检索结果-内蒙古大学图书馆

Journal of Network Intelligence 2025年第2期10卷 638-662页

作者： He, Wen-Wu Gong, Xuan-Jin Cui, Zhuo-Xu School of Computer Science and Mathematics Fujian University of Technology Fuzhou350118 China Fujian Provincial Key Laboratory of Big Data Mining and Applications Fuzhou350118 China School of Mathematics and Statistics Wuhan University Wuhan430072 China

This paper considers the parallel stochastic composite optimization for general asynchronous cases where both the objective function and the regularizer are non-convex. In particular, based on the randomized stochastic proximal gradient protocol, an asynchronous parallel algorithm termed ARSPG is proposed which incorporates well the non-convex regularization to obtain the desired oracle property. Theoretical analysis shows that ARSPG has the convergence rate in the order of O(1/ϵ2). Further, a gradient-free version termed ARSPGF is developed to handle cases where only noisy objective function values are available. The analysis shows that ARSPGF has the same order of convergence rate as that of the normal version. Experiments over benchmark data sets validate well theoretical analyses and experimental results also show interesting practical aspects of the proposed algorithms. © 2025 ISSN 2414-8105 (Online).

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

SJA: Server-driven Joint Adaptation of Loss and Bitrate for Multi-Party Realtime Video Streaming 42

SJA: Server-driven Joint Adaptation of Loss and Bitrate for ...

引用

42nd IEEE International Conference on computer Communications, INFOCOM 2023

作者： Shen, Kai Zhang, Dayou Zhu, Zi Zhang, Lei Wang, Fangxin Wang, Dan The Chinese University of HongKong The Future Network of Intelligence Institute Shenzhen China The Chinese University of HongKong School of Science and Engineering Shenzhen China Shenzhen University College of Computer Science and Software Engineering China Peng Cheng Laboratory China The Guangdong Provincial Key Laboratory of Future Networks of Intelligence China The Hong Kong Polytechnic University Department of Computing Hong Kong

ISBN: (纸本)9798350334142

The outbreak of COVID-19 has dramatically promoted the explosive proliferation of multi-party realtime video streaming (MRVS) services, represented by Zoom and Microsoft Teams. Different from Video-on-Demand (VoD) or live streaming, MRVS enables all-to-all realtime video communication, bringing significant challenges to service providing. First, unreliable network transmission can cause network loss, resulting in delay increase and visual quality degradation. Second, the transformation from two-party to multi-party communication makes resource scheduling much more difficult. Moreover, optimizing the overall QoE requires a global coordination, which is quite challenging given the various impact factors such as bitrate and *** this paper, we propose the SJA framework, which is, to our best knowledge, the first server-driven joint loss and bitrate adaptation framework in multi-party realtime video streaming services towards maximized QoE. We comprehensively design an appropriate QoE model for MRVS services to capture the interplay among perceptual quality, variations, bitrate mismatch, loss damage, and streaming delay. We mathematically formulate the QoE maximization problem in MRVS services. A Lyapunov-based relaxation and the SJA algorithm are further designed to address the optimization problem with close-to-optimal performance. Evaluations show that our framework can outperform the SOTA solutions by 18.4% ∼ 46.5%. © 2023 IEEE.

关键词： Quality control

来源：评论

学校读者我要写书评

暂无评论

Topic-based Multi-layer Knowledge Filtering for Emotion Recognition in Conversation

Topic-based Multi-layer Knowledge Filtering for Emotion Reco...

引用

International Conference on computer Supported Cooperative Work in Design

作者： Xiaoyang Li Zhenyu Yang Yiwen Li Zhijun Li 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

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

Emotion recognition in conversation (ERC) is a prominent research topic in natural language processing, widely applicable in various scenarios. However, accessing external commonsense knowledge and related dialogue topics, along with the complexity of fusing utterances, presents significant challenges. In this paper, we introduce a Topic-based Multilayer Knowledge Filtering (TMKF) model to enhance dialog emotion recognition accuracy. TMKF acquires commonsense knowledge for each utterance and employs two Variational Autoencoder (VAE) modules to extract global and speaker-level dialogue topics. We utilize Global Knowledge Filtering (GKF) and Local Knowledge Filtering (LKF) to obtain topic-specific knowledge representations after filtering commonsense information through global and local topic hierarchies. Subsequently, we leverage relational graphs to convolve commonsense knowledge with utterances, resulting in knowledge-constrained utterance representations for classification. Our proposed model is evaluated through extensive experiments on four widely used benchmark datasets for conversational emotion recognition. The results underscore the effectiveness of TMKF, which significantly outperforms other methods in standard metric evaluations.

关键词： Measurement Emotion recognition Filtering Convolution Oral communication Benchmark testing Nonhomogeneous media

来源：评论

学校读者我要写书评

暂无评论

HCF-Net: Hierarchical Context Fusion Network for Infrared Small Object Detection

arXiv

引用

arXiv 2024年

作者： Xu, Shibiao Zheng, ShuChen Xu, Wenhao Xu, Rongtao Wang, Changwei Zhang, Jiguang Teng, Xiaoqiang Li, Ao Guo, Li Artificial Intelligence Beijing University of Posts and Telecommunications China Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology Shandong Academy of Sciences China State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences China School of Artificial Intelligence University of Chinese Academy of Sciences China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science China School of Computer Science and Technology Harbin University of Science and Technology China

Infrared small object detection is an important computer vision task involving the recognition and localization of tiny objects in infrared images, which usually contain only a few pixels. However, it encounters difficulties due to the diminutive size of the objects and the generally complex backgrounds in infrared images. In this paper, we propose a deep learning method, HCF-Net, that significantly improves infrared small object detection performance through multiple practical modules. Specifically, it includes the parallelized patch-aware attention (PPA) module, dimension-aware selective integration (DASI) module, and multi-dilated channel refiner (MDCR) module. The PPA module uses a multi-branch feature extraction strategy to capture feature information at different scales and levels. The DASI module enables adaptive channel selection and fusion. The MDCR module captures spatial features of different receptive field ranges through multiple depth-separable convolutional layers. Extensive experimental results on the SIRST infrared single-frame image dataset show that the proposed HCF-Net performs well, surpassing other traditional and deep learning models. Code is available at https://***/zhengshuchen/HCFNet. Copyright © 2024, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Dynamic Logic Reasoning Model for Argumentation Relation Classification

IEEE Transactions on Audio, Speech and Language Processing

引用

IEEE Transactions on Audio, Speech and Language Processing 2025年 33卷 2151-2162页

作者： Yang Sun Caihua Yang Jianzhu Bao Bin Liang Min Yang Ruifeng Xu Human Language Technology Lab at the School of Computer Science of Technology Harbin Institute of Technology Shenzhen China Chinese University of Hong Kong Hong Kong SAR China SIAT Chinese Academy of Sciences Shenzhen China School of Computer Science and Technology Harbin Institute of Technology (Shenzhen) Shenzhen China Peng Cheng Laboratory Shenzhen China Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies Shenzhen China

Argumentation relation classification (ARC) aims to identify the relations between argumentation component (AC) pairs. Existing studies have achieved impressive results on public datasets through the utilization of AC-level features, fine-grained attributes, and structural information. However, they overlook the logical relations and structure within AC pairs and fall short in performing dynamic logical reasoning for ARC. Therefore, in this paper, we propose a Dyn Amic Logic r Easoning model (DALE) with logic graph construction and dynamic logical reasoning pattern learning for ARC. Specifically, we first construct a logic graph to establish the logical structure within individual ACs and between AC pairs. Then we propose dynamic reasoning modules comprising four distinct types of graph cells to explore different logical reasoning operations. Each cell incorporates a dynamic router and interconnects others to establish a dynamic routing network. This design enables the model to autonomously adapt and select distinct operational paths based on the specific nature of the input instance. Our comprehensive experiments, conducted on three public datasets, reveal that our model outperforms strong baselines.

关键词： Cognition Logic Semantics Syntactics Adaptation models Speech processing Linguistics Sun Standards Deep learning

来源：评论

学校读者我要写书评

暂无评论

TSFE: Research on Transformer and Feature Enhancement Methods for Image-Text Retrieval

TSFE: Research on Transformer and Feature Enhancement Method...

引用

International Conference on computer Supported Cooperative Work in Design

作者： Jinxiao Yang Xingang Wang Qingao Wang Key Laboratory of Computing Power Network and Information Security Ministry of EducationShandong 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

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

In recent years, cross-modal retrieval has a wide range of applications in fields such as information retrieval and multimedia processing, where the key is to find relevant data in another modality through one modal query. In cross-modal graphic retrieval, mutual attention mechanisms are commonly used to interact image and text features. However, this interaction mechanism makes it difficult to extract separate visual and textual features for subsequent indexing steps, especially in large-scale retrieval tasks. Furthermore, in image representation, non-semantic information in image features can lead to inaccuracies in the alignment of image and text features. Therefore this paper proposes a Transformer and Feature Enhancement Method (TSFE) for Image-Text Retrieval. The method better fuses the underlying features and the higher level features by using a hierarchical Transformer coding structure on two separate branches, image and text, to proofread and localise the final output features. The Feature Enhanced Attention (FEA) module is designed in order to infer non-semantic information in the image and enhance the features of salient regions. Channel-space attention and max pooling is introduced on top of Transformer encoder self-attention to filter redundant and interfering information from channel and spatial dimensions. Experiments on Flickr30k dataset and MS-COCO dataset in this paper show improved performance in cross-modal retrieval, thus validating the effectiveness and sophistication of the proposed method.

关键词： Visualization Semantics Pipelines Noise Image representation Transformers Feature extraction

来源：评论

学校读者我要写书评

暂无评论

An Ecg Signal Synthesis Approach Based on the Synergy of Wgan and Attention Mechanisms

SSRN

引用

SSRN 2024年

作者： Zhou, Hongfang Li, Yijie Guo, Yifan Xue, Haolin School of Computer Science and Engineering Xi’an University of Technology Xi’an710048 China Shaanxi Key Laboratory of Network Computing and Security Technology Xi’an710048 China

Electrocardiogram (ECG) synthesis plays a key role in the diagnosis of heart diseases. However, ECG data involves patient privacy and has obvious imbalance issue. This leads to a disconnect between theoretical research methods and practical applications. Based on this, the paper will explore the application of generative adversarial networks (GANs) in ECG signal synthesis. First, the paper proposes a WGAN-SD-GP model that uses the conditional WGAN networks incorporating an attention mechanism to enhance the ability to capture contextual information and effectively focus contextual information by scaling dot products. Secondly, the paper explores whether the design concepts of circular convolution, feature extraction and layer-hopping connection in R2U-Net can be applied to the synthesis of ECGs, and proposes the WGAN-SKD-GP model. The model combines the hopping layer connection with the attention mechanism, which enables it to process the input data more flexibly and enhances the feature expression ability. Finally, the experiments were designed to automatically classify arrhythmia using 1DResNet50 on a mixed dataset of synthetic and real signals, which was evaluated using several metrics, including Precision, Recall, F1 Score, Macro Avg, Weighted Avg, and Overall Accuracy. The experimental results not only verify the effectiveness of WGAN-SKD-GP in ECG signal synthesis, but also provide a new idea for solving the problem of insufficient data of ECG signals, which has significant potential application value. © 2024, The Authors. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Clustering-Based Custom Global Modules for Personalized Federated Learning

Clustering-Based Custom Global Modules for Personalized Fede...

引用

International Conference on Advanced Cloud and Big Data (CBD)

作者： Zining Chen Can Wang Baisong Zhang Weiye Wang Wen sheng Li Wei dong Zhang School of Computer Science and Technology Anhui University of Technology Ma'anshan China Anhui Provincial Key Laboratory of Digital Twin Technology in Metallurgical Industry Ma'anshan China

ISBN: (数字)9798331511074

ISBN: (纸本)9798331511081

The field of federated learning faces a fundamental challenge posed by the non-independent and identically distributed (Non-IID) data among heterogeneous clients. Personalized federated learning (PFL) addresses this issue by providing customized models for each client. The existing PFL methods ignore the impact of redundant information brought by shared knowledge on processing local tasks of clients, and clients prefer to find the mapping of local data distribution from shared knowledge space. This paper proposes a personalized aggregation method, FedCGM, which customizes a clustering coordinator for each client. The method extracts core knowledge from the global model that aligns with the local data distribution and adapts it to the local client. The challenge of FedCGM lies in identifying the mapping relationship between local data distributions and shared knowledge. To address this challenge, we construct posterior probability indices of the global modules on the target data distribution among participating members. This approach establishes a mapping relationship between data distribution and shared knowledge. We conducted extensive experiments on real-world datasets and found that FedCGM achieved higher accuracy compared to the state-of-the-art PFL methods.

关键词： Adaptation models Accuracy Federated learning Posterior probability Distributed databases Big Data Data models Data mining Faces

来源：评论

学校读者我要写书评

暂无评论

MCAF: Multi-Headed Causal Attention Fusion Approach for Multimodal Sentiment Analysis

MCAF: Multi-Headed Causal Attention Fusion Approach for Mult...

引用

International Joint Conference on Neural networks (IJCNN)

作者： Qingao Wang Xingang Wang Jinxiao Yang Yurun Bi 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

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Multimodal sentiment analysis(MSA) aims to synthesize multiple pieces of information, including textual, visual, and auditory information, to more accurately infer sentiment polarity. Due to the existence of complex and diverse affective causal relationships between different modalities, they interact with each other and constitute a multidimensional expression of human emotions. In the face of unbalanced data, i.e., when there are significant differences in the number of samples between different categories, the attention mechanism of the model tends to focus on spurious correlations in the training data, seriously impairing the model’s generalization ability and leading to bias, unbalanced prediction, and false correlation identification problems. To address the above problems, this study proposes a new multimodal fusion method based on the "within-sample sampling" and "cross-sample sampling" front door adjustment methods in causal inference strategies: the multi-head causal attention fusion method (MCAF). This method aims to capture potential causal relationships between different modalities through different attention heads, helping the model focus more on key causal features and avoid paying too much attention to false correlations in the training data. This helps improve the generalization performance of the model, make the decision-making process of the model more interpretable, and enhance the accuracy and robustness of the model for multimodal sentiment analysis tasks, making it more suitable for practical application scenarios.

关键词： Analytical models Sentiment analysis Visualization Correlation Neural networks Training data Predictive models

来源：评论

学校读者我要写书评

暂无评论

CAFI: News Recommendation with Candidate Perception of Fine-Grained Interaction Information

CAFI: News Recommendation with Candidate Perception of Fine-...

引用

International Conference on computer Supported Cooperative Work in Design

作者： Yiwen Li Zhenyu Yang Xiaoyang Li Zhijun Li 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

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

The most critical task in personalized news recommendation is to perform exact matching between candidate news and users’ interests. Existing news recommendation methods usually model users’ interests from historical clicked news items without considering candidate news, which makes it difficult to precisely match candidate news with users’ interests. Moreover, it is challenging to distinguish similar news when forming a vector representation. Simply adding candidate news to the user interest modeling process without considering word-level information does not provide sufficient discrimination for recommending appropriate news. In this paper, we propose a news recommendation model with candidate-aware fine-grained interaction information (CAFI). In our approach, we propose a fine-grained interaction module that matches candidate news items and text fragments of each historical news item at each semantic granularity to achieve interaction between the two at the word level and help similar historical news form more specific and accurate representations. In addition, our proposed gated self-attention mechanism utilizes the candidate news features as channel moderation gates to implement the process of filtering out information that is irrelevant to the candidate news for learning user interest representations, thereby better matching the candidate news to specific user interests. Experiments conducted on the large real-world Microsoft News Dataset (MIND) show that our model significantly outperforms the previously developed models in terms of all metrics. Our code is published at the following URL: https://***/liyiweneven/CAFI.

关键词： Uniform resource locators Measurement Codes Filtering Federated learning Semantics Focusing

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：