检索结果-内蒙古大学图书馆

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Junho Kim Jiwon Jeong Young Min Kim Dept. of Electrical and Computer Engineering Seoul National University Dept. of Electrical Engineering Stanford University Interdisciplinary Program in Artificial Intelligence and INMC Seoul National University

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

We introduce a lightweight and accurate localization method that only utilizes the geometry of 2D-3D lines. Given a pre-captured 3D map, our approach localizes a panorama image, taking advantage of the holistic 360° view. The system mitigates potential privacy breaches or domain discrepancies by avoiding trained or hand-crafted visual descriptors. However, as lines alone can be ambiguous, we express distinctive yet compact spatial contexts from relationships between lines, namely the dominant directions of parallel lines and the intersection between non-parallel lines. The resulting representations are efficient in processing time and memory compared to conventional visual descriptor-based methods. Given the groups of dominant line directions and their intersections, we accelerate the search process to test thousands of pose candidates in less than a millisecond without sacrificing accuracy. We empirically show that the proposed 2D-3D matching can localize panoramas for challenging scenes with similar structures, dramatic domain shifts or illumination changes. Our fully geometric approach does not involve extensive parameter tuning or neural network training, making it a practical algorithm that can be readily deployed in the real world. Project page including the code is available through this link: https://***/fgpl/.

关键词： Location awareness Geometry Training Visualization Accuracy Three-dimensional displays Pipelines

来源：评论

学校读者我要写书评

暂无评论

ADMM-SRNet: Alternating Direction Method of Multipliers Based Sparse Representation Network for One-Class Classification

引用

IEEE Transactions on Image Processing 2023年 32卷 2843-2856页

作者： Chiou, Chien-Yu Lee, Kuang-Ting Huang, Chun-Rong Chung, Pau-Choo National Cheng Kung University Department of Electrical Engineering Tainan 701 Taiwan National Chung Hsing University Department of Computer Science and Engineering Taichung 402 Taiwan National Cheng Kung University Cross College Elite Program and Academy of Innovative Semiconductor and Sustainable Manufacturing Tainan 701 Taiwan

One-class classification aims to learn one-class models from only in-class training samples. Because of lacking out-of-class samples during training, most conventional deep learning based methods suffer from the feature collapse problem. In contrast, contrastive learning based methods can learn features from only in-class samples but are hard to be end-to-end trained with one-class models. To address the aforementioned problems, we propose alternating direction method of multipliers based sparse representation network (ADMM-SRNet). ADMM-SRNet contains the heterogeneous contrastive feature (HCF) network and the sparse dictionary (SD) network. The HCF network learns in-class heterogeneous contrastive features by using contrastive learning with heterogeneous augmentations. Then, the SD network models the distributions of the in-class training samples by using dictionaries computed based on ADMM. By coupling the HCF network, SD network and the proposed loss functions, our method can effectively learn discriminative features and one-class models of the in-class training samples in an end-to-end trainable manner. Experimental results show that the proposed method outperforms state-of-the-art methods on CIFAR-10, CIFAR-100 and ImageNet-30 datasets under one-class classification settings. Code is available at https://***/nchucvml/ADMM-SRNet. © 1992-2012 IEEE.

关键词： contrastive learning deep learning dictionary learning One-class classification sparse representation

来源：评论

学校读者我要写书评

暂无评论

In situ Observation of Lithium Stripping and Plating Process in an Open-cell All-solid-state Lithium Metal Battery

引用

Microscopy and microanalysis : the official journal of Microscopy Society of America, Microbeam Analysis Society, Microscopical Society of Canada 2023年第1期29卷 1287-1288页

作者： Wu, C. Zhao, L. Ai, Q. Risal, S. Lou, J. Yao, Y. Fan, Zheng Materials Science and Engineering Program and Texas Center for Superconductivity at the University of Houston University of Houston Houston TX United States Department of Electrical and Computer Engineering University of Houston Houston TX United States Department of Materials Science and Nano Engineering Rice University Houston TX United States Department of Engineering Technology University of Houston Houston TX United States

来源：评论

学校读者我要写书评

暂无评论

A Discontinuous Galerkin Time-Domain Scheme to Simulate Semiconductor Lasers

A Discontinuous Galerkin Time-Domain Scheme to Simulate Semi...

引用

European Conference on Antennas and Propagation, EuCAP

作者： Ming Dong Liang Chen Ran Zhao Hakan Bagci Electrical and Computer Engineering Program Computer Electrical and Mathematical Science and Engineering Division King Abdullah University of Science and Technology Thuwal Saudi Arabia

A computational framework, which relies on the discontinuous Galerkin time-domain scheme, is proposed to simulate transient lasing generated by interactions of light with an active medium. The proposed scheme solves a coupled system of the Maxwell and the rate equations. The active medium inside the laser region is described quantum-mechanically by the rate equations to account for the atomic transitions of a multi-level system, while electromagnetic field interactions are described classically by the Maxwell equations. Numerical examples are provided to demonstrate the accuracy and the applicability of the proposed framework.

关键词：

来源：评论

学校读者我要写书评

暂无评论

On-chip meta-lens based Adaptive Integrated Photonic Imager

On-chip meta-lens based Adaptive Integrated Photonic Imager

引用

Conference on Lasers and Electro-Optics (CLEO)

作者： Jong Ryul Kim Heijun Jeong Tingyi Gu Quantum Science and Engineering program University of Delaware Newark DE USA Electrical and Computer Engineering University of Delaware Newark DE USA

We demonstrate single-drive adaptive on-chip meta-lens imager with optimized profile for doped silicon heater and metal heaters.

ISBN: (纸本)9798350369311

We demonstrate single-drive adaptive on-chip meta-lens imager with optimized profile for doped silicon heater and metal heaters.

关键词： Heating systems Metals Doping profiles Silicon System-on-chip Electro-optical waveguides Photonics

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study of DeepLabCut and Other Open-Source Pupillometry Data Analysis Algorithms – Which to Choose?

引用

Machine Graphics and Vision 2024年第2期33卷 77-90页

作者： Badkul, Amitesh Mishra, Sonakshi Kommajosyula, Srinivasa P. Department of Electrical & Electronics Engineering Birla Institute of Technology and Science Hyderabad Campus Jawahar Nagar Hyderabad India Department of Pharmacy Birla Institute of Technology and Science Hyderabad Campus Jawahar Nagar Hyderabad India Ph.D. Program in Computer Science The Graduate Center The City University of New York New YorkNY United States

Pupillometry measures pupil size, and several open-source algorithms are available to analyse pupillometry data. However, only a few studies compared these algorithms’ accuracy and computational resources. This study aims to compare the accuracy of computer vision-based algorithms (Swirski, Starburst, PuRe, ElSe, ExCuSe algorithms) and the machine learning algorithm, DeepLabCut, to the double-blinded human examiners (gold-standard). Training of DeepLabCut with different architectures and a variable number of markers (2-9 markers) was done on an open-source dataset. The duration of training was statistically longer for the ResNet152 model compared to the MobileNet model. The pupil diameters in computer vision-based software such as PuRe, Starburst, and Swirski were statistically different from human measurements. MobileNet 2 and 3 marker models were the closest to the human measurements. In conclusion, this work highlights the efficiency of lower marker models based on MobileNet architecture in DeepLabCut, which consumes fewer computational resources and is more accurate. © 2024 Institute of Information Technology, Warsaw university of Life Sciences - SGGW. All rights reserved.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Hybrid Classical-Quantum Optimization for Ensemble Learning 9

Hybrid Classical-Quantum Optimization for Ensemble Learning

引用

9th International Conference on Advanced Informatics: Concepts, Theory and Applications, ICAICTA 2022

作者： Yulianti, Lenny Putri Santoso, Judhi Trisetyarso, Agung Surendro, Kridanto Bandung Institute of Technology School of Electrical Engineering and Informatics Bandung Indonesia Bina Nusantara University Program - Computer Science Bandung Indonesia

ISBN: (数字)9781665456685

ISBN: (纸本)9781665456685

Ensemble learning has gained attention due to its ability to improve predictive performance in classification and regression problems. However, there are several issues related to optimizing accuracy, diversity, and efficiency simultaneously in the ensemble learning process. Existing studies mostly focus on one or two of them, or focus on all three but only on the specific process of ensemble learning. Besides, the quantum approach has been expected to accelerate the optimization process while maintaining accuracy. The contribution of this study is to design a hybrid classical-quantum methodology for optimizing ensemble learning in a holistic way. This methodology combines classical (i.e. clustering, improved evaluation measures, and generalized weighted ensemble with internally tuned hyperparameters) and quantum (i.e. quantum annealing) approaches, and this methodology is analyzed to provide more optimal results. © 2022 IEEE.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

ReMP: Reusable Motion Prior for Multi-domain 3D Human Pose Estimation and Motion Inbetweening

ReMP: Reusable Motion Prior for Multi-domain 3D Human Pose E...

引用

IEEE Workshop on Applications of computer Vision (WACV)

作者： Hojun Jang Young Min Kim Dept. of Electrical and Computer Engineering Seoul National University Interdisciplinary Program in Artificial Intelligence and INMC Seoul National University

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

We present Reusable Motion prior (ReMP), an effective motion prior that can accurately track the temporal evolution of motion in various downstream tasks. Inspired by the success of foundation models, we argue that a robust spatio-temporal motion prior can encapsulate underlying 3D dynamics applicable to various sensor modalities. We learn the rich motion prior from a sequence of complete parametric models of posed human body shape. Our prior can easily estimate poses in missing frames or noisy measurements despite significant occlusion by employing a temporal attention mechanism. More interestingly, our prior can guide the system with incomplete and challenging input measurements to quickly extract critical information to estimate the sequence of poses, significantly improving the training efficiency for mesh sequence recovery. ReMP consistently outperforms the baseline method on diverse and practical 3D motion data, including depth point clouds, LiDAR scans, and IMU sensor data. Project page is available in https://***/ReMP.

关键词： Training Point cloud compression Three-dimensional displays Accuracy Tracking Shape Pose estimation Noise Parametric statistics Noise measurement

来源：评论

学校读者我要写书评

暂无评论

Instance Segmentation of Damaged Insulators for Power System Inspection and Maintenance

Instance Segmentation of Damaged Insulators for Power System...

引用

2024 International Conference on Decision Aid Sciences and Applications, DASA 2024

作者： Merin, Jovencio Alon, Alvin Sarraga Pinkihan, Joel Sandil, Ricky C. Delos Santos Ligayo, Michael Angelo Arago, Ryan Flores Sevilla, Rovenson Cunanan, Christopher Technological University of the Philippines Dept. of Electrical Engineering Manila Philippines Center for AI Research Department of Trade and Industry Makati City Philippines College of Computing Sciences Ifugao State University Ifugao Philippines College Preparatory Program Kingdom of Saudi Arabia Saudi Arabia College of Engineering Quezon City University Quezon City Philippines Technological University of the Philippines Department of Electrical Engineering Manila Philippines Bulacan State University Christopher Franco Cunanan Computer Engineering Department Bulacan Philippines

ISBN: (纸本)9798350369106

This paper introduces a novel approach for power system inspection using Mask-RCNN, an advanced model for instance segmentation. The accuracy of our model in identifying and diagnosing damaged low- to medium-voltage insulators is exceptional, as evidenced by its Mean Average Precision (mAP) score of 98.7%• Throughout the training process, the model exhibited minimal loss metrics, indicating its proficiency in predicting bounding boxes precisely, segmenting, classifying, and aligning masks. The model exhibited consistent reliability in distinguishing between undamaged and damaged components during the inference process, as seen by its consistently high detection rates for both 'normal intact' and 'damaged broken' insulators. The results demonstrate the practical usefulness of the model and offer promising prospects for enhancing power system maintenance and inspection protocols. The model's consistent and accurate identification of damaged insulators has the potential to significantly enhance the safety and efficiency of power systems, thereby revolutionizing the industry. © 2024 IEEE.

关键词： Insulator contamination

来源：评论

学校读者我要写书评

暂无评论

A ShuffleNet Architecture-Based Multi-Layer Feature Scaling and Fusion Approach for Underwater Net Cage Damage Detection in Aquaculture

A ShuffleNet Architecture-Based Multi-Layer Feature Scaling ...

引用

IEEE International Conference on Consumer Electronics-Asia (ICCE-Asia)

作者： Xiang-Rui Huang Yi-Cheng Chen Liang-Bi Chen Wu-Chih Hu Department of Electrical Engineering Master Program in Electrical Engineering and Computer Science National Penghu University of Science and Technology Penghu Taiwan Department of Computer Science and Information Engineering National Penghu University of Science and Technology Penghu Taiwan

ISBN: (数字)9798331530839

ISBN: (纸本)9798331530846

In offshore aquaculture operations, personnel equipped with diving gear are often necessary to inspect the underwater net cages for damage, particularly on the sea floor. This manual inspection process is time-consuming and complex. To overcome this problem, this paper proposes a computer vision solution for identifying damage in underwater net cages to address the inefficiencies and challenges of traditional manual inspections. The proposed scheme utilizes a high-performance multi-branch computational architecture designed based on ShuffleNet architecture to detect net cage damage more efficiently. Experimental results demonstrate that this work performs well on the ImageNet ILSVRC-2010 dataset and achieves an accuracy of 88.54% in underwater net damage detection.

关键词： Accuracy Gears Computational modeling Sea floor computer architecture Manuals Inspection Feature extraction Personnel Aquaculture

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：