. Prior works accomplish ASTE by jointly modeling its two sub-tasks, i.e., term extraction and sentiment classification. However, they ignore that different features have different importance to the two sub-tasks, resulting in feature confusion and insufficient feature fusion. To address this, we propose a dual-encoder attention fusion model (DuaIAF) for ASTE, consisting of a term extraction module and a sentiment classification module. First, we adopt a grid tagging scheme to model word-to-word interactions within word pairs. Second, we employ a dual-encoder framework to obtain BERT-style grid multi-features for term extraction and contextualized features for sentiment classification, thus alleviating feature confusion. Third, deep fusion networks are applied to refine word-level and span-level features. A convolution neural network (CNN)-based self-attention network deeply fuses word-level grid multi-features to explore the 2D structure information and long-distance dependency information. Moreover, attention pooling aggregates contextualized features into span-level features, which helps capture span-to-span interactions between aspect term spans and opinion term spans. The experimental results show that our model outperforms previous state-of-the-art methods over 4 English and 2 Chinese datasets in various domains.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Bounded-DWA: An Efficient Local Planner for Ackermann-driven Vehicles on Sandy Terrain

Bounded-DWA: An Efficient Local Planner for Ackermann-driven...

引用

IEEE International Conference on Real-time computing and Robotics (RCAR)

作者： Ke Gong Zhiyuan Xu Xinyu Zhang Shanghai Key Laboratory of Trustworthy Computing Engineering Research Center of Software/Hardware Co-Design Technology and Application (MoE) and School of Software Engineering East China Normal University Shanghai Midea Group China

We present a new dynamic window approach (DWA) for mobile vehicles equipped with Ackermann steering geometry that adheres to Ackermann kinematic constraints. By integrating these constraints with the sampling window in DWA, we can further reduce and bound the sampling range and enhance the efficiency of the DWA when a mobile vehicle moves on sandy terrain. Furthermore, we improve the evaluation function to optimize the selected trajectory. Our algorithm is successfully validated in ROS and Gazebo through comparison with other existing local planner such as the original DWA and TEB algorithms. We also successfully deploy our Bounded-DWA in the application of coverage path planning, where tree-planting robots traverse on sandy terrain.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Digital Platform to Empower the Self-Employment in Sri Lanka 6

Digital Platform to Empower the Self-Employment in Sri Lanka

引用

6th International Conference on Information Technology Research, ICITR 2021

作者： Wickramasinghe, H.C.P. Thebuwana, T.D. Wijesinghe, G.K.H.S. Dissanayake, U.N. Kodagoda, Nuwan Suriyawansa, Kushnara Faculty of Computing Sri Lanka Institute of Information Technology Department of Computer Science and Software Engineering Sri Lanka

ISBN: (纸本)9781665420006

Unemployment is a huge problem around the world because a lack of job opportunities. People are unable to find the job opportunities according to their preferences and qualifications. As a solution for this, many countries are attempting to empower self-employment. Most of current world problems have been solved using modern technologies. Therefore, the development of self-employment also can be achieved through modern technology. The objective of our proposed platform, HIRELANCER, is empowering self-employment using modern technologies. HIRELANCER is bringing the consumers, service providers, and suppliers into the same platform. HIRELANCER will consist of innovative features that go beyond comparatively to other platforms such as an advanced mechanism to find best suitable service providers/suppliers for the service, handling the virtual front-desk, cost estimation for the services prior to contacting a service provider, and advanced facility to find a suitable career path for the people who are seeking career guidance. This research paper discusses how the innovative features of HIRELANCER will be beneficial for consumers, service providers, and suppliers and ultimately achieve our main objective, which is empowering self-employment in Sri Lanka. © 2021 IEEE.

关键词： Employment

来源：评论

学校读者我要写书评

暂无评论

EEiF: Efficient Isolated Forest with e Branches for Anomaly Detection

EEiF: Efficient Isolated Forest with e Branches for Anomaly ...

引用

IEEE International Conference on Data Mining (ICDM)

作者： Yifan Zhang Haolong Xiang Xuyun Zhang Xiaolong Xu Wei Fan Qin Zhang Lianyong Qi School of software Nanjing University of Information Science and Technology China Jiangsu Province Engineering Research Center of Advanced Computing and Intelligent Services China School of Computing Macquarie University Australia Uffield Department of Women's & Reproductive Health University of Oxford England College of Computer Science and Software Engineering Shenzhen University China Faculty of Science and Engineering University of Petroleum (East China) China

ISBN: (数字)9798331506681

ISBN: (纸本)9798331506698

Anomaly detection is a popular research topic in Artificial Intelligence and has been widely applied in network security, financial fraud detection, and industrial equipment failure detection. Isolation forest based methods are the base algorithms to detect anomalies in these scenarios for their simplicity and efficiency, which has been further exploited with multi-folk trees and learning mechanisms to realize the optimal isolation forest for high detection accuracy. However, the optimal isolation forest is time-consuming with the learning mechanisms, resulting in the task failing of time-constrained applications. Moreover, the original optimal isolation forest fails to construct the optimal tree structure restricted by the time complexity. To address the above challenges, we propose an efficient anomaly detection method called EEIF, which realizes the real e-folk structure of the optimal isolation forest in our practical algorithm design. Specifically, we design a distribution that perfectly matches the e-branch theory to construct the optimal isolation forest. Then, we design an FR clustering scheme to achieve fast training of the isolation forest with learning to hash and provide related proofs of accuracy and efficiency. Besides, a parallel algorithm is integrated into our method to reduce prediction time. Finally, extensive experiments are conducted on a large amount of real-world datasets and the results demonstrate that our method significantly improves efficiency while ensuring effectiveness, compared with the state-of-the-art methods.

关键词： Learning systems Training Accuracy Clustering algorithms Forestry Network security Fraud Time complexity Parallel algorithms Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Intrusion Detection in Smart IoT Devices for People with Disabilities 8

Intrusion Detection in Smart IoT Devices for People with Dis...

引用

8th IEEE International Smart Cities Conference, ISC2 2022

作者： Naveed, Muhammad Usman, Syed Muhammad Satti, Muhammad Islam Aleshaiker, Sama Anwar, Aamir Shaheed Zulfikar Ali Bhutto Institute of Science and Technology Department of Computer Science Islamabad Pakistan Ai Air University Faculty of Computing Department of Creative Technologies Islamabad Pakistan Riphah University Faculty of Computer Science and Software Engineering Islamabad Pakistan School of Computing & Engineering University of West London London United Kingdom

ISBN: (数字)9781665485616

ISBN: (纸本)9781665485616

An intrusion Detection System (IDS) is a system that resides inside the network and monitors all incoming and outgoing traffic. It prevents unethical activities from happening over the network. With the use of IoT devices, network traffic is also increased. Intruders and hackers are attracted to this network because of its low processing power and openness. IoT has transformed diagnostic and monitoring systems for patients in the healthcare industry. However, a secure network is needed for these health care devices. This research proposes a hybrid model to secure the IoT network from external intrusions. The proposed method consists of preprocessing data with the help of normalization and feature selection by removing high correlated features with the help of the Pearson correlation coefficient and Support Vector Machine (SVM) for classification. The proposed approach has achieved an accuracy of 99.3%, precision of 99.1% and an F-1 score of 99.25% on the standard dataset. Results have been compared with state-of-the-art, and the proposed method outperforms all performance measures. © 2022 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Improving resource-constrained IoT device lifetimes by mitigating redundant transmissions across heterogeneous wireless multimedia of things

引用

Digital Communications and Networks 2022年第5期8卷 778-790页

作者： Muhammad Salah ud din Muhammad Atif Ur Rehman Rehmat Ullah Chan-Won Park Dae Ho Kim Byung-seo Kim Department of Electronics&Computer Engineering Hongik UniversitySejong City30016South Korea Department of Computing&Mathematics Manchester Metropolitan University United Kingdom Cardiff School of Technologies Cardiff Metropolitan UniversityCardiffCF52YBUnited Kingdom Electronics and Telecommunications Research Institute Daejeon34129South Korea Department of Software and Communications Engineering Hongik UniversitySejong City30016South Korea

In Wireless Multimedia Sensor Networks(WMSNs),nodes capable of retrieving video,audio,images,and small scale sensor data,tend to generate immense traffic of various *** energy-efficient transmission of such a vast amount of heterogeneous multimedia content while simultaneously ensuring the quality of service and optimal energy consumption is ***,we propose a Power-Efficient Wireless Multimedia of Things(PE-WMoT),a robust and energy-efficient cluster-based mechanism to improve the overall lifetime of *** a PE-WMoT,nodes declare themselves Cluster Heads(CHs)based on available *** cluster formation and CH declaration processes are completed,the Sub-Cluster(SC)formation process triggers,in which application base nodes within close vicinity of each other organize themselves under the administration of a Sub-Cluster Head(SCH).The SCH gathers data from member nodes,removes redundancies,and forwards miniaturized data to its respective ***-WMoT adopts a fuzzy-based technique named the analytical hierarchical process,which enables CHs to select an optimal SCH among available SCs.A PE-WMoT also devises a robust scheduling mechanism between CH,SCH,and child nodes to enable collision-free data *** results revealed that a PE-WMoT significantly reduces the number of redundant packet transmissions,improves energy consumption of the network,and effectively increases network throughput.

关键词： Clustering WMSN WSN IoTs Resource-constrained Fuzzy AHP Sub clustering MAC Energy efficiency Network lifetime

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：