检索结果-内蒙古大学图书馆

Facial Action Unit Recognition Enhanced by Text Descriptions of FACS

IEEE Transactions on Affective computing 2024年第2期16卷 814-826页

作者： Chang, Yanan Zhang, Caichao Wu, Yi Wang, Shangfei University of Science and Technology of China Key Lab of Computing and Communication Software of Anhui Province Anhui Hefei230027 China

Although the descriptions of facial action units (AUs) provide crucial semantic knowledge for representation learning from facial images, they have not been fully explored for facial action unit recognition. In this paper, we propose a method that effectively explores the knowledge existing in AU descriptions to enhance AU recognition. Specifically, the proposed method consists of three components, i.e. AU recognition network, global representation alignment, and AU representation alignment. The AU recognition network extracts global features and AU-specific features for AU prediction from images. To leverage AU textual descriptions fully, we design two-level representation alignment for AU recognition. The global representation alignment component closes the distance between the global facial features and its corresponding positive global embedding extracted from textual descriptions. Then, the AU-specific features are aligned with the positive AU textual embedding by the AU representation alignment component. Negative textual embedding generation strategies are also designed to further boost the two-level representation alignment. Through the two-level alignment, AU textual descriptions guide image representation learning of the AU recognition network. Experiments on two benchmark datasets and one in-the-wild dataset demonstrate the efficacy of the description-enhanced AU recognition method, compared with the state-of-the-art works. © 2010-2012 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

PR3D: Precise and realistic 3D face reconstruction from a single image

PR3D: Precise and realistic 3D face reconstruction from a si...

引用

作者： Huang, Zhangjin Wu, Xing University of Science and Technology of China Hefei China Anhui Province Key Laboratory of Software in Computing and Communication Hefei China Deqing Alpha Innovation Institute Huzhou China

Reconstructing the three-dimensional (3D) shape and texture of the face from a single image is a significant and challenging task in computer vision and graphics. In recent years, learning-based reconstruction methods have exhibited outstanding performance, but their effectiveness is severely constrained by the scarcity of available training data with 3D annotations. To address this issue, we present the PR3D (Precise and Realistic 3D face reconstruction) method, which consists of high-precision shape reconstruction based on semi-supervised learning and high-fidelity texture reconstruction based on StyleGAN2. In shape reconstruction, we use in-the-wild face images and 3D annotated datasets to train the auxiliary encoder and the identity encoder, encoding the input image into parameters of FLAME (a parametric 3D face model). Simultaneously, a novel semi-supervised hybrid landmark loss is designed to more effectively learn from in-the-wild face images and 3D annotated datasets. Furthermore, to meet the real-time requirements in practical applications, a lightweight shape reconstruction model called fast-PR3D is distilled through teacher–student learning. In texture reconstruction, we propose a texture extraction method based on face reenactment in StyleGAN2 style space, extracting texture from the source and reenacted face images to constitute a facial texture map. Extensive experiments have demonstrated the state-of-the-art performance of our method. © 2024 John Wiley & Sons Ltd.

关键词： Textures

来源：评论

学校读者我要写书评

暂无评论

Hubness-Enabled Clustering and Recovery for Large-Scale Incomplete Multi-View Data

引用

ACM Transactions on Knowledge Discovery from Data 2024年第1期19卷 1-23页

作者： Yu, Xiao Liu, Hui Zhang, Yan Lin, Yuxiu Zhang, Caiming School of Computer Science and Technology Shandong University of Finance and Economics Shandong Province Jinan China Shandong Key Laboratory of Lightweight Intelligent Computing Visualization for Digital Economy Shandong Province Jinan China School of Software Shandong University Shandong Province Jinan China

Incomplete multi-view clustering has gained considerable attention in recent years due to the prevalence of incomplete multi-view data in real-world applications. However, existing methods often struggle to effectively deal with large-scale datasets, particularly those with a significant number of missing instances. To address these issues, we propose a novel method called Hubness-Enabled Clustering and Recovery for Large-Scale Incomplete Multi-View Data (HENRI). HENRI utilizes the consensus hubs of all views to identify informative anchors to handle large-scale incomplete datasets. Furthermore, it incorporates a novel sample-level fusion strategy that effectively integrates information from all views, leading to remarkable outcomes in both cluster formation and missing data reconstruction. HENRI demonstrates exceptional capability in capturing the underlying structures of the data and recovering missing information, even when faced with a significant number of instances with incomplete data in partial views. To validate its effectiveness, we conducted experiments on 6 complete datasets and 31 incomplete datasets, comparing against 11 baseline methods. The results are impressive, demonstrating the superior performance of HENRI over the state-of-The-Art methods. © 2024 Copyright held by the owner/author(s).

关键词： Data assimilation

来源：评论

学校读者我要写书评

暂无评论

Multi-layer network embedding on scc-based network with motif

引用

Digital communications and Networks 2024年第3期10卷 546-556页

作者： Lu Sun Xiaona Li Mingyue Zhang Liangtian Wan Yun Lin Xianpeng Wang Gang Xu Department of Communication Engineering Institute of Information Science TechnologyDalian Maritime UniversityDalian116026China Key Laboratory of Big Data Intelligent Computing Chongqing University of Posts and TelecommunicationsChongqing400065China Key Laboratory for Ubiquitous Network and Service Software of Liaoning Province DUT School of Software Technology&DUT-RU International School of Information Science and EngineeringDalian University of TechnologyDalian 116620China College of Information and Communication Engineering Harbin Engineering UniversityHarbin 150001China School of Information and Communication Engineering Hainan UniversityHaikou 570228China State Key Laboratory of Millimeter Waves School of Information Science and EngineeringSoutheast UniversityNanjing 210096China

Interconnection of all things challenges the traditional communication methods,and Semantic communication and computing(SCC)will become new *** is a challenging task to accurately detect,extract,and represent semantic information in the research of SCC-based *** previous research,researchers usually use convolution to extract the feature information of a graph and perform the corresponding task of node ***,the content of semantic information is quite *** graph convolutional neural networks provide an effective solution for node classification tasks,due to their limitations in representing multiple relational patterns and not recognizing and analyzing higher-order local structures,the extracted feature information is subject to varying degrees of ***,this paper extends from a single-layer topology network to a multi-layer heterogeneous topology *** Bidirectional Encoder Representations from Transformers(BERT)training word vector is introduced to extract the semantic features in the network,and the existing graph neural network is improved by combining the higher-order local feature module of the network model representation network.A multi-layer network embedding algorithm on SCC-based networks with motifs is proposed to complete the task of end-to-end node *** verify the effectiveness of the algorithm on a real multi-layer heterogeneous network.

关键词： Semantic communication and computing Multi-layer network Graph neural network Motif

来源：评论

学校读者我要写书评

暂无评论

Blockchain-Enabled Secure, Fair and Scalable Data Sharing in Zero-Trust Edge-End Environment

引用

IEEE Journal on Selected Areas in communications 2025年第6期43卷 2056-2069页

作者： Xu, Xiaolong Meng, Ke Xiang, Haolong Cui, Guangming Xia, Xiaoyu Dou, Wanchun Nanjing210044 China Nanjing University of Information Science and Technology School of Software and the Jiangsu Province Engineering Research Center of Advanced Computing and Intelligent Services Nanjing210044 China RMIT University School of Computing Technologies MelbourneVIC3000 Australia Nanjing University State Key Laboratory for Novel Software Technology Nanjing210023 China

In edge computing, the Zero-Trust Security Model (ZTSM), as a key enabling technology for next-generation networks, plays a crucial role in providing authentication for addressing data sharing concerns, such as frequent data breaches, data misuse, and cyberattacks. However, due to the complexity and diversity of edge environments, ZTSM struggles to meet the security requirements of data sharing frameworks solely through enhanced authentication. Consequently, such frameworks with ZTSM still face challenges in ensuring data integrity, evaluating various node behaviors, and coping with the increasing complexity of node attributes. To address these issues, we propose a blockchain-enabled secure, fair and scalable data sharing framework in a zero-trust edge-end environment in this paper. Specifically, we first propose a Merkle forest-based data storage model for the classified storage of loosely coupled data, consequently enhancing the scalability of the model. Then, we design a node behavior-based reputation assessment mechanism to ensure fairness during data sharing. Moreover, a data sharing protocol supervised by smart contract is proposed, working with the aforementioned storage and assessment schemes, to ensure the security of data sharing. Finally, comprehensive security analysis validates the security, fairness and scalability of the proposed framework. Extensive experimental results show that, as transaction volume grows, the time cost of data traversal in the storage model becomes progressively more efficient. Additionally, when the size of the smart contract is increased tenfold, the maximum time cost of the data sharing protocol rises by only 4.98 times. © 1983-2012 IEEE.

关键词： Data integrity

来源：评论

学校读者我要写书评

暂无评论

RENN: A Rule Embedding Enhanced Neural Network Framework for Temporal Knowledge Graph Completion 30

RENN: A Rule Embedding Enhanced Neural Network Framework for...

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Zong, Linlin Xie, Zhenrong Ma, Chi Liu, Xinyue Zhang, Xianchao Xu, Bo Key Laboratory for Ubiquitous Network and Service Software of Liaoning Province School of Software Dalian University of Technology China School of Computer Science and Technology Dalian University of Technology China Key Laboratory of Social Computing and Cognitive Intelligence Dalian University of Technology Ministry of Education China

ISBN: (纸本)9782493814104

Existing approaches encompass deep neural network-based methods for temporal knowledge graph embedding and rule-based logical symbolic reasoning. However, the former may not adequately account for structural dependencies between ***, the latter methods relies heavily on strict logical rule reasoning and lacks robustness in the face of fuzzy or noisy data. In response to these challenges, we present RENN, a groundbreaking framework that enhances temporal knowledge graph completion through rule embedding. RENN employs a three-step approach. First, it utilizes temporary random walk to extract temporal logic rules. Then, it pre-trains by learning embeddings for each logical rule and its associated relations, thereby enhancing the likelihood of existing quadruples and logical rules. Finally, it incorporates the embeddings of logical rules into the deep neural network. Our methodology has been validated through experiments conducted on various temporal knowledge graph models and datasets, consistently demonstrating its effectiveness and potential in improving temporal knowledge graph completion. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Heterogeneous UAV Resource Scheduling for Dynamic Time Sensitive Target Detection and Interference

引用

IEEE Internet of Things Journal 2025年第12期12卷 20030-20041页

作者： Wan, Liangtian Wang, Jiashuai Sun, Lu Li, Kuixian Xiong, Xuanrui Lin, Yun Dalian University of Technology Key Laboratory for Ubiquitous Network and Service Software of Liaoning Province School of Software Dalian116620 China Dalian Maritime University Institute of Information Science Technology Department of Communication Engineering Dalian116026 China Harbin Engineering University College of Information and Communication Engineering Harbin150001 China Chongqing University of Posts and Telecommunications School of Communications and Information Engineering Chongqing400065 China

In complex electromagnetic environments, targets that need to be interfered with often possess high levels of concealment and anti-interference capabilities. Additionally, due to the dynamic characteristics of these targets, interference tasks must be conducted within strict time constraints to ensure interference effect. In this paper, we adopt a reconnaissance-first approach for concealed targets. After detecting the accurate location of the target, we deploy Unmanned Aerial Vehicles (UAVs) to interfere with the targets. First, we established a UAV swarm task scheduling optimization model after considering constraints such as target threat range, priority of reconnaissance and interference tasks, interference task time, and UAV energy consumption. Meanwhile, we model the anti-interference capability of the target as a threat range. Second, we propose a non-dominated sorting genetic algorithm based on distance in the solution space and a dynamic parent selection strategy (DPSNSGA-II) to solve UAV Resource Scheduling optimization problem. The diversity of the population is increased and the situation of falling into local optima is reduced by improving the parent individual selection strategy, mutation strategy, and elite solution retention mechanism. Finally, we construct two data sets of varying sizes to evaluate the quality of solution sets and the convergence performance of the proposed algorithm. The simulation results indicate that the proposed DPSNSGA-II algorithm has better result for population diversity and convergence compared to state-of-the-art algorithms. © 2014 IEEE.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Linguistic Steganalysis Based on Meta Features and Immune Mechanism

引用

Chinese Journal of Electronics 2023年第4期19卷 661-666页

作者： Hao Yang Xianbin Cao Anhui Province Key Laboratory of Software in Computing and Communication School of Computer Science and Technology University of Science and Technology of China Hefei China

Linguistic steganalysis depends on efficient detection features due to the diversity of syntax and the polysemia of semantics in natural language processing. This paper presents a novel linguistics steganalysis approach based on meta features and immune clone mechanism. Firstly, meta features are used to represent texts. Then immune clone mechanism is exploited to select appropriate features so as to constitute effective detectors. Our approach employed meta features as detection features, which is an opposite view from the previous literatures. Moreover, the immune training process consists of two phases which can identify respectively two kinds of stego texts. The constituted detectors have the capable of blind steganalysis to a certain extent. Experiments show that the proposed approach gets better performance than typical existing methods, especially in detecting short texts. When sizes of texts are confined to 3kB, detection accuracies have exceeded 95%.

关键词： Training Integrated circuits Steganography Semantics Cloning Detectors Linguistics

来源：评论

学校读者我要写书评

暂无评论

Low-Resolution Face Recognition Enhanced by High-Resolution Facial Images 17

Low-Resolution Face Recognition Enhanced by High-Resolution ...

引用

17th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2023

作者： Wang, Haihan Wang, Shangfei University of Science and Technology of China Key Lab of Computing and Communication Software of Anhui Province China University of Science and Technology of China Anhui Robot Technology Standard Innovation Base China

ISBN: (纸本)9798350345445

Despite recent advances in high-resolution (HR) face recognition, recognizing identities from low-resolution (LR) facial images remains challenging due to the absence of facial shape and detail. Current research focuses solely on reducing the distribution discrepancy between the HR and LR embeddings from the output layer, rather than thoroughly investigating the superiority of HR facial images for improved performance. In this paper, we propose a novel low-resolution face recognition method enhanced by the guidance of high-resolution facial images in both feature map space and embedding space. Specifically, in feature map space, the similarity constraint across the multilayer feature maps is adopted to align the intermediate features of facial images. Then we introduce multiple generators to recover HR images from extracted feature maps and utilize the reconstructed loss to supplement the missing facial details in LR images. In embedding space, we propose a supervised auxiliary contrastive loss to encourage the paired HR and LR embedding from the same class to be pulled together, whereas those from different classes are pushed apart. The one-to-many matching strategy and the adaptive weight adjustment strategy are applied to make the network adapt to the inputs of different resolutions. Experiments on four benchmark datasets with both synthesized and realistic LR facial images demonstrate the superiority of the proposed method to state-of-the-art. © 2023 IEEE.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Human Pose Estimation with Shape Aware Loss 17

Human Pose Estimation with Shape Aware Loss

引用

17th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2023

作者： Fang, Lin Wang, Shangfei University of Science and Technology of China Key Lab of Computing and Communication Software of Anhui Province China University of Science and Technology of China Anhui Robot Technology Standard Innovation Base China

ISBN: (纸本)9798350345445

Although the mean square error (mse) of heatmap is an intuitive loss for heatmap-based human pose estimation, the joints localization accuracy may not be improved when heatmap mse reduces. In this paper, we show that a great cause for such misalignment is the unnecessary requirement from heatmap mse on the irrelevant Gaussian parameter, i.e. maximum. The coordinate prediction is precise as long as the probability distribution held by the predicted heatmap is a well-shaped Gaussian distribution and has the same center as the ground truth. However, heatmap mse unnecessarily requires the Gaussian distribution to hold the same maximum as the ground truth. Correspondingly, we introduce mse on the image gradients of the target and predicted heatmap (referred to as gradmap mse) to focus on the shape of the heatmap. Combining heatmap and gradmap mse, we propose a simple yet effective Shape Aware Loss (SAL) method. Being model-agnostic, our method can benefit various existing models. We apply SAL to the three latest network architectures and obtain performance improvements for all of them. Comparisons of the visualized predicted heatmaps further prove the effectiveness of the proposed method. © 2023 IEEE.

关键词： Mean square error

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

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

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：