检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Li, Zezeng Li, ShengHao Wang, Zhanpeng Lei, Na Luo, Zhongxuan Gu, Xianfeng School of Software Dalian University of Technology China Beijing Key Laboratory of Light-field Imaging and Digital Geometry Capital Normal University China School of Mathematical Sciences University of the Chinese Academy of Sciences China Computer Science and Applied Mathematics State University of New York Stony Brook United States

Sampling from diffusion probabilistic models (DPMs) can be viewed as a piecewise distribution transformation, which generally requires hundreds or thousands of steps of the inverse diffusion trajectory to get a high-quality image. Recent progress in designing fast samplers for DPMs achieves a trade-off between sampling speed and sample quality by knowledge distillation or adjusting the variance schedule or the denoising equation. However, it can’t be optimal in both aspects and often suffer from mode mixture in short steps. To tackle this problem, we innovatively regard inverse diffusion as an optimal transport (OT) problem between latents at different stages and propose the DPM-OT, a unified learning framework for fast DPMs with a direct expressway represented by OT map, which can generate high-quality samples within around 10 function evaluations. By calculating the semi-discrete optimal transport map between the data latents and the white noise, we obtain an expressway from the prior distribution to the data distribution, while significantly alleviating the problem of mode mixture. In addition, we give the error bound of the proposed method, which theoretically guarantees the stability of the algorithm. Extensive experiments validate the effectiveness and advantages of DPM-OT in terms of speed and quality (FID and mode mixture), thus representing an efficient solution for generative modeling. Source codes are available at https://***/cognaclee/DPM-OT Copyright © 2023, The Authors. All rights reserved.

关键词： Diffusion

来源：评论

学校读者我要写书评

暂无评论

Research on Target Detection Method Based on Improved YOLOv5 19th

Research on Target Detection Method Based on Improved YOLOv5

引用

19th International Conference on Web Information Systems and Applications, WISA 2022

作者： Wang, Rongzhuang Liu, Jun Zhang, Hualiang School of Computer Science and Technology Shenyang University of Chemical Technology Shenyang110142 China Liaoning Key Laboratory of Intelligent Technology for Chemical Process Industry Shenyang110142 China Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang110016 China Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang110169 China

ISBN: (纸本)9783031203084

At present, various target detection algorithms are used in detection and classification. It is a problem to improve the accuracy and speed of target detection by using deep learning and neural network model to train the parameters of the data set. Aiming at the problems of insufficient detection, inaccurate detection of complex background and loss of small target feature information in yolov5 target detection, an improved method combining hole convolution, moving exponential average and retraining of positive samples is proposed in this paper. This method effectively solves the problems of complex background, occlusion and incomplete feature extraction, reduces the loss rate of target features, and improves the detection accuracy of each category. The improved yolov5 target detection algorithm in this paper can not only use multi feature fusion and accelerate positive sample matching, but also use cavity convolution to increase receptive field, improve the detection effect of small targets and reduce the occurrence of missed detection and false detection. Experiments show that the improved yolov5 algorithm has better detection rate and lower loss rate than many existing target detection algorithms. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Federated Learning While Providing Model as a Service: Joint Training and Inference Optimization

arXiv

引用

arXiv 2023年

作者： Han, Pengchao Wang, Shiqiang Jiao, Yang Huang, Jianwei School of Information Engineering Guangdong University of Technology Guangzhou China IBM T. J. Watson Research Center Yorktown HeightsNY United States Department of Computer Science and Technology Tongji University Shanghai China School of Science and Engineering Shenzhen Institute of Artificial Intelligence and Robotics for Society The Chinese University of Hong Kong Shenzhen Shenzhen China

While providing machine learning model as a service to process users’ inference requests, online applications can periodically upgrade the model utilizing newly collected data. Federated learning (FL) is beneficial for enabling the training of models across distributed clients while keeping the data locally. However, existing work has overlooked the coexistence of model training and inference under clients’ limited resources. This paper focuses on the joint optimization of model training and inference to maximize inference performance at clients. Such an optimization faces several challenges. The first challenge is to characterize the clients’ inference performance when clients may partially participate in FL. To resolve this challenge, we introduce a new notion of age of model (AoM) to quantify client-side model freshness, based on which we use FL’s global model convergence error as an approximate measure of inference performance. The second challenge is the tight coupling among clients’ decisions, including participation probability in FL, model download probability, and service rates. Toward the challenges, we propose an online problem approximation to reduce the problem complexity and optimize the resources to balance the needs of model training and inference. Experimental results demonstrate that the proposed algorithm improves the average inference accuracy by up to 12%. Copyright © 2023, The Authors. All rights reserved.

关键词： Constrained optimization

来源：评论

学校读者我要写书评

暂无评论

Audio-Visual Segmentation with Semantics

arXiv

引用

arXiv 2023年

作者： Zhou, Jinxing Shen, Xuyang Wang, Jianyuan Zhang, Jiayi Sun, Weixuan Zhang, Jing Birchfield, Stan Guo, Dan Kong, Lingpeng Wang, Meng Zhong, Yiran Ministry of Education School of Computer Science and Information Engineering Hefei University of Technology Hefei China The Sensetime Research Shanghai China Visual Geometry Group University of Oxford Oxford United Kingdom School of Computer Science and Engineering The Beihang University Beijing China School of Computing The Australian National University Canberra Australia Nvidia RedmondWA United States The University of Hong Kong Hong Kong Shanghai AI Lab Shanghai China

We propose a new problem called audio-visual segmentation (AVS), in which the goal is to output a pixel-level map of the object(s) that produce sound at the time of the image frame. To facilitate this research, we construct the first audio-visual segmentation benchmark, i.e., AVSBench, providing pixel-wise annotations for sounding objects in audible videos. It contains three subsets: AVSBench-object (Single-source subset, Multi-sources subset) and AVSBench-semantic (Semantic-labels subset). Accordingly, three settings are studied: 1) semi-supervised audio-visual segmentation with a single sound source;2) fully-supervised audio-visual segmentation with multiple sound sources, and 3) fully-supervised audio-visual semantic segmentation. The first two settings need to generate binary masks of sounding objects indicating pixels corresponding to the audio, while the third setting further requires generating semantic maps indicating the object category. To deal with these problems, we propose a new baseline method that uses a temporal pixel-wise audio-visual interaction module to inject audio semantics as guidance for the visual segmentation process. We also design a regularization loss to encourage audio-visual mapping during training. Quantitative and qualitative experiments on AVSBench compare our approach to several existing methods for related tasks, demonstrating that the proposed method is promising for building a bridge between the audio and pixel-wise visual semantics. Code is available at https://***/OpenNLPLab/AVSBench. Online benchmark is available at http://***. Copyright © 2023, The Authors. All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Machine learning methods for estimating down-hole depth of cut

Machine learning methods for estimating down-hole depth of c...

引用

2021 Geothermal Rising Conference: Using the Earth to Save the Earth, GRC 2021

作者： Sacks, Jacob Choi, Kevin Bruss, Kathryn Su, Jiann-Cherng Buerger, Stephen P. Mazumdar, Anirban Boots, Byron Paul G. Allen School of Computer Science and Engineering University of Washington George W. Woodruff School of Mechanical Engineering Georgia Institute of Technology Geothermal Research Group Sandia National Labs Robotics Research and Development Sandia National Labs

ISBN: (纸本)0934412278

Depth of cut (DOC) refers to the depth a bit penetrates into the rock during drilling. This is an important quantity for estimating drilling performance. In general, DOC is determined by dividing the rate of penetration (ROP) by the rotational speed. Surface based sensors at the top of the drill string are used to determine both ROP and rotational speed. However, ROP measurements using top-hole sensors are noisy and often require taking a derivative. Filtering reduces the update rate, and both top-hole linear and angular velocity can be delayed relative to downhole behavior. In this work, we describe recent progress towards estimating ROP and DOC using down-hole sensing. We assume downhole measurements of torque, weight-on-bit (WOB), and rotational speed and anticipate that these measurements are physically realizable. Our hypothesis is that these measurements can provide more rapid and accurate measures of drilling performance. We examine a range of machine learning techniques for estimating ROP and DOC based on this local sensing paradigm. We show how machine learning can provide rapid and accurate performance when evaluated on experimental data taken from Sandia's Hard Rock Drilling Facility. These results have the potential to enable better drilling assessment, improved control, and extended component life-times. Copyright © 2021 Geothermal Rising.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

鞭毛/纤毛内在驱动机制启发的一体式管状机器人驱动器

引用

Engineering 2023年第4期23卷 170-180,M0008页

作者：苗佳麒张铁山李根郭栋孙思琦谭蓉史家海申亚京 Shenzhen Research Institute of City University of Hong Kong Shenzhen 515100China Department of Biomedical Engineering City University of Hong KongHong Kong 999077China Department of Electronic and Computer Engineering Hong Kong University of Science and TechnologyHong Kong 999077China Cheng Kar-Shun Robotics Institute(CKSRI) Hong Kong University of Science and TechnologyHong Kong 999077China Synthetic Biology Translational Research Programmes Yong Loo Lin School of MedicineNational University of SingaporeSingapore 119077Singapore Department of Biochemistry Yong Loo Lin School of MedicineNational University of SingaporeSingapore 119077Singapore

鞭毛和纤毛独特的运动模式(如鞭毛的平面/螺旋波形式推进和纤毛的二维/三维不对称搏动)在众多生物的生命活动中起到至关重要的作用,这也启发了诸多仿生设计,尤其对于微型机器人系统。然而,与自然界中微生物能够从统一化的9+2轴丝生物结... 详细信息

鞭毛和纤毛独特的运动模式(如鞭毛的平面/螺旋波形式推进和纤毛的二维/三维不对称搏动)在众多生物的生命活动中起到至关重要的作用,这也启发了诸多仿生设计,尤其对于微型机器人系统。然而,与自然界中微生物能够从统一化的9+2轴丝生物结构中进化出多种运动模式不同的是,当前的仿生学仍然没有有效的工程策略去实现这样的智慧。在此,我们通过研究鞭毛和纤毛的内部结构及其内在驱动机制,推导出了一个统一的物理模型来描述微管弯曲及其所构建的宏观鞭毛/纤毛运动。基于该模型,我们进而提出了基于三通道的管状驱动概念,并相应地通过杆嵌入铸造工艺制造了一个三通道的管状驱动器。通过编程不同通道的驱动模式,这一管状驱动器不仅可以再现自然界中多样的二维及三维鞭毛/纤毛运动,还可以延展出更多的非对称纤毛搏动模式以实现低雷诺数下的有效推进。该研究加深了我们对微生物推进机制的理解,为仿生系统的设计提供了新灵感,并有望在广泛的工程领域中寻找到重要的应用场景。

关键词： Biomimetic systems Soft actuators 9+2 structure Artificial cilia Low Reynolds number

来源：评论

学校读者我要写书评

暂无评论

Temporally-Extended Prompts Optimization for SAM in Interactive Medical Image Segmentation

arXiv

引用

arXiv 2023年

作者： Shen, Chuyun Li, Wenhao Zhang, Ya Wang, Xiangfeng School of Computer Science and Technology East China Normal University Shanghai200062 China School of Data Science The Chinese University of Hong Kong Shenzhen Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518172 China Cooperative Medianet Innovation Center Shanghai Jiao Tong University Shanghai200240 China

The Segmentation Anything Model (SAM) has recently emerged as a foundation model for addressing image segmentation. Owing to the intrinsic complexity of medical images and the high annotation cost, the medical image segmentation (MIS) community has been encouraged to investigate SAM’s zero-shot capabilities to facilitate automatic annotation. Inspired by the extraordinary accomplishments of interactive medical image segmentation (IMIS) paradigm, this paper focuses on assessing the potential of SAM’s zero-shot capabilities within the IMIS paradigm to amplify its benefits in the MIS domain. Regrettably, we observe that SAM’s vulnerability to prompt forms (e.g., points, bounding boxes) becomes notably pronounced in IMIS. This leads us to develop a framework that adaptively offers suitable prompt forms for human experts. We refer to the framework above as temporally-extended prompts optimization (TEPO) and model it as a Markov decision process, solvable through reinforcement learning. Numerical experiments on the standardized benchmark BraTS2020 demonstrate that the learned TEPO agent can further enhance SAM’s zero-shot capability in the MIS context. Copyright © 2023, The Authors. All rights reserved.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

An Overview on Economic Analysis of Internet of Everything

引用

IEEE Communications Surveys and Tutorials 2025年

作者： Ding, Ningning Ouyang, Xiaomin Gao, Lin Huang, Jianwei Xing, Guoliang Guangzhou511453 China Hong Kong University of Science and Technology Department of Computer Science and Engineering 999077 Hong Kong Harbin Institute of Technology School of Electronics and Information Engineering Guangdong Provincial Key Laboratory of Aerospace Communication and Networking Technology Shenzhen China Chinese University of Hong Kong School of Science and Engineering Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen Key Laboratory of Crowd Intelligence Empowered Low-Carbon Energy Network CSIJRI Joint Research Centre on Smart Energy Storage Guangdong Shenzhen518172 China The Chinese University of Hong Kong Department of Information Engineering 999077 Hong Kong

The Internet of Everything (IoE) integrates people, processes, data, and things into a unified network, enabling highly interconnected systems with enhanced performance in terms of delay, reliability, and connection density. With the advent of next-generation networks, IoE has garnered significant attention for its transformative potential across various domains. However, while most existing studies focus on developing enabling technologies and deployment frameworks, the economic dimensions of IoE systems remain critically underexplored, despite being essential for ensuring their sustainability and scalability. This paper addresses this gap by providing a comprehensive review of the economic analysis of IoE systems. Specifically, we categorize existing research into four key aspects: information collection, information transmission, information fusion, and service application. We identify major economic challenges and propose modeling approaches, including game-theoretic and learning-based methods. Furthermore, we explore diverse IoE application scenarios, such as metaverse solutions and large-scale industrial systems, and summarize prevailing business patterns in the industry. By highlighting the economic dimension as a core component of IoE systems, this survey offers valuable insights into future research directions and outlines critical open challenges. © 1998-2012 IEEE.

关键词： Internet of Everything

来源：评论

学校读者我要写书评

暂无评论

Generative AI Powered Forensic Device

Generative AI Powered Forensic Device

引用

International Conference on Computing Communication Control and Automation (ICCUBEA)

作者： Vanita G. Kshirsagar Digvijay G. Bhosale Shubhangi Suryawanshi Anita Sachin Mahajan Pramod Patil Jyotsna Vilas Barpute Prashant G. Ahire Rahul A. Patil Automation and Robotics Dr. D. Y. Patil Institute of Technology Pune India Artificial Intelligence and Data Secience Dr. D. Y. Patil Institute of Technology Pune Artificial Intelligence and Data Science Dr. D. Y. Patil Institute of Technology Pune India Computer Engineering Ajeenkya D. Y. Patil School of Engineering Pune India Computer Engineering Dr. D.Y. Patil Institute of Technology Pune India Computer Science and Engineering Symbiosis Institute of Technology Pune India Computer Engineering Pimpri Chinchwad College of Engineering Pune

ISBN: (数字)9798350391770

ISBN: (纸本)9798350391787

Crime is a dominant concern in contemporary society. It is crucial to prevent it and deliver justice promptly. Forensic science is critical for criminal investigations and maintaining law and order. The traditional tactics utilized in this field are frequently based on manual procedures, which are both time-consuming and prone to error, rendering them ineffectual in providing prompt and dependable justice. Utilizing automation and advanced technologies for forensic science and crime scene investigation is now essential. This paper suggests a portable gadget that utilizes Internet of Things (IOT), Machine Learning and Deep Learning to predict, gain understanding, and possibly recognize offenders. This gadget is designed to reconstruct fingerprints, detect weapons and recognize suspicious activities. It utilizes algorithms and technologies like autoencoders, GANs, SSD and YOLOv8. We talk about the benefits of merging these technologies into one easy-to-use device, which will offer data integration, instant data processing, and improved forensic analysis. The article offers information about automating important areas to improve investigative processes and enhance the criminal justice system's efficiency and effectiveness in the future.

关键词： Cloud computing Automation Forensics Weapons Prevention and mitigation Fingerprint recognition Internet of Things Image reconstruction Testing Videos

来源：评论

学校读者我要写书评

暂无评论

You Can Wash Hands Better: Accurate Daily Handwashing Assessment with a Smartwatch

引用

IEEE Transactions on Mobile Computing 2025年

作者： Wang, Fei Zhang, Tingting Wu, Xilei Wang, Pengcheng Wang, Xin Ding, Han Shi, Jingang Han, Jinsong Huang, Dong Xi'an Jiaotong University School of Software Engineering Xi'an 710049 China Xidian University State Key Laboratory of Integrated Services Networks Xi'an 710071 China Kuaishou Technology Inc. Local Life Research and Development Center Beijing 100085 China Xi'an Jiaotong University School of Computer Science and Technology Xi'an 710049 China Zhejiang University College of Computer Science and Technology Hangzhou 310027 China Carnegie Mellon University Robotics Institute Pittsburgh 15213 United States

Hand hygiene is among the most effective daily practices for preventing infectious diseases such as influenza, malaria, and skin infections. While professional guidelines emphasize proper handwashing to reduce the risk of viral infections, surveys reveal that adherence to these recommendations remains low. To address this gap, we propose UWash, a wearable solution leveraging smartwatches to evaluate handwashing procedures, aiming to raise awareness and cultivate high-quality handwashing habits. We frame the task of handwashing assessment as an action segmentation problem, similar to those in computer vision, and introduce a simple yet efficient two-stream UNet-like network to achieve this goal. Experiments involving 51 subjects demonstrate that UWash achieves 92.27% accuracy in handwashing gesture recognition, an error of < 0.5 seconds in onset/offset detection, and an error of < 5 points in gesture scoring under user-dependent settings. The system also performs robustly in user-independent and user-independent-location-independent evaluations. Remarkably, UWash maintains high performance in real-world tests, including evaluations with 10 random passersby at a hospital 9 months later and 10 passersby in an in-the-wild test conducted 2 years later. UWash is the first system to score handwashing quality based on gesture sequences, offering actionable guidance for improving daily hand hygiene. © 2002-2012 IEEE.

关键词： deep neural network gesture recognition handwashing assessment smartwatch

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：