检索结果-内蒙古大学图书馆

SE-PSNet: Silhouette-based enhancement feature for panoptic segmentation network

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Chang, Shuo-En Yang, Yi-Cheng Lin, En-Ting Hsiao, Pei-Yung Fu, Li-Chen Department of Computer Science and Information Engineering National Taiwan University Taipei Taiwan Graduate Institute of Networking and Multimedia National Taiwan University Taipei Taiwan Department of Electrical Engineering National University of Kaohsiung Kaohsiung Taiwan

Recently, there has been a panoptic segmentation task combining semantic and instance segmentation, in which the goal is to classify each pixel with the corresponding instance ID. In this work, we propose a solution to tackle the panoptic segmentation task. The overall structure combines the bottom-up method and the top-down method. Therefore, not only can there be better performance, but also the execution speed can be maintained. The network mainly pays attention to the quality of the mask. In the previous work, we can see that the uneven contour of the object is more likely to appear, resulting in low-quality prediction. Accordingly, we propose enhancement features and corresponding loss functions for the silhouette of objects and backgrounds to improve the mask. Meanwhile, we use the new proposed confidence score to solve the occlusion problem and make the network tend to use higher quality masks as prediction results. To verify our research, we used the COCO dataset and CityScapes dataset to do experiments and obtained competitive results with fast inference time. © 2021, CC BY-NC-SA.

关键词：

IoT-Based Transmission Tower Monitoring Communications and Visualization Platform

学校读者我要写书评

暂无评论

IoT-Based Transmission Tower Monitoring Communications and V...

Future Telecommunication Technologies (SOFTT), Symposium on

作者： Mohamad Razin Naim Mohd Alias Dzahir Rashidi Mohd Dzaki Norashidah Md Din Siti Noratiqah Mohd Deros Rossi Passarella Azzam Eusuf Chaai Amier Chaai College of Graduate Studies Universiti Tenaga Nasional (UNITEN) Malaysia Institute of Energy Infrastructures Universiti Tenaga Nasional (UNITEN) Malaysia Faculty of Computer Science Department Computer Networking & Information System Universitas Sriwijaya Palembang Indonesia School of Computer Science University of Nottingham Malaysia Campus (UNMC) Malaysia

ISBN: (纸本)9781665455985

Transmission tower fault monitoring has always been a challenge for power system engineers. Vertical and horizontal displacement monitoring is important for evaluating health status of transmission tower's infrastructures. Quick fault detection can help protect the equipment by allowing the disconnection of transmission tower before any significant damage of the equipment. The purpose of this study is to propose an IoT monitoring system for transmission towers. The monitoring system adheres to Three-Layer IoT architecture. In the perception layer, sensors MPU6050 and Anemometer are used to measure a specific parameter. The data, which includes the Roll, Pitch, Yaw, and wind velocity, is gathered and delivered to the ESP32 through network layer using WiFi, which then stored the information in the cloud using InfluxDB. For visualization purposes in the application layer, Grafana is utilized which is hosted in the web dashboard and the mobile application. Flutter framework is used to develop the mobile application. An alert will be displayed in the mobile application when the threshold of the wind speed exceeds 10m/s.

关键词： Fluid flow measurement Wind speed Fault detection Poles and towers Electrical fault detection Mobile applications Sensors

Multiple-Image Super-Resolution for Networked Extremely Low-Resolution Thermal Sensor Array

学校读者我要写书评

暂无评论

Multiple-Image Super-Resolution for Networked Extremely Low-...

Machine Learning on Edge in Sensor Systems (SenSys-ML), IEEE Second Workshop on

作者： Chi-Sheng Shih Yao-Ting Wang Jyun-Jhe Chou Department of Computer Science and Information Engineering Graduate Institute of Networking and Multimedia National Taiwan University Taipei Taiwan

ISBN: (数字)9781728199962

ISBN: (纸本)9781728199979

Observing activeness of patients and elderly for long time at private space is a desired metric for elderly care. Many state-of-the-art mechanisms require either using wearable sensors, assists by medical staffs, or observation at designated location. Consequently, it is difficult, if not impossible, to acquire long term trend. Thermal sensors are not sensitive to illumination and can detect heat sources under low lightness. Moreover, it is not trivial to identify an individual from thermal images. However, a low cost and effective solution remain open. Low-resolution thermal sensors cost less but suffer from noisy reading. In this work, we fuse multiple low-resolution thermal images to reconstruct higher resolution thermal images to identify human activities. The evaluation results show that the accuracy of activity recognition while using low resolution thermal images are 96% of that while using high resolution thermal images, which requires 80 times of data and ten times of hardware cost.

关键词： Sensor arrays THERMAL SENSOR Medical Staff Thermal Personal Space Wearable sensors images Heat sources super-resolution aged person High definition Human Activities illumination Lighting

Lower Bounds for the Minimum Spanning Tree Cycle Intersection Problem

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Dubinsky, Manuel Chao, Kun-Mao Massri, César Taubin, Gabriel Ingeniería en Informática Departamento de Tecnología y Administración Universidad Nacional de Avellaneda Argentina Departamento de Computación Facultad de Ciencias Exactas y Naturales Universidad de Buenos Aires Argentina Department of Computer Science and Information Engineering National Taiwan University Taipei Taiwan Graduate Institute of Biomedical Electronics and Bioinformatics National Taiwan University Taipei Taiwan Graduate Institute of Networking and Multimedia National Taiwan University Taipei Taiwan Departamento de Matemática Universidad de CAECE CABA Argentina School of Engineering Brown University ProvidenceRI United States

Minimum spanning trees are important tools in the analysis and design of networks. Many practical applications require their computation, ranging from biology and linguistics to economy and telecommunications. The set of cycles of a network has a vector space structure. Given a spanning tree, the set of non-tree edges defines cycles that determine a basis. The intersection of two such cycles is the number of edges they have in common and the intersection number -denoted ∩(G)-, is the number of non-empty pairwise intersections of the cycles of the basis. The Minimum Spanning Tree Cycle Intersection problem consists in finding a spanning tree such that the intersection number is minimum. This problem is relevant in order to integrate discrete differential forms. In this paper, we present two lower bounds of the intersection number of an arbitrary connected graph G = (V, E). In the first part, we prove the following statement: (Equation presented) where n = |V | and ν is the cyclomatic number of G. In the second part, based on some experimental results and a new observation, we conjecture the following improved tight lower bound: (Equation presented) where 2ν = q(n − 1) + r is the integer division of 2ν and n − 1. This is the first result in a general context, that is for an arbitrary connected graph. © 2024, CC BY.

关键词： Vector spaces

CholecSeg8k: A semantic segmentation dataset for laparoscopic cholecystectomy based on Cholec80

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Hong, W.-Y. Kao, C.-L. Kuo, Y.-H. Wang, J.-R. Chang, W.-L. Shih, Chi-Sheng Graduate Institute of Networking and Multimedia Department of Computer Science and Information Engineering National Taiwan University Taipei106 Taiwan

computer-assisted surgery has been developed to enhance surgery correctness and safety. However, the researchers and engineers suffer from limited annotated data to develop and train better algorithms. Consequently, the development of fundamental algorithms such as Simultaneous Localization and Mapping (SLAM) are limited. This article elaborates the efforts of preparing the dataset for semantic segmentation, which is the foundation of many computer-assisted surgery mechanisms. Based on the Cholec80 dataset [3], we extracted 8,080 laparoscopic cholecystectomy image frames from 17 video clips in Cholec80 and annotated the images. The dataset is named CholecSeg8K and its total size is 3GB. Each of these images are annotated at pixel-level for thirteen classes, which are commonly founded in laparoscopic cholecystectomy surgery. CholecSeg8k is released under the license CC BY-NC-SA 4.0. © 2020, CC BY-NC-SA.

关键词： Semantics

Improving Generalization of Metric Learning via Listwise Self-distillation

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zeng, Zelong Yang, Fan Wang, Zheng Satoh, Shin'ichi The Department of Information and Communication Engineering Graduate School of Information Science and Technology The University of Tokyo Japan The Digital Content and Media Sciences Research Division National Institute of Informatics Japan The School of Computer Science National Engineering Research Center for Multimedia Software Wuhan University China

Most deep metric learning (DML) methods employ a strategy that forces all positive samples to be close in the embedding space while keeping them away from negative ones. However, such a strategy ignores the internal relationships of positive (negative) samples and often leads to overfitting, especially in the presence of hard samples and mislabeled samples. In this work, we propose a simple yet effective regularization, namely Listwise Self-Distillation (LSD), which progressively distills a model's own knowledge to adaptively assign a more appropriate distance target to each sample pair in a batch. LSD encourages smoother embeddings and information mining within positive (negative) samples as a way to mitigate overfitting and thus improve generalization. Our LSD can be directly integrated into general DML frameworks. Extensive experiments show that LSD consistently boosts the performance of various metric learning methods on multiple datasets. Copyright © 2022, The Authors. All rights reserved.

关键词： Distillation

Geo-Localization via Ground-to-Satellite Cross-View Image Retrieval

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zeng, Zelong Wang, Zheng Yang, Fan Satoh, Shin'ichi The School of Computer Science National Engineering Research Center for Multimedia Software Wuhan University China The Department of Information and Communication Engineering Graduate School of Information Science and Technology The University of Tokyo Japan The Digital Content and Media Sciences Research Division National Institute of Informatics Japan

The large variation of viewpoint and irrelevant content around the target always hinder accurate image retrieval and its subsequent tasks. In this paper, we investigate an extremely challenging task: given a ground-view image of a landmark, we aim to achieve cross-view geo-localization by searching out its corresponding satellite-view images. Specifically, the challenge comes from the gap between ground-view and satellite-view, which includes not only large viewpoint changes (some parts of the landmark may be invisible from front view to top view) but also highly irrelevant background (the target landmark tend to be hidden in other surrounding buildings), making it difficult to learn a common representation or a suitable mapping. To address this issue, we take advantage of drone-view information as a bridge between ground-view and satellite-view domains. We propose a Peer Learning and Cross Diffusion (PLCD) framework. PLCD consists of three parts: 1) a peer learning across ground-view and drone-view to find visible parts to benefit ground-drone cross-view representation learning;2) a patch-based network for satellite-drone cross-view representation learning;3) a cross diffusion between ground-drone space and satellite-drone space. Extensive experiments conducted on the University-Earth and University-Google datasets show that our method outperforms state-of-the-arts significantly. Copyright © 2022, The Authors. All rights reserved.

关键词： Satellites

A Survey on Temporal Knowledge Graph Completion: Taxonomy, Progress, and Prospects

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wang, Jiapu Wang, Boyue Qiu, Meikang Pan, Shirui Xiong, Bo Liu, Heng Luo, Linhao Liu, Tengfei Hu, Yongli Yin, Baocai Gao, Wen Beijing Municipal Key Lab of Multimedia and Intelligent Software Technology Beijing Artificial Intelligence Institute Faculty of Information Technology Beijing University of Technology Beijing100124 China The Beacom College of Computer and Cyber Sciences Dakota State University MadisonSD United States Griffith University QLD Australia The Department of Computer Science University of Stuttgart Stuttgart70569 Germany The Department of Data Science and AI Monash University Melbourne Australia The Institute of Digital Media Peking University Beijing100871 China The School of Electronic and Computer Engineering Peking University Shenzhen Graduate School Shenzhen518055 China

Temporal characteristics are prominently evident in a substantial volume of knowledge, which underscores the pivotal role of Temporal Knowledge Graphs (TKGs) in both academia and industry. However, TKGs often suffer from incompleteness for three main reasons: the continuous emergence of new knowledge, the weakness of the algorithm for extracting structured information from unstructured data, and the lack of information in the source dataset. Thus, the task of Temporal Knowledge Graph Completion (TKGC) has attracted increasing attention, aiming to predict missing items based on the available information. In this paper, we provide a comprehensive review of TKGC methods and their details. Specifically, this paper mainly consists of three components, namely, 1) Background, which covers the preliminaries of TKGC methods, loss functions required for training, as well as the dataset and evaluation protocol;2) Interpolation, that estimates and predicts the missing elements or set of elements through the relevant available information. It further categorizes related TKGC methods based on how to process temporal information;3) Extrapolation, which typically focuses on continuous TKGs and predicts future events, and then classifies all extrapolation methods based on the algorithms they utilize. We further pinpoint the challenges and discuss future research directions of TKGC. Copyright © 2023, The Authors. All rights reserved.

关键词： Interpolation

Three-stage binarization of color document images based on discrete wavelet transform and generative adversarial networks

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Ju, Rui-Yang Lin, Yu-Shian Jin, Yanlin Chen, Chih-Chia Chien, Chun-Tse Chiang, Jen-Shiun Graduate Institute of Networking and Multimedia National Taiwan University No. 1 Sec. 4 Roosevelt Rd. Taipei City106319 Taiwan Department of Electrical and Computer Engineering Tamkang University No.151 Yingzhuan Rd. Tamsui Dist. New Taipei City251301 Taiwan Department of Electrical and Computer Engineering Rice University 6100 Main St. HoustonTX77005 United States

The efficient extraction of text information from the background in degraded color document images is an important challenge in the preservation of ancient manuscripts. The imperfect preservation of ancient manuscripts has led to different types of degradation over time, such as page yellowing, staining, and ink bleeding, seriously affecting the results of document image binarization. This work proposes an effective three-stage network method to image enhancement and binarization of degraded documents using generative adversarial networks (GANs). Specifically, in Stage-1, we first split the input images into multiple patches, and then split these patches into four single-channel patch images (gray, red, green, and blue). Then, three single-channel patch images (red, green, and blue) are processed by the discrete wavelet transform (DWT) with normalization. In Stage-2, we use four independent generators to separately train GAN models based on the four channels on the processed patch images to extract color foreground information. Finally, in Stage-3, we train two independent GAN models on the outputs of Stage-2 and the resized original input images (512 × 512) as the local and global predictions to obtain the final outputs. The experimental results show that the Avg-Score metrics of the proposed method are 77.64, 77.95, 79.05, 76.38, 75.34, and 77.00 on the (H)-DIBCO 2011, 2013, 2014, 2016, 2017, and 2018 datasets, which are at the state-of-the-art level. The implementation code for this work is available at https://***/abcpp12383/ ThreeStageBinarization. Copyright © 2022, The Authors. All rights reserved.

关键词： Generative adversarial networks