检索结果-内蒙古大学图书馆

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Zhao, Shuo Gu, Qiliang Zhang, Jianqiang Song, Gongpeng Lu, Qin Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China Shandong Branch of China Mobile Communication Group Design Institute Co. Jinan China

ISBN: (纸本)9781665410205

Chinese short text similarity computation stands as a pivotal task within natural language processing, garnering significant attention. However, existing models grapple with limitations in handling intricate semantic relationships, such as the challenge of discerning subtle semantic nuances in text, inadequacies in effectively integrating diverse levels of semantic information, and the struggle to capture polysemous meanings accurately. In addressing these issues, this paper introduces an innovative Chinese short text similarity computation model, SMGC-SBERT. This model addresses shortcomings of the existing models by employing a multi-module fusion strategy, thereby enabling a more precise measurement of semantic similarity between texts. Primarily, the model incorporates SAT embedding to acquire phrase-level semantic information and leverages the MS-BERT model to encode text, improving the model's comprehension of textual polysemy and obtaining richer semantic representation. Then, the fusion of module features, including multi-branch convolutional networks and mix pooling, enables the extraction of textual features from varied levels, bolstering the model's representational capacity. Additionally, to further reduce overfitting risks while improving accuracy and other performance, a multi-layer feature adjustment network is utilized for short text similarity calculation. The final resultant experimental findings showcase the superiority of the SMGC-SBERT model over other neural network models, demonstrating significant advancements across both Chinese-SNLI and CCKS2018_Task3 Chinese short text datasets. © 2024 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Future Resource Bank for ISAC: Achieving Fast and Stable Win-Win Matching for Both Individuals and Coalitions

arXiv

引用

arXiv 2025年

作者： Qi, Houyi Liwang, Minghui Hosseinalipour, Seyyedali Fu, Liqun Zou, Sai Ni, Wei School of Informatics Xiamen University Fujian China Department of Control Science and Engineering Shanghai Research Institute for Intelligent Autonomous Systems Tongji University Shanghai China Department of Electrical Engineering University at Buffalo SUNY NY United States College of Big Data and Information Engineering Guizhou University China Data61 CSIRO Australia

Future wireless networks must support emerging applications where environmental awareness is as critical as data transmission. Integrated Sensing and Communication (ISAC) enables this vision by allowing base stations (BSs) to allocate bandwidth and power to mobile users (MUs) for communications and cooperative sensing. However, this resource allocation is highly challenging due to: (i) dynamic resource demands from MUs and resource supply from BSs, and (ii) the selfishness of MUs and BSs. To address these challenges, existing solutions rely on either real-time (online) resource trading, which incurs high overhead and failures, or static long-term (offline) resource contracts, which lack flexibility. To overcome these limitations, we propose the Future Resource Bank for ISAC, a hybrid trading framework that integrates offline and online resource allocation through a level-wise client model, where MUs and their coalitions negotiate with BSs. We introduce two mechanisms: (i) Offline Role-Friendly Win-Win Matching (offRFW2M), leveraging overbooking to establish risk-aware, stable contracts, and (ii) Online Effective Backup Win-Win Matching (onEBW2M), which dynamically reallocates unmet demand and surplus supply. We theoretically prove stability, individual rationality, and weak Pareto optimality of these mechanisms. Through simulations, we show that our framework improves social welfare, latency, and energy efficiency compared to existing methods. Copyright © 2025, 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

A Lightweight Object Detection Method for Bank Operation and Maintenance Scenarios 5

A Lightweight Object Detection Method for Bank Operation and...

引用

5th International Conference on Pattern Recognition and Artificial Intelligence, PRAI 2022

作者： Xue, Junmin Rao, Yunbo Wu, Jiangang Gou, Haosong Liu, Yong Yang, Yang University of Electronic Science and Technology of China School of Information and Software Engineering Chengdu China Data Center of Postal Savings Bank of China Beijing China Chengdu Aerospace Science and Industry Big Data Research Institute Corporation Limited Chengdu China Sichuan Institute of Computer Sciences Chengdu China

ISBN: (数字)9781665499163

ISBN: (纸本)9781665499163

Due to the complex background of bank operation and maintenance scenarios, it is extremely difficult to detect and analyze the object of operation and maintenance scenarios. The traditional target detection algorithms, such as F-RCNN, are not suitable for object detection. We propose a lightweight object detection method for bank operation and maintenance scenarios based on deep learning. The proposed method highlights two improvements based on Yolov5. The first adjustment of it is this method constructs a new convolution method and a new activation function. Also, we use the multi-scale output strategy of Feature Pyramid Networks (FPN) to develop a new lightweight feature extraction algorithm. These changes we made are based on the real-life situation, such as bank operation and maintenance scenarios. Experiments have been carried out on the same data set with multiple object detection algorithms, and the experimental results show that the proposed method reduces the complexity of the activation function. Meanwhile, the module is flexible, and can be easily applied to other similar business scenario detection models. © 2022 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

FERI: Feature Enhancement and Relational Interaction for Image-text Matching 30

FERI: Feature Enhancement and Relational Interaction for Ima...

引用

30th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2024

作者： Zhang, Yu Zhang, Jianqiang Song, Gongpeng Lu, Qin Zhao, Shuo Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Jinan China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computer Networks Jinan China Shandong Branch of China Mobile Communication Group Design Institute Co. Jinan China

ISBN: (纸本)9798331515966

Image-text matching is an important problem at the intersection of computer vision and natural language processing. It aims to establish the semantic link between image and text to achieve high-quality semantic alignment between the two modalities. However, the existing methods have the problem that the meaning expressed in the image or the complex narrative in the text cannot be fully understood due to insufficient feature extraction. Moreover, due to the essential modal differences between images and texts, how to effectively and accurately align the semantic contents in images and texts has become the key of research. In order to solve the above problems, this paper proposes a method based on feature enhancement and relationship interaction. When processing images, the proposed method fuses labeled features, region features and location features to represent images. When processing text, a combination of Bi-GRU and self-attention mechanism is used to represent the text. In order to further align the semantic content in images and texts accurately, this paper improves two relational interaction mechanisms by identifying connection relationships and learning association relationships. Thus, the relation enhanced embedding is obtained. Finally, it calculated the similarity of the enhanced embedding to judge the matching degree of the image and text. Extensive experiments on the public datasets Flickr30K and MSCOCO demonstrate the effectiveness of our method. © 2024 IEEE.

关键词： cross-modal retrieval feature enhancement image-text matching relationship interaction

来源：评论

学校读者我要写书评

暂无评论

Text-guided HuBERT: Self-Supervised Speech Pre-training via Generative Adversarial Networks

arXiv

引用

arXiv 2024年

作者： Ma, Duo Yue, Xianghu Ao, Junyi Gao, Xiaoxue Li, Haizhou Shenzhen Research Institute of Big Data School of Data Science The Chinese University of Hong Kong Shenzhen518172 China Department of Electrical and Computer and Engineering National University of Singapore Singapore119077 Singapore

Human language can be expressed in either written or spoken form, i.e. text or speech. Humans can acquire knowledge from text to improve speaking and listening. However, the quest for speech pre-trained models to leverage unpaired text has just started. In this paper, we investigate a new way to pre-train such a joint speech-text model to learn enhanced speech representations and benefit various speech-related downstream tasks. Specifically, we propose a novel pre-training method, text-guided HuBERT, or T-HuBERT, which performs self-supervised learning over speech to derive phoneme-like discrete representations. And these phoneme-like pseudo-label sequences are firstly derived from speech via the generative adversarial networks (GAN) to be statistically similar to those from additional unpaired textual data. In this way, we build a bridge between unpaired speech and text in a unsupervised manner. Extensive experiments demonstrate the significant superiority of our proposed method over various strong baselines, which achieves up to 15.3% relative Word Error Rate (WER) reduction on the LibriSpeech dataset. © 2024, CC BY.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Suppress Content Shift: Better Diffusion Features via Off-the-Shelf Generation Techniques 38

Suppress Content Shift: Better Diffusion Features via Off-th...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Meng, Benyuan Xu, Qianqian Wang, Zitai Yang, Zhiyong Cao, Xiaochun Huang, Qingming Institute of Information Engineering CAS China School of Cyber Security University of Chinese Academy of Sciences China Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS China Peng Cheng Laboratory China School of Computer Science and Tech. University of Chinese Academy of Sciences China School of Cyber Science and Tech. Shenzhen Campus of Sun Yat-sen University China Key Laboratory of Big Data Mining and Knowledge Management CAS China

Diffusion models are powerful generative models, and this capability can also be applied to discrimination. The inner activations of a pre-trained diffusion model can serve as features for discriminative tasks, namely, diffusion feature. We discover that diffusion feature has been hindered by a hidden yet universal phenomenon that we call content shift. To be specific, there are content differences between features and the input image, such as the exact shape of a certain object. We locate the cause of content shift as one inherent characteristic of diffusion models, which suggests the broad existence of this phenomenon in diffusion feature. Further empirical study also indicates that its negative impact is not negligible even when content shift is not visually perceivable. Hence, we propose to suppress content shift to enhance the overall quality of diffusion features. Specifically, content shift is related to the information drift during the process of recovering an image from the noisy input, pointing out the possibility of turning off-the-shelf generation techniques into tools for content shift suppression. We further propose a practical guideline named GATE to efficiently evaluate the potential benefit of a technique and provide an implementation of our methodology. Despite the simplicity, the proposed approach has achieved superior results on various tasks and datasets, validating its potential as a generic booster for diffusion features. Our code is available at this url. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Capacity Maximization for Double Passive/Active RIS-Aided MISO Systems in Multi-User Scenarios

引用

IEEE Internet of Things Journal 2025年

作者： Peng, Xin Liu, Chenyu Yu, Chao Xie, Wenwu Yang, Liang Hunan Institute of Science and Technology School of Information Science and Engineering Yueyang414006 China Hunan Engineering Research Center for Autonomous Data Perception and Processing in Industrial Intelligent Networking Yueyang414006 China Hunan University College of Computer Science and Electronic Engineering Changsha410082 China

This paper addresses the problem of capacity maximization in double reconfigurable intelligent surface (RIS) -aided multiple-input single-output (MISO) systems under multi-user scenarios. A system model is proposed for double RIS-aided MISO configurations, incorporating both passive RIS (PRIS) and active RIS (ARIS). The primary objective is to maximize the minimum channel capacity across all users, and a corresponding optimization problem is formulated to achieve this goal. To overcome the challenges posed by the fractional structure of the non-convex objective function, auxiliary variables are introduced, and the bisection method is utilized. Given the highly coupled and nonconvex nature of the optimization variables, a joint alternating optimization (AO) algorithm is designed based on the bisection method and successive convex approximation (SCA), enabling iterative determination of the beamforming vectors at the base station and the reflection coefficients of RISs. The results indicate that deploying double RISs substantially enhances the system’s channel capacity through reflected links. Notably, the ARIS protocols yield higher performance gains, particularly under scenarios involving high total power and large amplification factors. In multi-user environments, the double RIS configuration significantly outperforms the single RIS setup due to the increased degrees of freedom, especially when supported by ARIS protocols. These findings underscore the substantial potential and advantages of double RIS configurations in complex communication environments. © 2014 IEEE.

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

An Adaptive Multi-Bernoulli Filter for Coexisting Point Target and Extended Target Tracking With Unknown Detection Probability

引用

IEEE Access 2025年 13卷 84593-84606页

作者： Li, Yuansheng Cui, Ling Ma, Junhu Luo, Zhaohui Chongqing Vocational Institute of Engineering College of Big Data and Internet of Things Chongqing402260 China Kunming University of Science and Technology Faculty of Information Engineering and Automation Kunming650500 China Southwest China Institute of Electronic Technology Chengdu610036 China Shunde Polytechnic College of Intelligent Manufacturing Shunde Foshan528300 China

This paper proposes an adaptive multi-Bernoulli (MB) filter for coexisting point target and extended target tracking, where the detection probability of each target is unknown and time-varying. The detection probability of the target directly affects the tracking accuracy in multi-sensor multi-target tracking. In realistic tracking circumstances, the detection probability of the target is unknown. Therefore, it is crucial to adaptively estimate the detection probability of the target in real-time. In addition, as the resolution of sensor increases, the point target and extended target often coexist in the field of view. Therefore, it is necessary to construct a generalized measurement model for tracking coexisting point target and extended target. For the coexistence of point and extended target, we model the spatial probability density function which can accommodate both point target and extended target based on a MB filter. For the unknown detection probability, we integrate the detection probability into the target state and the detection probability is characterized as a Beta distribution. To obtain a closed-form solution, the spatial probability density function of each MB component is modeled as a mixture of the Beta-Gaussian distribution and the Beta Gamma Gaussian Inverse Wishart (BGGIW) distribution. Based on the estimated probability of the point target, the target is determined as either a point target or an extended target. Finally, the detection probability, kinematic state, Poisson measurement rate (MR) and extended state of each target are estimated synchronously. Simulation results verify the effectiveness and robustness of the proposed algorithm. © 2013 IEEE.

关键词： Gaussian distribution

来源：评论

学校读者我要写书评

暂无评论

WSpeller: Robust Word Segmentation for Enhancing Chinese Spelling Check

WSpeller: Robust Word Segmentation for Enhancing Chinese Spe...

引用

2022 Findings of the Association for Computational Linguistics: EMNLP 2022

作者： Li, Fangfang Shan, Youran Duan, Junwen Mao, Xingliang Huang, MinLie School of Computer Science and Engineering Central South University China Institute of Big Data and Internet Innovation Hunan University of Technology and Business China Beijing National Research Center for Information Science and Technology Tsinghua University China

Chinese spelling check (CSC) detects and corrects spelling errors in Chinese texts. Previous approaches have combined character-level phonetic and graphic information, ignoring the importance of segment-level information. According to our pilot study, spelling errors are always associated with incorrect word segmentation. When appropriate word boundaries are provided, CSC performance is greatly enhanced. Based on these findings, we present WSpeller, a CSC model that takes into account word segmentation. A fundamental component of WSpeller is a W-MLM, which is trained by predicting visually and phonetically similar words. Through modification of the embedding layer's input, word segmentation information can be incorporated. Additionally, a robust module is trained to assist the W-MLM-based correction module by predicting the correct word segmentations from sentences containing spelling errors. We evaluate WSpeller on the widely used benchmark datasets SIGHAN13, SIGHAN14, and SIGHAN15. Our model is superior to state-of-the-art baselines on SIGHAN13 and SIGHAN15 and maintains equal performance on SIGHAN14. © 2022 Association for Computational Linguistics.

关键词： Errors

来源：评论

学校读者我要写书评

暂无评论

Not All Diffusion Model Activations Have Been Evaluated as Discriminative Features 38

Not All Diffusion Model Activations Have Been Evaluated as D...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Meng, Benyuan Xu, Qianqian Wang, Zitai Cao, Xiaochun Huang, Qingming Institute of Information Engineering CAS China School of Cyber Security University of Chinese Academy of Sciences China Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS China Peng Cheng Laboratory China School of Cyber Science and Tech. Shenzhen Campus of Sun Yat-sen University China School of Computer Science and Tech. University of Chinese Academy of Sciences China Key Laboratory of Big Data Mining and Knowledge Management CAS China

Diffusion models are initially designed for image generation. Recent research shows that the internal signals within their backbones, named activations, can also serve as dense features for various discriminative tasks such as semantic segmentation. Given numerous activations, selecting a small yet effective subset poses a fundamental problem. To this end, the early study of this field performs a large-scale quantitative comparison of the discriminative ability of the activations. However, we find that many potential activations have not been evaluated, such as the queries and keys used to compute attention scores. Moreover, recent advancements in diffusion architectures bring many new activations, such as those within embedded ViT modules. Both combined, activation selection remains unresolved but overlooked. To tackle this issue, this paper takes a further step with a much broader range of activations evaluated. Considering the significant increase in activations, a full-scale quantitative comparison is no longer operational. Instead, we seek to understand the properties of these activations, such that the activations that are clearly inferior can be filtered out in advance via simple qualitative evaluation. After careful analysis, we discover three properties universal among diffusion models, enabling this study to go beyond specific models. On top of this, we present effective feature selection solutions for several popular diffusion models. Finally, the experiments across multiple discriminative tasks validate the superiority of our method over the SOTA competitors. Our code is available at this url. © 2024 Neural information processing systems foundation. All rights reserved.

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：