检索结果-内蒙古大学图书馆

UncTrack: Reliable Visual Object Tracking With Uncertainty-Aware Prototype Memory Network

IEEE Transactions on Image Processing 2025年 34卷 3533-3546页

作者： Siyuan Yao Yang Guo Yanyang Yan Wenqi Ren Xiaochun Cao School of Computer Science (National Pilot Software Engineering School) Beijing University of Posts and Telecommunications Beijing China State Key Laboratory of Processors Institute of Computing Technology Chinese Academy of Sciences Beijing China School of Cyber Science and Technology Sun Yat-sen University Shenzhen Campus Shenzhen China

Transformer-based trackers have achieved promising success and become the dominant tracking paradigm because of their accuracy and efficiency. Despite the substantial progress, most of the existing approaches handle object tracking as a deterministic coordinate regression problem, while the target localization uncertainty has been largely overlooked, which hampers trackers’ ability to maintain reliable target state prediction in challenging scenarios. To address this issue, we propose UncTrack, a novel uncertainty-aware transformer-based tracker that predicts the target localization uncertainty and incorporates this uncertainty information for accurate target state inference. Specifically, UncTrack uses a transformer encoder to perform feature interactions between the template and search images. The output features are passed into an uncertainty-aware localization decoder (ULD) to coarsely predict the corner-based localization and the corresponding localization uncertainty. Then, the localization uncertainty is sent into a prototype memory network (PMN) to excavate valuable historical information to identify whether the target state prediction is reliable. To enhance the template representation, the samples with high confidence are fed back into the prototype memory bank for memory updating, which makes the tracker more robust to challenging appearance variations. Extensive experiments demonstrate that our method outperforms the state-of-the-art methods. Our code is available at https://***/ManOfStory/UncTrack

关键词： Uncertainty Location awareness Target tracking Transformers Reliability Prototypes Object tracking Visualization Accuracy Training

来源：评论

学校读者我要写书评

暂无评论

Enhancement of IoT based Flood Detection and Prevention using Arduino UNO with WiFi Module 9

Enhancement of IoT based Flood Detection and Prevention usin...

引用

9th International Conference on Advanced computing and Communication Systems, ICACCS 2023

作者： Charaan, R. M. Dilip Shobana, J. Krishnamoorthy, P. Princy, B. Anni Abinaya, R.J. Murugesan, K. Vel Tech Rangarajan Dr Sagunthala R&D Institute of Science and Technology Department of Computer Science and Engineering Tamil Nadu India SRM Institute of Science and Technology School of Computing Department of Data Science and Business Systems Tamil Nadu Kattankulathur India Siddharth Institute of Engineering & Technology Department of Computer Science and Engineering Tamil Nadu India Panimalar Engineering College Department of Computer and Communication Engineering Tamil Nadu India Karpagam Academy of Higher Education Department of Electronics and Communication Engineering Tamil Nadu India Loyola Institute of Technology Department of Electronics and Communication Engineering Tamil Nadu India

ISBN: (纸本)9798350397376

The overflow of water from a lake or river usually causes flooding. Sometimes, a dam breach might result in the unexpected release of vast quantities of water. Some of the water seeps into the ground, flooding the region. In a station, rivers are involving the riverbanks. Along with a lack of goods and houses, businesses, and offices, street infrastructure floods contain bacteria, sewage from waste sites, and chemical spills, which later cause a number of diseases. The rate of change in river stage in real time, which can assist signal the gravity and immediacy of this hazard, is a crucial piece of information for flood predictions. Understanding the type of storm that produced the moisture, including its duration, strength, and actual extent, is important for determining the possible severity of the flood. In this system, an Arduino Uno is connected to four separate sensors: a humidity sensor, a flow sensor, a float sensor, and an ultrasonic sensor. The float sensor detects when the water is full. With the aid of IOT, these sensor combinations are utilised to predict floods, alert the appropriate authorities, and sound an immediate alarm in adjacent communities to rapidly relay information about potential floods. These sensors provide data via the IOT's WiFi module. When flooding conditions are detected, the system warns the nearby villages and places and estimates how long it would take for help to reach at a particular location. The technology also determines when it might be considered a flood and gives them a window of time to leave in case it does. © 2023 IEEE.

关键词： Floods

来源：评论

学校读者我要写书评

暂无评论

Comparison Between Rectangular and Circular Microstrip Patch Antenna Arrays 2

Comparison Between Rectangular and Circular Microstrip Patch...

引用

2nd International engineering Conference on Electrical, Energy, and Artificial Intelligence, EICEEAI 2023

作者： Samir, Ahmed Ismail, Taisir Attar, Hani Solyman, Ahmed Hafez, Mohamed Agieb, Ramy Said Mti Unversity Faculty of Engineering Department of Electrical Engineering Cairo Egypt Zarqa University Department of Electrical Engineering Zarqa Jordan Zarqa University Faculty of Engineering Zarqa Jordan College of Engineering University of Business and Technology Jeddah21448 Saudi Arabia School of Computing Engineering and Built Environment Glasgow Caledonian University Glasgow United Kingdom INTI-IU-University Faculty of Engineering Feqs Nilai Malaysia

ISBN: (纸本)9798350373363

In this paper, several designs of microstrip array antennas suitable for wireless communication applications are presented. This paper demonstrates several shapes of microstrip array antennas, such as rectangular and circular patch antenna arrays. Specifically, single, 2 × 1, and 4 × 1 elements of both shapes are designed and simulated by High Frequency Structural Simulator (HFSS). Moreover, this paper presents a comparison between both rectangular and triangular antenna arrays. Since the resonance frequency of these antennas is 2.4 GHz, these antennas are suitable for the ISM band and WLAN). © 2023 IEEE.

关键词： Microstrip antennas

来源：评论

学校读者我要写书评

暂无评论

Distance-Only Task Orchestration Algorithm for Energy Efficiency in Satellite-Based Mist computing

Distance-Only Task Orchestration Algorithm for Energy Effici...

引用

International Conference on Image and Signal Processing and their Applications (ISPA)

作者： Messaoud Babaghayou Noureddine Chaib Leandros Maglaras Yagmur Yigit Mohamed Amine Ferrag LIM Laboratory Laghouat University Laghouat Algeria School of Computing Engineering and The Built Environment Edinburgh Napier University United Kingdom School of Computing Engineering and The Built Environment Edinburgh Napier University Technology Innovation Institute (TII) Abu Dhabi United Arab Emirates

ISBN: (数字)9798350309249

ISBN: (纸本)9798350309256

This paper addresses the challenge of efficiently offloading heavy computing tasks from ground mobile devices to the satellite-based mist computing environment. With ground-based edge and cloud servers often being inaccessible, the exploitation of satellite mist computing becomes imperative. Existing offloading algorithms have shown limitations in adapting to the unique characteristics of heavy computing tasks. Thus, we propose a heavy computing task offloading algorithm that prioritizes satellite proximity. This approach not only reduces energy consumption during telecommunications but also ensures tasks are executed within the specified timing constraints, which are typically non-time-critical. Our proposed algorithm outperforms other offloading schemes in terms of satellites energy consumption, average end-to-end delay, and tasks success rates. Although it exhibits a higher average VM CPU usage, this increase does not pose critical challenges. This distance-based approach offers a promising solution to enhance energy efficiency in satellite-based mist computing, making it well-suited for heavy computing tasks demands.

关键词： Energy consumption Satellites Signal processing algorithms Signal processing Energy efficiency Mobile handsets Telecommunications

来源：评论

学校读者我要写书评

暂无评论

*** - An Automated Parasitic Egg Detection Model from Microscopic Images of Fecal Smears using Deep Learning Techniques 2

*** - An Automated Parasitic Egg Detection Model from Micros...

引用

2nd IEEE International Conference on Advances in computing, Communication and Applied Informatics, ACCAI 2023

作者： Jaya Sundar Rajasekar, Sakthi Jaswal, Gaurav Perumal, Varalakshmi Ravi, Sasana Dutt, Varun Melmaruvathur Adhiparasakthi Institute of Medical Sciences and Research Melmaruvathur India Indian Institute of Technology IHub & Hci Foundation Himachal Pradesh Mandi India Anna University Madras Institute of Technology Campus Chennai India Iit Mandi School of Computing and Electrical Engineering Himachal Pradesh India

ISBN: (纸本)9798350315905

Intestinal parasitic infestations are one of the leading reasons of morbidity worldwide and has been recognized as one of the most significant causes of diseases by World Health Organization (WHO). The mainstay of diagnosis is through direct manual examination of fecal smears using microscope in the laboratory. However, there are several shortcomings in the manual parasite egg detection like its time-consuming nature, low sensitivity and mandatory requirement of skilled technicians. Utilization of Artificial Intelligence in automation of the laboratory identification of parasite eggs has been proposed in this work. Various Deep Learning models like Yolov8, Detectron2, Inception v3 and YOLOs have been utilized for parasite egg detection task and their performance has been evaluated. Our results indicate that YOLOv8 with SGD optimizer has yielded superior performance, mAP of 0.92 and F1-score of 98%, compared to the other models evaluated and the existing literature. Its high accuracy and fast convergence make it an ideal choice for the parasitic egg detection tasks. © 2023 IEEE.

关键词： Automation

来源：评论

学校读者我要写书评

暂无评论

Currency Recognition Using EAST for Text Detection and Tesseract OCR for Text Recognition 2

Currency Recognition Using EAST for Text Detection and Tesse...

引用

2nd International engineering Conference on Electrical, Energy, and Artificial Intelligence, EICEEAI 2023

作者： Abass, Eman S. Mohamed, Abd-Elnaser Fawzy Amer, Ayman Hafez, Mohamed Solyman, Ahmed Fawzy, Mohamed Mti University Faculty of Engineering Department of Electrical Engineering Cairo Egypt Bilbeis Higher Institute for Engineering Communication Department Sharqia Egypt Zarqa University Faculty of Engineering Zarqa Jordan College of Engineering University of Business and Technology Jeddah21448 Saudi Arabia INTI-IU-University Faculty of Engineering Feqs Nilai Malaysia School of Computing Engineering and Built Environment Glasgow Caledonian University Glasgow United Kingdom

ISBN: (纸本)9798350373363

This research study presents a novel approach for detecting currency utilizing cutting-edge technologies such as the Efficient and Accurate Scene Text (EAST) model and Tesseract Optical Character Recognition (OCR). The EAST model is employed to identify text within scenes, whereas Tesseract OCR is utilized to effectively recognize and classify monetary units in real-time video stream input. The empirical results demonstrate the efficacy of the suggested methodology in discerning and classifying distinct monetary units, a pivotal necessity in diverse financial scenarios. The amalgamation of the EAST model with OCR can augment money identification technology, strengthening the dependability of financial services such as ATM operation and currency conversion and ultimately elevating consumer happiness during financial transactions. © 2023 IEEE.

关键词： Optical character recognition

来源：评论

学校读者我要写书评

暂无评论

DISCOVERING LATENT CONCEPTS LEARNED IN BERT 10

DISCOVERING LATENT CONCEPTS LEARNED IN BERT

引用

10th International Conference on Learning Representations, ICLR 2022

作者： Dalvi, Fahim Khan, Abdul Rafae Alam, Firoj Durrani, Nadir Xu, Jia Sajjad, Hassan Qatar Computing Research Institute HBKU Research Complex Doha5825 Qatar School of Engineering and Science Steven Institute of Technology HobokenNJ07030 United States

A large number of studies that analyze deep neural network models and their ability to encode various linguistic and non-linguistic concepts provide an interpretation of the inner mechanics of these models. The scope of the analyses is limited to pre-defined concepts that reinforce the traditional linguistic knowledge and do not reflect on how novel concepts are learned by the model. We address this limitation by discovering and analyzing latent concepts learned in neural network models in an unsupervised fashion and provide interpretations from the model's perspective. In this work, we study: i) what latent concepts exist in the pre-trained BERT model, ii) how the discovered latent concepts align or diverge from classical linguistic hierarchy and iii) how the latent concepts evolve across layers. Our findings show: i) a model learns novel concepts (e.g. animal categories and demographic groups), which do not strictly adhere to any pre-defined categorization (e.g. POS, semantic tags), ii) several latent concepts are based on multiple properties which may include semantics, syntax, and morphology, iii) the lower layers in the model dominate in learning shallow lexical concepts while the higher layers learn semantic relations and iv) the discovered latent concepts highlight potential biases learned in the model. We also release a novel BERT ConceptNet dataset (BCN) consisting of 174 concept labels and 1M annotated instances. © 2022 ICLR 2022 - 10th International Conference on Learning Representationss. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Hybrid CNN and Random Forest Model with Late Fusion for Detection of Autism Spectrum Disorder in Toddlers

SSRN

引用

SSRN 2025年

作者： Nawghare, Pushpmala Sampatrao Prasad, Jayashree Department of Computer Science and Engineering MIT School of Computing MIT Art Design and Technology University Maharashtra Pune412201 India Sinhgad College of Engineering Vadgaon Pune India

Accurate and early diagnosis of Autism Spectrum Disorder (ASD) in toddlers is crucial for effective intervention. Traditional models like Support Vector Machines (SVM), Logistic Regression (LR), and Random Forest (RF) have shown limited success, with accuracies around 65%, while deep learning approaches such as transfer learning with Convolutional Neural Networks (CNNs) achieve higher accuracies, ranging from 75% to 85%. Building on this progress, our study proposes a hybrid model combining VGG16, a pre-trained deep CNN, with an RF classifier to leverage high-level image feature extraction using the ACD image dataset on Kaggle alongside robust decision-making on the ACD Questionnaire dataset. The proposed model achieves an accuracy of 88.34%, outperforming both standalone deep learning models like VGG16, EfficientNetB0, and AlexNet-based models as well as conventional ML models. This improvement demonstrates the effectiveness of combining feature-rich deep learning outputs with RF's ensemble-based classification. Our findings suggest that this hybrid approach is highly suitable for ASD classification tasks, enhancing the reliability of predictions in clinical settings. This research not only establishes the model as an option for ASD diagnosis but also underscores the potential of hybrid architectures that fuse deep learning with machine learning. © 2025, The Authors. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Comparative Study of Circular and Rectangular Microstrip Patch antennas in Wi-Fi Band 2

Comparative Study of Circular and Rectangular Microstrip Pat...

引用

2nd International engineering Conference on Electrical, Energy, and Artificial Intelligence, EICEEAI 2023

作者： Ahmed, Samir Ismail, Taisir Attar, Hani Hafez, Mohamed Solyman, Ahmed Agieb, Ramy Said Mti University Faculty of Engineering Department of Electrical Engineering Cairo Egypt Zarqa University Department of Electrical Engineering Zarqa Jordan Zarqa University Faculty of Engineering Zarqa Jordan College of Engineering University of Business and Technology Jeddah21448 Saudi Arabia INTI-IU-University Faculty of Engineering Feqs Nilai Malaysia School of Computing Engineering and Built Environment Glasgow Caledonian University Glasgow United Kingdom

ISBN: (纸本)9798350373363

The growing ubiquity of Wi-Fi has necessitated the development of small and effective antenna designs, especially microstrip patch antennas. In the Wi-Fi frequency range of 2.4 GHz to 2.4835 GHz, this paper compares the performance of circular and rectangular microstrip patch antennas. The study aims to evaluate their performance regarding radiation characteristics, gain, and bandwidth to help choose antennas for Wi-Fi applications. According to the results, the rectangular patch antenna with a rectangular slot outperforms the circular patch antenna with a rectangular slot regarding return loss, coming in at roughly -37.07 dB. Furthermore, the Voltage Standing Wave Ratio (VSWR)value of the rectangular patch antenna is 1.02, which is higher than that of the circular patch antenna, which is 1.34. The rectangular patch antenna has the most excellent radiation efficiency (64.5%) and offers the broadest bandwidth (about 115 MHz). Engineers and researchers looking to enhance antenna designs for Wi-Fi applications can learn much from this study by considering variables like radiation efficiency, bandwidth, VSWR, and return loss. © 2023 IEEE.

关键词： Microstrip antennas

来源：评论

学校读者我要写书评

暂无评论

Natural Language as Policies: Reasoning for Coordinate-Level Embodied Control with LLMs

arXiv

引用

arXiv 2024年

作者： Mikami, Yusuke Melnik, Andrew Miura, Jun Hautamäki, Ville Department of Computer Science and Engineering Toyohashi University of Technology Japan School of Computing University of Eastern Finland Finland Bielefeld University Germany

We demonstrate experimental results with LLMs that address robotics task planning problems. Recently, LLMs have been applied in robotics task planning, particularly using a code generation approach that converts complex high-level instructions into mid-level policy codes. In contrast, our approach acquires text descriptions of the task and scene objects, then formulates task planning through natural language reasoning, and outputs coordinate level control commands, thus reducing the necessity for intermediate representation code as policies with pre-defined APIs. Our approach is evaluated on a multimodal prompt simulation benchmark, demonstrating that our prompt engineering experiments with natural language reasoning significantly enhance success rates compared to its absence. Furthermore, our approach illustrates the potential for natural language descriptions to transfer robotics skills from known tasks to previously unseen tasks. The project website: https://*** © 2024, CC BY.

关键词： Robot programming

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：