检索结果-内蒙古大学图书馆

22nd international conference on Advances in Mobile Computing and Multimedia Intelligence, MoMM 2024

作者： Tsuchida, Shuhei Ohnishi, Ayumi Mukai, Kae Watanabe, Ken Watanabe, Katsumi Terada, Tsutomu Tsukamoto, Masahiko Ochanomizu University 2-1-1 Otsuka Tokyo Bunkyo-ku112-8610 Japan Kobe University 1-1 Rokkodai-cho Nada-ku Kobe657-8501 Japan Waseda University 3-4-1 Okubo Tokyo Shinjuku-ku169-8555 Japan

ISBN: (纸本)9783031780486

This study is the initial phase in developing coping mechanisms for individuals who struggle with ‘choking under pressure’ due to stress. We focus on examining the motion and physiological information of dancers in high-pressure performance and low-pressure practice environments. Our primary objective is to identify key differences in stress responses between individuals who manage pressure well and those who do not. Through a comparative analysis of the motion and physiological information, we seek to identify the disparities between those who are adept at handling choking under pressure and those who are not. To simulate a high-pressure performance environment, a dance audition will be conducted and the physical and mental state of the auditionees during the evaluation process will be monitored and analyzed. The results indicated that auditionees who were unable to cope with choking under pressure showed significantly reduced physical movements compared to those who were able to handle it. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Audition

来源：评论

学校读者我要写书评

暂无评论

A Weakly Supervised Semantic Segmentation Model with Enhanced CLIP Feature Extraction

A Weakly Supervised Semantic Segmentation Model with Enhance...

引用

international conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Fanxuan Kong Jun Lu College of Computer Science and Technology Heilongjiang University Harbin China Jiaxiang Industrial Technology Research Institute of Heilongjiang University Jining China Key Laboratory of Database and Parallel Computing of Heilongjiang Province Harbin China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

This paper addresses the limitations of the Contrastive Language-Image Pre-training (CLIP) model’s image encoder and proposes a segmentation model WSSS-ECFE with enhanced CLIP feature extraction, aiming to improve the performance of the Weakly Supervised Semantic Segmentation (WSSS) task. WSSS-ECFE employs the Enhanced Bottleneck module proposed in this paper and adds dynamic residual connection to improve the model’s processing effect on complex scenes. In terms of implementation, the Enhanced Bottleneck module employs the Swish activation function and the Depthwise Separable Convolution to enhance the feature extraction and segmentation capability of the model, and uses multiple attention mechanisms to further optimize the feature representation and segmentation accuracy. The WSSS task on the public datasets PASCAL VOC 2012 and MS COCO 2014 achieves 82.6% and 56.3% mean intersection over union (mIoU), achieving state-of-the-art performance in models with low resource requirements.

关键词： Training Attention mechanisms Accuracy Convolution Semantic segmentation Graphics processing units Feature extraction Boosting Acoustics Speech processing

来源：评论

学校读者我要写书评

暂无评论

DRANet: Dual-threshold Guided Reliability Aware Network for Semi-Supervised Image Semantic Segmentation

DRANet: Dual-threshold Guided Reliability Aware Network for ...

引用

international conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Lizhe Qiu Mingyang Zhang Yuan Zheng College of Computer Science Inner Mongolia University Huhhot PR China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Different from supervised semantic segmentation task, semi-supervised semantic segmentation (SSSS) aims to alleviate the burden of time-consuming pixel-wise manual labeling. Although existing methods have achieved the promising performance with a small amount of labeled images, they still suffer from an insufficient mining on a large amount of unlabeled images due to simple evaluation way for them. To address this issue, we propose a novel Dual-threshold Guided Reliability Aware Network (DRANet) for SSSS task. To comprehensively evaluate the reliability of unlabeled images, we provide a dual-threshold guided augmentation module (DGAM), which not only introduces two predefined thresholds to group unlabeled images with different confidences according to their learning status, but also performs different data augmentations on unlabeled images based on their evaluation results. In particular, for an unlabeled image with higher confidence, a double-stream augmentation strategy is adopted, leading to a more sufficient learning for it. Experiments on Cityscapes and Pascal VOC 2012 datasets confirm the superiority of our DRANet over existing methods. Code is available at https://***/ZY-IMU-CV/DRANet_QLZ_2024.

关键词： Training Semantic segmentation Semantics Manuals Signal processing Data augmentation Reliability Labeling Data mining Speech processing

来源：评论

学校读者我要写书评

暂无评论

Remote Sensing Based Crop Monitoring Techniques: A Case Study for the Navajo Nation

Remote Sensing Based Crop Monitoring Techniques: A Case Stud...

引用

2024 Annual conference, ASPRS 2024

作者： Thangavel, Varatharajaperumal Nagarajan, Sudhagar Arockiasamy, Madasamy Khan, Md. Tarique Sklivanitis, George Department of Civil Environmental and Geomatics Engineering Florida Atlantic University FL United States School of Engineering Math & Technology Faculty Navajo Technical University CrownpointNM United States Department of Electrical Engineering and Computer Science Florida Atlantic University FL United States

Agriculture plays a major role in eradicating poverty, promoting prosperity, and nourishing a projected 10 billion people by 2050 globally. In a changing climate, achieving optimal agricultural yields requires a deeper understanding of available natural resources and crops. This is especially important for places like the Navajo Nation, which faces significant challenges in food supply chain management due to various factors such as water demand, water quality, and insufficient information about land fertility and crops timings/seasons. Additionally, it is the largest Native American reservation in the U.S. It covers 27,425 square miles across Arizona, Utah, and New Mexico and has a population of 165,158 people, according to the 2020 census. Agriculture has been a key part of life in the Navajo Nation since the late 19th and early 20th centuries, playing a big role in the region’s development and stability. However, the lack of knowledge about decisions and actions during the crop growing season has resulted in lower crop productivity, as evidenced by the USDA statistical report for the Navajo Nation in 2012 and 2017. To support farmers by providing better decision-making and actionable insights, high-resolution, open-source Sentinel-2 satellite images are being used to develop advanced crop mapping techniques for identifying the spatial extent of various agricultural crops in the Navajo Nation. To address this, a collection of research papers was reviewed, leading to the development of a new methodology for analysing Sentinel-2 data from the 2017 and 2023 growing seasons within the Navajo Nation. The collected data was pre-processed by creating monthly median composites of surface reflectance to remove noise and enhance the results more accurately. After preprocessing, spectral indices were calculated from the spectral bands, including NDVI (Normalized Difference Vegetation Index), EVI (Enhanced Vegetation Index), GCVI (Green Chlorophyll Vegetation Index), and LSWI

关键词： Surface waters

来源：评论

学校读者我要写书评

暂无评论

ASDIA: An Adversarial Sample to Preserve Privacy Program in Federated Learning

引用

IEEE Transactions on Dependable and Secure Computing 2025年

作者： Tian, Shujuan Tan, Yi Wang, Han Liu, Haolin Li, Zhetao Xiangtan University School of Computer Science School of Cyberspace Security Xiangtan China Xiangtan University Hunan International Scientific and Technological Cooperation Base of Intelligent network Xiangtan411105 China Xiangtan University Key Laboratory of Hunan Province for Internet of Things and Information Security Xiangtan411105 China Department of Electrical Engineering and Computer Science University of Kansas 1520 W 15th St LawrenceKS United States Jinan University College of Information Science and Technology Guangzhou510632 China

Federated learning enables training across multiple entities while ensuring data security and the effectiveness of knowledge dissemination. Despite its benefits, it remains susceptible to privacy breaches by both external and internal adversaries, who may exploit data or model parameters to glean sensitive participant information or disrupt the training process, thus compromising participant privacy and security. This paper proposes a novel methodology, Adversarial Samples for Defense Inference Attack (ASDIA), aimed at dual protection of data privacy and model robustness within federated learning through adversarial samples and gradient reconstruction. ASDIA includes gradient processing approach before uploading: initially identifying privacy-sensitive gradient, followed by the injection of well-calibrated noise to these gradients. This method not only obfuscates the adversary's classification demarcations but also aids in model performance recovery, all the while maintaining computational efficiency. ASDIA reduces the efficacy of attacks to near-random guessing levels and shows better balance between the model utility and privacy protection compared to the most advanced defense strategies. Additionally, regarding model performance, ASDIA proves its merit across diverse datasets under overfitting and non-overfitting scenarios. © 2004-2012 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Remote State Estimation and Blum–Shub–Smale Machines—A Computability Analysis With Applications to Virtual Twinning

引用

IEEE Transactions on Automatic Control 2025年第5期70卷 3165-3180页

作者： Boche, Holger Bock, Yannik Deppe, Christian Fitzek, Frank H. P. Technical University of Munich Chair of Theoretical Information Technology MunichD-80290 Germany BMBF Research Hub 6G-Life D-80333 Munich Germany MunichD-80799 Germany MunichD-80807 Germany Technische Universität Braunschweig Institute for Communications Technology BraunschweigD-38106 Germany 5G Lab Germany DresdenD-01062 Germany

This article analyzes aspects of the problem of remote state estimation (RSE) via noisy communication channels for their Blum–Shub–Smale (BSS) computability, motivated by an exemplary application to a formal model of virtual twinning subject to stringent integrity requirements. Computability theory provides a unique framework for the formal and mathematically rigorous analysis of algorithms and computing machines. Therefore, computability theory is essential in the domain of safety- and life-critical technology, where the formal verification of automated systems is necessary. Based on the RSE problem, we establish a simple mathematical model of virtual-twin systems that entails a formal notion of integrity (i.e., a state where the virtual entity accurately mirrors its physical counterpart). The model's notion of integrity is related to the question of whether the system under consideration is capable of computing the communication channel's zero-error capacity and corresponding zero-error codes. While this task is known to exceed the theoretical capabilities of Turing computers, we prove its formal feasibility within the model BSS machines. As different authors have proposed BSS machines as potential model of some forms of analog computing, this article serves as a proof-of-concept for a theoretical analog supremacy of unconventional information-processing hardware. Considering recent advances in the development of such hardware, forms of analog supremacy will likely become relevant in the future of cyber-physical systems and information technology. © 1963-2012 IEEE.

关键词： Computability and decidability

来源：评论

学校读者我要写书评

暂无评论

Remote online interactive teaching system design and implementation

Remote online interactive teaching system design and impleme...

引用

2012 international conference on computer science and information processing, csip 2012

作者： Deng, Shaobo Information Engineering NanChang Institute of Technology Jiangxi 330099 China

This paper introduces remote online interactive teaching function demand, and presents a full design proposal of remote online interactive teaching software and the implementing methods of its main function module bas... 详细信息

ISBN: (纸本)9781467314114

关键词： Educational technology

来源：评论

学校读者我要写书评

暂无评论

Design and implementation of a kind of word document plagiarism detection method

Design and implementation of a kind of word document plagiar...

引用

2012 international conference on computer science and information processing, csip 2012

作者： Jian, Feng Department of Computer Science Fuzhou Polytechnic Fujian China

ISBN: (纸本)9781467314114

As more and more the school assignments submitted by the form of electronic documents, there are more and more jobs plagiarism between the students. The authors propose a document-based plagiarism detection algorithm, proceed from the two aspects of the image contrast and text comparison, then effectively detect those similar documents, and then manually to determine whether the existence of plagiarism. This software effictively improves the teacher on the students' work management capabilities. © 2012 IEEE.

关键词： Teaching

来源：评论

学校读者我要写书评

暂无评论

Navigation method in tourist navigation system

Navigation method in tourist navigation system

引用

2012 international conference on computer science and information processing, csip 2012

作者： Liu, Liangfang Yi, Qiaoling Liu, Yanfei Department of Computer Engineering Zhongshan Polytecnic Zhongshan China

ISBN: (纸本)9781467314114

The aim of this project is to investigate the application of shortest path algorithms in GIS (Geographical information System) and design a navigation method for the tourist navigation system based on beacon network. The investigation will focus on Navigation Method Module of the system - how to choose the best route for the tourist according to their different requirements. © 2012 IEEE.

关键词： Navigation systems

来源：评论

学校读者我要写书评

暂无评论

The application of data mining in the classification of spam messages

The application of data mining in the classification of spam...

引用

2012 international conference on computer science and information processing, csip 2012

作者： Liu, Guoxiang Yang, Fengxia Computer Department Cangzhou teachers'College Cangzhou China

ISBN: (纸本)9781467314114

Spam messages in mobile phone flooded and the management to it was not effective. The paper analyzes the characteristics of spam messages, its forming reason and its harm, discusses the classification method of filtering spam messages, and points out it is the key work of the researchers to develop the more effective classification method. © 2012 IEEE.

关键词： Data mining

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：