检索结果-内蒙古大学图书馆

32nd International Joint Conference on Artificial Intelligence, IJCAI 2023

作者： Zhou, Xingchen He, Ying Richard Yu, F. Li, Jianqiang Li, You College of Computer Science and Software Engineering Shenzhen University China China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China

ISBN: (纸本)9781956792034

The emergence of Neural Radiance Fields (NeRF) has promoted the development of synthesized high-fidelity views of the intricate real world. However, it is still a very demanding task to repaint the content in NeRF. In this paper, we propose a novel framework that can take RGB images as input and alter the 3D content in neural scenes. Our work leverages existing diffusion models to guide changes in the designated 3D content. Specifically, we semantically select the target object and a pre-trained diffusion model will guide the NeRF model to generate new 3D objects, which can improve the editability, diversity, and application range of NeRF. Experiment results show that our algorithm is effective for editing 3D objects in NeRF under different text prompts, including editing appearance, shape, and more. We validate our method on both real-world datasets and synthetic-world datasets for these editing tasks. Please visit https://*** for a better view of our results. © 2023 International Joint Conferences on Artificial Intelligence. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Focus on Local: Finding Reliable Discriminative Regions for Visual Place Recognition 39

Focus on Local: Finding Reliable Discriminative Regions for ...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Wang, Changwei Chen, Shunpeng Song, Yukun Xu, Rongtao Zhang, Zherui Zhang, Jiguang Yang, Haoran Zhang, Yu Fu, Kexue Du, Shide Xu, Zhiwei Gao, Longxiang Guo, Li Xu, Shibiao China School of Artificial Intelligence Beijing University of Posts and Telecommunications China Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Shandong Fundamental Research Center for Computer Science China MAIS Institute of Automation Chinese Academy of Sciences China Tongji University China College of Computer and Data Science Fuzhou University China Shandong University China

ISBN: (纸本)157735897X

Visual Place Recognition (VPR) is aimed at predicting the location of a query image by referencing a database of geotagged images. For VPR task, often fewer discriminative local regions in an image produce important effects while mundane background regions do not contribute or even cause perceptual aliasing because of easy overlap. However, existing methods lack precisely modeling and full exploitation of these discriminative regions. In this paper, we propose the Focus on Local (FoL) approach to stimulate the performance of image retrieval and re-ranking in VPR simultaneously by mining and exploiting reliable discriminative local regions in images and introducing pseudo-correlation supervision. First, we design two losses, Extraction-Aggregation Spatial Alignment Loss (SAL) and Foreground-Background Contrast Enhancement Loss (CEL), to explicitly model reliable discriminative local regions and use them to guide the generation of global representations and efficient re-ranking. Second, we introduce a weakly-supervised local feature training strategy based on pseudo-correspondences obtained from aggregating global features to alleviate the lack of local correspondences ground truth for the VPR task. Third, we suggest an efficient re-ranking pipeline that is efficiently and precisely based on discriminative region guidance. Finally, experimental results show that our FoL achieves the state-of-the-art on multiple VPR benchmarks in both image retrieval and re-ranking stages and also significantly outperforms existing two-stage VPR methods in terms of computational efficiency. 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

Augmenting the Proficiencies of GANs Through Modernizing Agriculture and Healthcare

Augmenting the Proficiencies of GANs Through Modernizing Agr...

引用

International Conference on Trends in Electronics and Informatics (ICEI)

作者： M. Jothi T. Veeramakali Department of Data Science and Business Systems School of Computing SRM Institute of Science and Technology Kattankulathur Tamilnadu India

ISBN: (数字)9798331544607

ISBN: (纸本)9798331544614

Nowadays, generative models with deep learning have a focus and give enormous success in various real-time experience domains. Deep learning (DL) is a subdivision of machine learning that is inspired by the structure and function of human brain activity, known as artificial neural networks. It is a data-driven technique that achieves the best accuracy while using a large number of input samples. Generative Adversarial Networks (GANs) are a robust class of neural networks used for unsupervised learning under DL categories. GAN is one of the most influential architectures demonstrating remarkable success in generating high-quality data. The reusable feature learning process from a huge number of unlabelled data paves the way for research. This survey article discusses an overview of the GAN model, such as the original GAN, Conditional GANs, and resolution GANs, along with their specific adaptations for various tasks. Additionally, we examine the situations faced by Generative Adversarial Networks depending on various applications such as image and video generation, medical image analysis, text-to-image synthesis, agriculture, and creative industries such as music and art. This survey explores diverse applications of recently developed frameworks and benchmark datasets used for development, along with their architecture and metric evaluations.

关键词： Deep learning Surveys Measurement Image analysis Accuracy Generative adversarial networks Agriculture Real-time systems Medical diagnostic imaging Farming

来源：评论

学校读者我要写书评

暂无评论

Integrated Simulation Research of Multi-natural Energy-driven Unmanned Surface Vehicle

Integrated Simulation Research of Multi-natural Energy-drive...

引用

2023 International Conference on Applied Mathematics and Digital Simulation, AMDS 2023

作者： Chen, Ao Chen, Tianding He, Hong Wang, Hui Fan, Yimei Yu, Xin School of Physics and Information Engineering Minnan Normal University Fujian Province China School of Computing and Information Science Fuzhou Institute of Technology Fujian Province China School of Data and Computer Science Xiamen Institute of Technology Fujian Province China

In response to the limitations of existing unmanned surface vehicles in complex marine environments, where they often fail to meet the requirements for extended endurance, broad operational range, offshore missions, and prolonged operational durations, an autonomous Unmanned Surface Vehicle (NUSV) has been designed and developed. The NUSV is propelled by wind, solar, and wave energy sources. Concerning wind energy, a micro wind energy storage mechanism based on a spiral spring has been designed to enable power generation in low-wind conditions. A wave energy transmission device, complete with a dynamic model, has been devised for wave energy. This device converts torque generated from wave action in different directions into a unified torque, providing continuous power to drive the generator. Solar energy is harnessed using Maximum Power Point Tracking (MPPT) algorithms to ensure optimal operation of the solar panels. The electrical energy generated from these three natural sources is stored using Pulse Width Modulation (PWM) and DC-DC Boost converters. A programmable logic controller manages and allocates this stored electrical energy for the NUSV's equipment, including underwater propulsion systems, surface cameras, laser radar, GPS, and other electronic devices. This integration of wind, solar, and wave energy sources enables the NUSV to meet power demands, allowing for long-duration operations at sea, extended offshore missions, wide operational ranges, and prolonged mission durations. © Published under licence by IOP Publishing Ltd.

关键词： DC-DC converters

来源：评论

学校读者我要写书评

暂无评论

Matching Knowledge Graphs in Entity Embedding Spaces: An Experimental Study [Extended Abstract] 40

Matching Knowledge Graphs in Entity Embedding Spaces: An Exp...

引用

40th IEEE International Conference on data Engineering, ICDE 2024

作者： Zeng, Weixin Zhao, Xiang Tan, Zhen Tang, Jiuyang Cheng, Xueqi National University of Defense Technology Laboratory for Big Data and Decision China National University of Defense Technology Science and Technology on Information Systems Engineering Laboratory China Institute of Computing Technology CAS China

ISBN: (纸本)9798350317152

Entity alignment (EA) identifies equivalent entities that locate in different knowledge graphs (KGs), and has attracted growing research interests over the last few years with the advancement of KG embedding techniques. Although a pile of embedding-based EA frameworks have been developed, they mainly focus on improving the performance of entity representation learning, while largely overlook the subsequent stage that matches KGs in entity embedding spaces. Nevertheless, accurately matching entities based on learned entity representations is crucial to the overall alignment performance, as it coordinates individual alignment decisions and determines the global matching result. Hence, it is essential to understand how well existing solutions for matching KGs in entity embedding spaces perform on present benchmarks, as well as their strengths and weaknesses. To this end, in this article we provide a comprehensive survey and evaluation of matching algorithms for KGs in entity embedding spaces in terms of effectiveness and efficiency on both classic settings and new scenarios that better mirror real-life challenges. Based on in-depth analysis, we provide useful insights into the design trade-offs and good paradigms of existing works, and suggest promising directions for future development. © 2024 IEEE.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

OOP: Object-Oriented Programming Evaluation Benchmark for Large Language Models 62

OOP: Object-Oriented Programming Evaluation Benchmark for La...

引用

Findings of the 62nd Annual Meeting of the Association for Computational Linguistics, ACL 2024

作者： Wang, Shuai Ding, Liang Shen, Li Luo, Yong Du, Bo Tao, Dacheng Institute of Artificial Intelligence School of Computer Science Wuhan University China Hubei Luojia Laboratory Wuhan China The University of Sydney Australia School of Cyber Science and Teachnology Sun Yat-sen University China College of Computing & Data Science Nanyang Technology University Singapore

ISBN: (纸本)9798891760998

Advancing automated programming necessitates robust and comprehensive code generation benchmarks, yet current evaluation frameworks largely neglect object-oriented programming (OOP) in favour of functional programming (FP), e.g., HumanEval and MBPP. To address this, (1) our study introduces a pioneering OOP-focused benchmark, featuring 431 Python programs that encompass essential OOP concepts and features like classes and encapsulation methods. (2) We propose a novel evaluation metric, pass@o, tailored for OOP, enhancing traditional pass@k metric. (3) Our evaluation of 23 leading large language models (LLMs), including both general and code-specialized models, reveals three key insights: 1) pass@o offers a more relevant and comprehensive assessment for OOP code generation;2) Despite excelling in FP, code-specialized LLMs like WizardCoder lag in OOP compared to models like ChatGPT;3) The poor performance of all advanced LLMs on our OOP benchmark highlights a critical need for improvements in this field. Our benchmark and scripts are publicly released at: https://***/alphadl/OOP-eval. © 2024 Association for Computational Linguistics.

关键词： Object oriented programming

来源：评论

学校读者我要写书评

暂无评论

SoVAR: Build Generalizable Scenarios from Accident Reports for Autonomous Driving Testing 24

SoVAR: Build Generalizable Scenarios from Accident Reports f...

引用

39th ACM/IEEE International Conference on Automated Software Engineering, ASE 2024

作者： Guo, An Zhou, Yuan Tian, Haoxiang Fang, Chunrong Sun, Yunjian Sun, Weisong Gao, Xinyu Luu, Anh Tuan Liu, Yang Chen, Zhenyu State Key Laboratory for Novel Software Technology Nanjing University Nanjing210023 China School of Computer Science and Technology Zhejiang Sci-Tech University Hangzhou310018 China College of Computing and Data Science Nanyang Technological University Singapore

ISBN: (纸本)9798400712487

Autonomous driving systems (ADSs) have undergone remarkable development and are increasingly employed in safety-critical applications. However, recently reported data on fatal accidents involving ADSs suggests that the desired level of safety has not yet been fully achieved. Consequently, there is a growing need for more comprehensive and targeted testing approaches to ensure safe driving. Scenarios from real-world accident reports provide valuable resources for ADS testing, including critical scenarios and high-quality seeds. However, existing scenario reconstruction methods from accident reports often exhibit limited accuracy in information extraction. Moreover, due to the diversity and complexity of road environments, matching current accident information with the simulation map data for reconstruction poses significant *** this paper, we design and implement SoVAR, a tool for automatically generating road-generalizable scenarios from accident reports. SoVAR utilizes well-designed prompts with linguistic patterns to guide the large language model (LLM) in extracting accident information from textual data. Subsequently, it formulates and solves accident-related constraints in conjunction with the extracted accident information to generate accident trajectories. Finally, SoVAR reconstructs accident scenarios on various map structures and converts them into test scenarios to evaluate its capability to detect defects in industrial ADSs. We experiment with SoVAR, using the accident reports from the National Highway Traffic Safety Administration's (NHTSA) database to generate test scenarios for the industrial-grade ADS Apollo. The experimental findings demonstrate that SoVAR can effectively generate generalized accident scenarios across different road structures. Furthermore, the results confirm that SoVAR identified 5 distinct safety violation types that contributed to the crash of Baidu Apollo. © 2024 Copyright is held by the owner/author(s). Publication ri

关键词： Highway administration

来源：评论

学校读者我要写书评

暂无评论

Part-Based Convolutional Neural Network and Dual Interactive Wasserstein Generative Adversarial Networks for Land Mark Detection and Localization of Autonomous Robots in Outdoor Environment Note: Sub-titles are not captured in Xplore and should not be used 1

Part-Based Convolutional Neural Network and Dual Interactive...

引用

1st International Conference on Computational science and Technology, ICCST 2022

作者： Sindhu, S. Saravanan, M. Srm Institute of Science and Technology Faculty of School of Computing Department of Data Science and Business Systems Kattankulathur India Srm Institute of Science and Technology Faculty of School of Computing Department of Networking and Communications Kattankulathur India

ISBN: (纸本)9781665476553

Robot localization is a fundamental competency required by an autonomous robot because the robot's location knowledge is an essential precursor to making decisions about future actions. Accurate localization of robots or autonomous vehicles is the most important requirement for autonomous applications. In this manuscript, a part-based convolutional neural network and dual interactive Wasserstein generative adversarial networks for landmark detection and localization of autonomous robots in an outdoor environment are proposed (P-CNN-DIWGAN-LMD-LZ). This research contains two phases landmark detection phase and the localization phase. In the landmark detection phase, the part-based convolutional neural network (P-CNN) is proposed to detect landmarks in capturing images. This landmark detection process creates 3 categories of responses for every detected landmarks instance: bounding box, label, and score. The bounding box has positioning with the sizing of detected landmarks at the input imagery. Label implicates detected landmark's class name. A score signifies an abjectness score that scales bounding box membership for landmarks or background classes. In the localization phase, a dual interactive Wasserstein generative adversarial network (DIWGAN) is proposed to determine robot location coordinates. Finally, the proposed method attains high robot localization recall at high accuracy in the real-world environment. Here, the outdoor robot localization dataset is taken from the KITTI dataset. The proposed method is implemented in Python;its performance is estimated under certain performance metrics, like mean absolute error (MAE), cosine proximity (CP), and accuracy. The performance of the proposed method shows higher accuracy compared with existing approaches, like DQP-ODA-LMD-LZ, TDL-LMD-LZ, and 3D-RISS-MLEVD- LMD-LZ. © 2022 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Playing to the Strengths of High- and Low-Resolution Cues for Ultra-High Resolution Image Segmentation

引用

IEEE Robotics and Automation Letters 2025年第8期10卷 7787-7794页

作者： Qi Li Jiexin Luo Chunxiao Chen Jiaxin Cai Wenjie Yang Yuanlong Yu Shengfeng He Wenxi Liu College of Computer and Data Science Fuzhou University Fuzhou China School of Computing and Information Systems Singapore Management University Singapore

In ultra-high resolution image segmentation task for robotic platforms like AAVs and autonomous vehicles, existing paradigms process a downsampled input image through a deep network and the original high-resolution image through a shallow network, then fusing their features for final segmentation. Although these features are designed to be complementary, they often contain redundant or even conflicting semantic information, which leads to blurred edge contours, particularly for small objects. This is especially detrimental to robotics applications requiring precise spatial awareness. To address this challenge, we propose a novel paradigm that disentangles the task into two independent subtasks concerning high- and low-resolution inputs, leveraging high-resolution features exclusively to capture low-level structured details and low-resolution features for extracting semantics. Specifically, for the high-resolution input, we propose a region-pixel association experts scheme that partitions the image into multiple regions. For the low-resolution input, we assign compact semantic tokens to the partitioned regions. Additionally, we incorporate a high-resolution local perception scheme with an efficient field-enriched local context module to enhance small object recognition in case of incorrect semantic assignment. Extensive experiments demonstrate the state-of-the-art performance of our method and validate the effectiveness of each designed component.

关键词： Semantics Image resolution Feature extraction data mining Image edge detection Training Semantic segmentation Autonomous vehicles Accuracy Spatial resolution

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based ECG Classification for Arterial Fibrillation Detection

引用

Computers, Materials & Continua 2024年第6期79卷 4805-4824页

作者： Muhammad Sohail Irshad Tehreem Masood Arfan Jaffar Muhammad Rashid Sheeraz Akram Abeer Aljohani Faculty of Computer Science&Information Technology The Superior UniversityLahore54000Pakistan Intelligent Data Visual Computing Research(IDVCR) Lahore54000Pakistan Department of Computer Science National University of TechnologyIslamabad45000Pakistan Information Systems Department College of Computer and Information SciencesImam Mohammad Ibn Saud Islamic University(IMSIU)Riyadh11432Saudi Arabia Department of Computer Science Applied CollegeTaibah UniversityMedina42353Saudi Arabia

The application of deep learning techniques in the medical field,specifically for Atrial Fibrillation(AFib)detection through Electrocardiogram(ECG)signals,has witnessed significant *** and timely diagnosis increases the patient’s chances of ***,issues like overfitting and inconsistent accuracy across datasets remain *** a quest to address these challenges,a study presents two prominent deep learning architectures,ResNet-50 and DenseNet-121,to evaluate their effectiveness in AFib *** aim was to create a robust detection mechanism that consistently performs *** such as loss,accuracy,precision,sensitivity,and Area Under the Curve(AUC)were utilized for *** findings revealed that ResNet-50 surpassed DenseNet-121 in all evaluated *** demonstrated lower loss rate 0.0315 and 0.0305 superior accuracy of 98.77%and 98.88%,precision of 98.78%and 98.89%and sensitivity of 98.76%and 98.86%for training and validation,hinting at its advanced capability for AFib *** insights offer a substantial contribution to the existing literature on deep learning applications for AFib detection from ECG *** comparative performance data assists future researchers in selecting suitable deep-learning architectures for AFib ***,the outcomes of this study are anticipated to stimulate the development of more advanced and efficient ECG-based AFib detection methodologies,for more accurate and early detection of AFib,thereby fostering improved patient care and outcomes.

关键词： Convolution neural network atrial fibrillation area under curve ECG false positive rate deep learning classification

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：