检索结果-内蒙古大学图书馆

IEEE International Conference on Systems, Man and Cybernetics

作者： Huanxiao Zhou Yushui Geng Jing Zhao Xishan Ma 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 Graduate School Qilu University of Technology (Shandong Academy of Sciences) Jinan China

ISBN: (数字)9781665410205

ISBN: (纸本)9781665410212

Image-text retrieval refers to querying the text or image of another modality given an image or text, and its key lies in the ability to accurately measure the similarity between text and image. Most of the existing retrieval methods only utilize the intramodal relations of each modality or the intermodal relations of the two modalities to perform the retrieval task. To address the above problems, we integrate the intra-modal and inter-modal relations and propose a Semantic Relation-based Cross Attention network(SRCAN). In our proposed method, we first mine the possible intra-modal associations between regions in an image and between words in a text to obtain features with semantic relationships, and then capture the fine-grained associations between segments through the cross-attention mechanism. Finally, we balance the intra-modal and inter-modal relationships to improve the performance of the model. Our proposed method is experimentally validated on two datasets, Flickr30K and MS-COCO, and the experimental results show that our method achieves superior results.

关键词： Image segmentation Semantics Bidirectional control Feature extraction Cognition Feeds Cybernetics

来源：评论

学校读者我要写书评

暂无评论

High-Fidelity and High-Efficiency Talking Portrait Synthesis With Detail-Aware Neural Radiance Fields

引用

IEEE Transactions on Visualization and computer Graphics 2024年 PP卷 PP-PP页

作者： Wang, Muyu Zhao, Sanyuan Dong, Xingping Shen, Jianbing Wuhan University School of Computer Science National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan430072 China Beijing Institute of Technology School of Computer Science Beijing China University of Macau State Key Laboratory of Internet of Things for Smart City Department of Computer and Information Science China

In this paper, we propose a novel rendering framework based on neural radiance fields (NeRF) named HH-NeRF that can generate high-resolution audio-driven talking portrait videos with high fidelity and fast rendering. Specifically, our framework includes a detail-aware NeRF module and an efficient conditional super-resolution module. Firstly, a detail-aware NeRF is proposed to efficiently generate a high-fidelity low-resolution talking head, by using the encoded volume density estimation and audio-eye-aware color calculation. This module can capture natural eye blinks and high-frequency details, and maintain a similar rendering time as previous fast methods. Secondly, we present an efficient conditional super-resolution module on the dynamic scene to directly generate the high-resolution portrait with our low-resolution head. Incorporated with the prior information, such as depth map and audio features, our new proposed efficient conditional super resolution module can adopt a lightweight network to efficiently generate realistic and distinct high-resolution videos. Extensive experiments demonstrate that our method can generate more distinct and fidelity talking portraits on high resolution (900 × 900) videos compared to state-of-the-art methods. Our code is available at https://***/muyuWang/HHNeRF. © 1995-2012 IEEE.

关键词： Rendering (computer graphics)

来源：评论

学校读者我要写书评

暂无评论

NM-LUD: A NLOS Mitigation Method with Low-cost UWB Devices for Indoor Positioning

NM-LUD: A NLOS Mitigation Method with Low-cost UWB Devices f...

引用

International Conference on computers, Communications, and Systems (ICCCS)

作者： Tong Wu Han Li Bo Gao Ke Xiong Pingyi Fan Khaled Ben Letaief Engineering Research Center of Network Management Technology for High Speed Railway of Ministry of Education School of Computer and Information Technology Beijing Jiaotong University Beijing China Collaborative Innovation Center of Railway Traffic Safety Beijing Jiaotong University Beijing China National Engineering Research Center of Advanced Network Technologies Beijing Jiaotong University Beijing China Department of Electronic Engineering Tsinghua University Beijing China Department of Electrical and Computer Engineering Hong Kong University of Science and Technology Hong Kong

Ultra-wideband (UWB) is a popular technology for indoor positioning. However, non-line-of-sight (NLOS) propagation caused by human occlusion dramatically affects the accuracy of UWB-based indoor positioning. Most of the existing works focused on mitigating NLOS errors in the scenarios with building structure occlusion, but the NLOS mitigation under human occlusion has not been well addressed. To this end, this paper aims to mitigate the NLOS impact of human occlusion, and then proposes a method of NLOS mitigation to reduce NLOS ranging errors under human occlusion with low-cost UWB devices (i.e., NM-LUD). It takes a set of signal features extracted from low-cost devices as input, calculates their weights and mitigates the ranging error based on the features' weights. Experiment results on the two data sets collected by LinkTrack S and UML1 UWB devices show that the method reduces ranging error from 0.9009 m to 0.1435 m (about by 84.07%) and from 0.7466 m to 0.0792 m (about by 89.39%) respectively, which greatly mitigates the influence of NLOS caused by human occlusion.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cross-modal retrieval based on Attention Embedded Variational Auto-Encoder

Cross-modal retrieval based on Attention Embedded Variationa...

引用

International Joint Conference on Neural networks (IJCNN)

作者： Kaili Zhou Yiyun Xing Yushui Geng Jing Zhao 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 Graduate School Qilu University of Technology (Shandong Academy of Sciences) Jinan China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

This study proposes a cross-modal retrieval technique, which employs an Attention Embedded Variational AutoEncoder (AE-VAE) to tackle the problem of reduced retrieval accuracy resulting from data noise and data absence in cross-modal retrieval tasks. First, the variational auto-encoder(VAE) is used as an infrastructure to transform modal data into latent variables by encoding and decoding different modal features, thus preserving the semantic structure of the raw modal data and suppressing noise and missing information in the data. Secondly, to better capture the important semantic features of image and text modalities, an improved multi-attention module is introduced in the encoder. In addition, a cross-modal alignment module is designed to further align the latent variables of different modalities in the latent space to solve the confusion problem and improve the accuracy and robustness of cross-modal retrieval. Finally, experiments are conducted on four public datasets, CUB, SUN, AwA1 and AwA2, and the experimental results show that our proposed model is effective in improving the accuracy and robustness of retrieval.

关键词： Accuracy Uncertainty Noise Semantics Transforms Probabilistic logic Robustness

来源：评论

学校读者我要写书评

暂无评论

Semantic-Enhanced Attention network for Image-Text Matching

Semantic-Enhanced Attention Network for Image-Text Matching

引用

International Conference on computer Supported Cooperative Work in Design

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

Image-text matching is an important task in cross-modal information processing, which consists of evaluating the similarity between images and text. However, the data of the two modalities have different distributions and representations, which cannot be directly compared. Therefore, the two modalities need to be processed separately. Most existing image-text matching methods extract image fragments and text fragments separately, using an attention mechanism to establish relationships between regions in the image and words in the text. Subsequently, they aggregate the similarity of these images and text fragments. Regardless, not all fragment alignment is meaningful, and irrelevant fragment alignment will bring redundancy and reduce retrieval accuracy. In addition to that, there are contextual relationships between image regions and between text words, which should also be taken into account. In this paper, we simultaneously consider these two aspects and propose a Semantic-Enhanced Attention network (SEAN). It first focuses on each modality, mining contextual relationships between fragments within each modality and aggregating contextual information into visual and textual embeddings. Then, we compute the similarity between all image regions and text fragments, focusing all attention on the region-word pairs with the highest similarity. Finally, we summarize these to infer the similarity between the image and text. Our method achieves competitive results on two generalized image text retrieval datasets, Flickr30K and MS-COCO.

关键词： Visualization Attention mechanisms Federated learning Computational modeling Aggregates Semantics Redundancy

来源：评论

学校读者我要写书评

暂无评论

Analysis of Anomaly Detection Techniques Applied to Web API network Scenario 11

Analysis of Anomaly Detection Techniques Applied to Web API ...

引用

11th Joint International Information technology and Artificial Intelligence Conference, ITAIC 2023

作者： Huang, Zhendong Fan, Xuyan Li, Zhiqi Zhao, Changzhi Chen, Guangxuan Liu, Yuling People's Public Security University of China Department of Information and Network Security Beijing China Ruian Public Security Bureau Wenzhou China Zhejiang Police College Department of Computer and Information Security Hangzhou China The National Information Center of China Customs Beijing China Beijing State Grid Siji Network Security Technology Limited Company Beijing China Institute of Information Engineering Chinese Academy of Sciences Beijing China

ISBN: (纸本)9798350333664

Web API networks comprise a multitude of API services, and compared to traditional network environments, they possess unique security requirements and face distinct threats. This article delves into the security characteristics of Web API networks and the particular threats they encounter, establishing evaluation criteria for anomaly detection models tailored to Web API networks and their associated scenarios. Through an integrated assessment of numerous studies, we meticulously compare and analyze various models in terms of false positive rates, robustness, detection latency, and their adaptability and detection capabilities. The findings reveal that while many models excel in detecting singular attacks within the Web API network context, their scope of attack detection is often constrained, making it challenging to comprehensively address the myriad threats Web API networks confront. Moreover, several unresolved challenges persist in the research, such as the scarcity of real-world datasets, inadequate model generalization capabilities, and subpar robustness. © 2023 IEEE.

关键词： anomaly detection API calls model evaluation scenario application Web API network

来源：评论

学校读者我要写书评

暂无评论

A Multimodal Medical Image Fusion Method Incorporating an Adaptive Attention Mechanism

A Multimodal Medical Image Fusion Method Incorporating an Ad...

引用

International Conference on computer Supported Cooperative Work in Design

作者： Yingxian Zhang Yushui Geng Hu Liang Hai Zhong 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 Industrial Network and Information System Security Shandong Fundamental Research Center for Computer Science Jinan China Graduate School Qilu University of Technology (Shandong Academy of Sciences) Jinan China Department of Radiology The Second Hospital of Shandong University Jinan China

ISBN: (数字)9798331513054

ISBN: (纸本)9798331513061

Multimodal medical image fusion technology provides more comprehensive and accurate image support for clinical diagnosis and treatment by integrating complementary information from different imaging modalities. Aiming at the problem that existing methods are still insufficient in detail feature extraction and inter-modal information fusion, this paper proposes a multimodal medical image fusion method combined with an adaptive attention mechanism. First, we design the Grouped Receptive Field Attentional Convolution (GRFAConv) to solve the problem of insufficient detail feature extraction capability. With the multi-head receptive field adaptive weighting strategy of grouped convolution, the range and weight of the receptive field of the convolution kernel can be adaptively adjusted according to the different demands of local and global features of the image to improve the effect of detail retention. Second, for the problem of information fusion between different modalities, we introduce an improved CBAM attention module in the feature fusion process, which adaptively selects and enhances the features in the key regions through the channel attention and spatial attention mechanisms, which greatly improves the clarity of the fused image details and the accuracy of the information expression in the key regions. Furthermore, experimental results on several medical image datasets show that the algorithm proposed in this paper can generate relatively high-quality fused images. It not only enriches the detailed features of the image, but also achieves significant advantages in several evaluation metrics.

关键词： Measurement Attention mechanisms Accuracy Convolution Federated learning Feature extraction Clinical diagnosis Kernel Medical diagnostic imaging Image fusion

来源：评论

学校读者我要写书评

暂无评论

Quantum Privacy-Preserving Price E-Negotiation

arXiv

引用

arXiv 2023年

作者： Liu, Wen-Jie Li, Chun-Tang Zheng, Yu Xu, Yong Xu, Yin-Song Jiangsu Engineering Center of Network Monitoring Nanjing University of Information Science & Technology Nanjing210044 China School of Computer and Software Nanjing University of Information Science & Technology Nanjing210044 China

Privacy-preserving price e-negotiation (3PEN) is an important topic of secure multi-party computation (SMC) in the electronic commerce field, and the key point of its security is to guarantee the privacy of seller’s and buyer’s prices. In this study, a novel and efficient quantum solution to the 3PEN problem is proposed, where the oracle operation and the qubit comparator are utilized to obtain the comparative results of buyer’s and seller’s prices, and then quantum counting is executed to summarize the total number of products which meets the trading conditions. Analysis shows that our solution not only guarantees the correctness and the privacy of 3PEN, but also has lower communication complexity than those classical ones. © 2023, CC BY.

关键词： Comparators (optical)

来源：评论

学校读者我要写书评

暂无评论

Small Target Detection from DIKW Model Perspective

Small Target Detection from DIKW Model Perspective

引用

2024 International Conference on Remote Sensing, Mapping, and Image Processing, RSMIP 2024

作者： Wang, Yujuan Peng, Ling Yu, Riji Juan, Hu Yan, Shankai Zhang, Bin Guangzhou Xinhua University Machong Town Guangdong Province Dongguan City China Huanggang Real Estate Registration Center Huanggang Land and Resources Bureau Huanggang City China School of Art Hubei University Wuhan China School of Computer Science and Information Engineering Hubei University Wuhan China The Discipline Inspection and Supervision College of Huanggang Normal University Huanggang City China School of Computer Science Technology Hainan University Haikou China Network Information Center Xinjiang University of Political Science and Law Tumushuke China Department of Computer Science City University of Hong Kong Hong Kong School of Remote Sensing and Information Engineering Wuhan University Hong Kong Hong Kong

ISBN: (纸本)9781510680012

Through the revelation and internal logic relationship of the DIKW model, the logic of data, information, knowledge, and wisdom in small target detection research initially built a new point of view, and did some basic tasks for small target detection and research, so as to use it to use it to do some basic tasks for small target detection and research. Small target detection research model under DIKW. The DIKW Information System was introduced into the field of small target testing. First, the DIKW model was analyzed. The framework of data information -information knowledge -intelligent framework was studied, and small target detection methods of one -stage and two -stage stages were studied, such as CNN -based methods, transformer methods and mixed methods. This article analyzes the basic network framework of small target detection, and builds data, information, knowledge and wisdom in small targets detection research. © 2024 SPIE.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

DQ-WiAPDoM: A DQN-based AP Deployment Optimization Method for Wi-Fi FTM Positioning

DQ-WiAPDoM: A DQN-based AP Deployment Optimization Method fo...

引用

Smart Technologies and Systems for Next Generation Computing (ICSTSN), International Conference on

作者： Zihao Liu Han Li Bo Gao Ke Xiong Pingyi Fan School of Computer and Information Technology Beijing Jiaotong University Beijing China Engineering Research Center of Network Management Technology for High Speed Railway of Ministry of Education School of Computer and Information Technology Beijing Jiaotong University Beijing China Department of Electronic Engineering Tsinghua University Beijing China

This paper focuses on how to optimize the deployment location of the anchor Wi-Fi access points (APs) in order to enhance the indoor positioning performance of the finetime measurement (FTM) protocol. Compared to conventional Wi-Fi positioning, FTM protocol is able to achieve relatively good indoor positioning performance since it estimates distance between a sender and its receiver with the flight duration of Wi-Fi signals. However, the FTM-based positioning accuracy in NLoS environments is still not high, which restricts its application in indoor scenarios. To this end, we formulate an optimization problem to maximize the total number of LoS paths by optimizing the locations of the anchor APs. To solve the problem, we propose a Deep Q-network (DQN)-based AP deployment optimization method (DQ-WiAPDoM), which utilizes DQN to optimize the locations of APs such that the total number of LoS paths over all covered area is maximized. Experimental results show that DQ-WiAPDoM converges well and is able to reduce the average positioning error efficiently.

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：