检索结果-内蒙古大学图书馆

2nd International Conference on Image Processing, computer Vision and Machine Learning, ICICML 2023

作者： Ge, Yiyuan Zhang, Ji Chen, Zhihao Li, Bi Beijing Information Science and Technology University School of Instrument Science and Opto-Electronics Engineering Beijing China Beijing Information Science and Technology University Computer School Beijing China Xidian University School of Mechano- Electronic Engineering Xian China

ISBN: (纸本)9798350331417

Within the domain of computer vision, person search stands out as a crucial and intricate undertaking. With the growth of urban population and the popularity of surveillance cameras, person search demonstrates its versatility in a multitude of applications, particularly within the realm of video surveillance, public safety and intelligent transportation. The person search task is comprised of two subtasks, namely person detection and person re-identification (ReID),the task of person detection concentrates on identifying similarities among diverse identities. In contrast, person ReID task centres on discovering dissimilarities among distinct identities. In order to reduce the influence of variations in tasks during the model training phase, we segment the ResNet50 network according to the subtasks and propose an end-to-end content-aware person search framework. Where the detection branch is built on top of shallow features and the person ReID branch is built on top of deep features. Meanwhile, we introduce gated deformable convolution module(GDCM)to sense the location of the person and further distinguish the background from the person. Finally, the effectiveness of the method is demonstrated on two authoritative datasets(CUHK-SYSUPRW). © 2023 IEEE.

关键词： Content-aware Gated Deformable Convolution Person search

来源：评论

学校读者我要写书评

暂无评论

Data Mining with Privacy Protection Using Precise Elliptical Curve Cryptography

引用

Intelligent Automation & Soft Computing 2023年第1期35卷 839-851页

作者： B.Murugeshwari D.Selvaraj K.Sudharson S.Radhika Department of Computer Science and Engineering Velammal Engineering CollegeChennai600066India Department of Electronics and Communication Engineering Panimalar Engineering CollegeChennai600123India Department of Information Technology Velammal Insitutue of TechnologyChennai601204India Department of Computer Science and Engineering Saveetha School of EngineeringSaveetha Institute of Medical and Technical SciencesChennai600124India

Protecting the privacy of data in the multi-cloud is a crucial *** mining is a technique that protects the privacy of individual data while mining those *** most significant task entails obtaining data from numerous remote *** algorithms can obtain sensitive information once the data is in the data *** traditional algorithms/techniques promise to provide safe data transfer,storing,and retrieving over the cloud *** strategies are primarily concerned with protecting the privacy of user *** study aims to present data mining with privacy protection(DMPP)using precise elliptic curve cryptography(PECC),which builds upon that algebraic elliptic curve *** approach enables safe data exchange by utilizing a reliable data consolidation approach entirely reliant on rewritable data concealing ***,it outperforms data mining in terms of solid privacy procedures while maintaining the quality of the *** approximation error,computational cost,anonymizing time,and data loss are considered performance *** suggested approach is practical and applicable in real-world situations according to the experimentalfindings.

关键词： Data mining cryptography privacy preserving elliptic curve information security

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Deep Learning Approaches for Aspect-Based Sentiment Classification 4th

Comparative Analysis of Deep Learning Approaches for Aspect-...

引用

4th International Conference on Data, engineering, and Applications, IDEA 2022

作者： Satyarthi, Shailendra Sharma, Sanjiv Department of Computer Science and Engineering Madhav Institute of Technology and Science Gwalior India Department of Information Technology Madhav Institute of Technology and Science Gwalior India

ISBN: (纸本)9789819700363

Social networking-based platforms (e.g., Twitter, Facebook, Amazon) where users feel free to express their opinion/sentiment about any product, service or event, in the form of reviews, tweets, blogs, etc., in the last decade with the enhanced use of social media and social networking, result in huge amount of data in unstructured and unorganized form, and the need of sentiment analysis of user’s opinionated text arises for improvement in the product or service policymaking decisions. Therefore, sentiments in user’s text play crucial role, and classifying the sentiment (positive, negative or neutral) at review/document level or at sentence level is not sufficient for achieving the real solution for improvement in product, service or an event;therefore, there is a need of deeper level and fine-grained analysis at aspect level known as aspect-based sentiment classification (ABSC) which attract researchers. This paper emphasizes on various existing approaches for ABSC specifically deep learning methods and their comparative analysis. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Tweets

来源：评论

学校读者我要写书评

暂无评论

CLIMB-ReID: A Hybrid CLIP-Mamba Framework for Person Re-identification 39

CLIMB-ReID: A Hybrid CLIP-Mamba Framework for Person Re-iden...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Yu, Chenyang Liu, Xuehu Zhu, Jiawen Wang, Yuhao Zhang, Pingping Lu, Huchuan School of Information and Communication Engineering Dalian University of Technology Dalian China School of Computer Science and Artificial Intelligence Wuhan University of Technology Wuhan China School of Future Technology School of Artificial Intelligence Dalian University of Technology Dalian China

ISBN: (纸本)157735897X

Person Re-IDentification (ReID) aims to identify specific persons from non-overlapping cameras. Recently, some works have suggested using large-scale pre-trained vision-language models like CLIP to boost ReID performance. Unfortunately, existing methods still struggle to address two key issues simultaneously: efficiently transferring the knowledge learned from CLIP and comprehensively extracting the context information from images or videos. To address these issues, we introduce CLIMB-ReID, a pioneering hybrid framework that synergizes the impressive power of CLIP with the remarkable computational efficiency of Mamba. Specifically, we first propose a novel Multi-Memory Collaboration (MMC) strategy to transfer CLIP’s knowledge in a parameter-free and prompt-free form. Then, we design a Multi-Temporal Mamba (MTM) to capture multi-granular spatiotemporal information in videos. Finally, with Importance-aware Reorder Mamba (IRM), information from various scales is combined to produce robust sequence features. Extensive experiments show that our method outperforms other state-of-the-art methods on both image and video person ReID benchmarks. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Product selection method based on feature level fusion of heterogeneous product data 4

Product selection method based on feature level fusion of he...

引用

4th International Conference on Neural Networks, information and Communication engineering, NNICE 2024

作者： Qin, Jinfei Huang, Jun Wang, Qingfeng Liu, Zhiqin Southwest University of Science and Technology Department of Electronic Information Mianyang China Southwest University of Science and Technology School of Computer Science and Technology Mianyang China

ISBN: (纸本)9798350394375

To enable e-commerce sellers to identify products favoured by consumer groups and thereby increase their store's sales and profit margins, a product classification model based on feature-level fusion of heterogeneous data is proposed. The model uses a convolutional neural network to learn feature representations from product title, descriptions and reviews. It also uses a deep autoencoder to learn feature representations from product attributes. By combining the features of heterogeneous data, a comprehensive representation of the product is obtained. Experiments were conducted using data from all basketball products on the Amazon e-commerce platform. The results of the experiments showed that building a product classification model based on heterogeneous data outperformed using only product title. The accuracy of the model improved by 3.13% and the F1 score increased by 4.54%. These results strongly suggest that the product classification model based on heterogeneous data has learned more comprehensive features related to product popularity. © 2024 IEEE.

关键词： Electronic commerce

来源：评论

学校读者我要写书评

暂无评论

A Cluster-Based OFDMA MAC Protocol using Carrier-Sensing Scheme for IEEE 802.11ax WLANs 14

A Cluster-Based OFDMA MAC Protocol using Carrier-Sensing Sch...

引用

14th International Conference on Ubiquitous and Future Networks, ICUFN 2023

作者： Chen, Yen-Da Lin, Jia-Wei Hsueh, Mu-Hua Shih, Kuei-Ping Lunghwa University of Science and Technology Department of Computer Information and Network Engineering Taiwan Tamkang University Department of Computer Science and Information Engineering Taiwan

ISBN: (纸本)9798350335385

Orthogonal Frequency Division Multiple Access (OFDMA) is utilized in wireless local area networks (WLANs) to improve channel utilization and increase network throughput. However, random transmissions by wireless stations can lead to Resource Unit Collision Problem (RUCP) and Hidden Node induced RUCP (HN-RUCP), significantly degrading network throughput. Therefore, this paper proposes a Cluster-based OFDMA MAC protocol using the Carrier-sensing scheme, CC-OFDMA, for dense WLANs. Simulation results conducted using MATLAB show that the CC-OFDMA MAC protocol outperforms related works in terms of transmission latency and collisions. © 2023 IEEE.

关键词： Frequency division multiple access

来源：评论

学校读者我要写书评

暂无评论

An AI Planning Approach to Supply Chain Logistics Planning and Scheduling 6

An AI Planning Approach to Supply Chain Logistics Planning a...

引用

6th International Conference on Internet of Things, Automation and Artificial Intelligence, IoTAAI 2024

作者： Tu, Mingjun Liang, Ruishi Zheng, Fanghao University of Electronic Science and Technology of China School of Computer Science and Engineering ChengDu China University of Electronic Science and Technology of China Zhongshan Institute School of Computer Science Zhongshan China

ISBN: (纸本)9798350386974

Fuelled by rapid advancements in logistics technology and the internet, the transaction volume in the food industry continues to soar, accompanied by escalating consumer expectations regarding the freshness and safety of various foods, notably perishable produce, chilled products, and pre-prepared dishes. As the key step ensuring the freshness and safety of food, efficient planning and optimization of supply chain logistics have become increasingly vital. This paper introduces an AI planning model for supply chain logistics planning and scheduling. Firstly, it extracts knowledge from the supply chain logistics process, with particular emphasis on controlling cargo damage and costs induced by temperature fluctuations in cold chain logistics. Secondly, incorporating elements of numerical and preference planning, a dual-objective optimization model is established, aiming at concurrently minimizing costs and reducing cargo losses during planning. Formulated using PDDL (Planning Domain Definition Language), this model is transformed into an AI-planning task. Ultimately, the model's effectiveness is demonstrated through scenario-based resolution by planning algorithms, showcasing its capability to make optimized decisions tailored to diverse objectives. It adeptly balances cost reduction with cargo damage mitigation, thereby enhancing customer satisfaction and furnishing invaluable guidance for supply chain logistics planning and scheduling. © 2024 IEEE.

关键词： Customer satisfaction

来源：评论

学校读者我要写书评

暂无评论

Intercommunication Method between Local Edge Computing Devices Using QUIC-Based CYPHONIC

Intercommunication Method between Local Edge Computing Devic...

引用

2024 IEEE International Conference on Consumer Electronics, ICCE 2024

作者： Horisaki, Shota Matama, Kazushige Goto, Ren Naito, Katsuhiro Suzuki, Hidekazu Meijo University Graduate School of Science and Technology Nagoya Japan Aichi Institute of Technology Graduate School of Business Administration and Computer Science Toyota Japan Aichi Institute of Technology Faculty of Information Science Toyota Japan Meijo University Faculty of Information Engineering Nagoya Japan

ISBN: (纸本)9798350324136

Internet of Things (IoT) devices are installed in various locations to realize smart cities, smart factories, smart homes, etc., and are connected to the Internet for data communication. Most current IoT systems are built on a client-server model using servers built on the cloud. On the other hand, edge computing services are increasing and there are still demands to manage sensitive data in a local environment, and a local edge computing is emerging as a new concept to address these demands. Next-generation IoT services are expected to increase the importance of interoperability between different IoT systems, and connectivity to the local edge computing environment will be required. The authors have proposed QUIC-based CYPHONIC (CYber PHysical Overlay Network over Internet Communication) as a communication architecture that simultaneously achieves communication connectivity and mobility transparency in a mixed IPv4/IPv6 environment. This paper shows that QUIC-based CYPHONIC can be used to realize end-To-end encrypted communication between local edge devices located in different local networks over the actual Internet environment with practically acceptable performance. © 2024 IEEE.

关键词： End-To-End Connectivity Local Edge Computing Overlay Network QUIC

来源：评论

学校读者我要写书评

暂无评论

RM-CSTV:An effective high-resolution method of non-line-of-sight millimeter-wave radar 3-D imaging

引用

National science Open 2024年第5期3卷 36-52页

作者： Xinyuan Liu Shunjun Wei Wei Pu Xiang Cai Yanbo Wen Shisheng Guo Lingjiang Kong Xiaoling Zhang School of Information and Communication Engineering University of Electronic Science and Technology of ChinaChengdu 611731China

Non-line-of-sight(NLOS)imaging is a novel radar sensing technology that enables the reconstruction of hidden ***,it may suffer from synthetic aperture length reduction caused by ambient *** this study,a complex total variation(CTV)regularization-based sparse reconstruction method for NLOS three-dimensional(3-D)imaging by millimeter-wave(mm W)radar,named RM-CSTV method,is proposed to improve imaging quality and *** this scheme,the NLOS imaging model is first introduced,and associated geometric constraints for NLOS objects are ***,an effective high-resolution NLOS imaging method based on the range migration(RM)kernel and complex sparse joint total variation constraint,dubbed as modified RM-CSTV,is proposed for 3-D high-resolution imaging with edge *** experiments with multi-type NLOS targets show that the proposed RM-CSTV method can provide effective and high-resolution NLOS targets 3-D imaging.

关键词： NLOS imaging 3-D-SAR 3-D imaging sparse reconstruction

来源：评论

学校读者我要写书评

暂无评论

Digital Regimen for Parkinson Disease: An Informative Approach Using Mobile Application 2

Digital Regimen for Parkinson Disease: An Informative Approa...

引用

2nd International Conference on Emerging Trends in information technology and engineering, ic-ETITE 2024

作者： Seya Prakash, P. Gunasekaran, G. School of Computer Science Engineering and Information Systems Vellore Institute of Technology Vellore India Vellore Institute Technology Department of Smart Computing Vellore India

ISBN: (纸本)9798350328202

Parkinson's disease (PD) is an advanced neuro-degenerative condition where a large number of people around the world are profoundly affected. The scarcity of precise data regarding the typical circumstances faced by humans with PD severely restricts ongoing research and therapeutic endeavours. This proposed work aims to investigate various innovations to address this issue comprehensively. Specifically, this proposed work intends to develop a versatile application tailored to help the PD patients and incorporating smart medication reminders. Moreover, this proposed work will focus on creating exercise/workout plans & diet plans based on continuous data collection and patient feedback to enhance prescription management while minimizing side effects. Simultaneously, initiatives aimed at reducing the stress level and improve mental health. The development and implementation of this versatile applications hold significant promise in improving patient outcomes. By addressing the dearth of accurate information and fostering a systematic support ecosystem, it aspires to enhance the lives of individuals grappling with PD on a global scale. © 2024 IEEE.

关键词： Neurodegenerative diseases

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：