Proceedings of the 2020 6th International Conference on Computer and Technology Applications最新文献

Converting Diagram to a Timeline Ontology 将图表转换为时间轴本体

Proceedings of the 2020 6th International Conference on Computer and Technology Applications Pub Date : 2020-04-14 DOI: 10.1145/3397125.3397151

N. Voit, S. Kirillov, S. Bochkov

引用次数: 0

End-to-End Texture-Aware and Depth-Aware Embedded Advertising for Videos 端到端纹理感知和深度感知视频嵌入广告

Proceedings of the 2020 6th International Conference on Computer and Technology Applications Pub Date : 2020-04-14 DOI: 10.1145/3397125.3397133

Jiasen Li, Xun Gong, Boning Li

{"title":"End-to-End Texture-Aware and Depth-Aware Embedded Advertising for Videos","authors":"Jiasen Li, Xun Gong, Boning Li","doi":"10.1145/3397125.3397133","DOIUrl":"https://doi.org/10.1145/3397125.3397133","url":null,"abstract":"The number of online videos is increasing rapidly with the prosperity of advertising market. To dig out the immense potential of videos, there are mainly two advertising types for commercial usage, mid-roll and embedded. Embedded advertisements, compared with mid-roll ones, is an imperceptible and brilliant strategy. However once the video is produced, the advertisement embedded in it is nonchangeable, which causes out-of-date advertisements or personalized advertising difficulty. Meanwhile, the trade-off among video webs' income, video shooters' production difficulty and video watchers' aesthetic taste remains as a challenge with previous advertising strategies. To solve the problems above, we propose a pipeline that automatically embeds advertisements in real-time into a monocular RGB video or a single RGB image. The pipeline detects a non-intrusive region with awareness of texture and depth, and overlays it with an advertisement. Tools such as segmentation and 3D reconstruction are used inside this pipeline to detect physical-world information. A corner-based tracker is built to preserve 3D shape information of the candidate region, which makes the embedded advertisement natural. the pipeline runs a shoot change detector in parallel to keep advertisement visible on the main scene.","PeriodicalId":303304,"journal":{"name":"Proceedings of the 2020 6th International Conference on Computer and Technology Applications","volume":"42 7","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120922326","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Description-aware Fashion Image Inpainting with Convolutional Neural Networks in Coarse-to-Fine Manner 基于粗糙到精细方式的卷积神经网络的描述感知时尚图像绘制

Proceedings of the 2020 6th International Conference on Computer and Technology Applications Pub Date : 2020-04-14 DOI: 10.1145/3397125.3397155

Furkan Kinli, B. Özcan, Mustafa Furkan Kıraç

{"title":"Description-aware Fashion Image Inpainting with Convolutional Neural Networks in Coarse-to-Fine Manner","authors":"Furkan Kinli, B. Özcan, Mustafa Furkan Kıraç","doi":"10.1145/3397125.3397155","DOIUrl":"https://doi.org/10.1145/3397125.3397155","url":null,"abstract":"Inpainting a particular missing region in an image is a challenging vision task, and promising improvements on this task have been achieved with the help of the recent developments in vision-related deep learning studies. Although it may have a direct impact on the decisions of AI-based fashion analysis systems, a limited number of studies for image inpainting have been done in fashion domain, so far. In this study, we propose a multi-modal generative deep learning approach for filling the missing parts in fashion images by constraining visual features with textual features extracted from image descriptions. Our model is composed of four main blocks which can be introduced as textual feature extractor, coarse image generator guided by textual features, fine image generator enhancing the coarse output, and lastly global and local discriminators improving refined outputs. Several experiments conducted on FashionGen dataset with different combination of neural network components show that our multi-modal approach is able to generate visually plausible patches to fill the missing parts in the images.","PeriodicalId":303304,"journal":{"name":"Proceedings of the 2020 6th International Conference on Computer and Technology Applications","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134223053","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

An EMR Sharing and Privacy Protection Mechanism Based on Medical Consortium Blockchain 基于医疗联盟区块链的电子病历共享与隐私保护机制

Proceedings of the 2020 6th International Conference on Computer and Technology Applications Pub Date : 2020-04-14 DOI: 10.1145/3397125.3397153

Zhiyong Li, Li-Hui Zhang

引用次数: 2

Investigating End User Errors in Oil and Gas Critical Control Systems 调查油气关键控制系统中的终端用户错误

Proceedings of the 2020 6th International Conference on Computer and Technology Applications Pub Date : 2020-04-14 DOI: 10.1145/3397125.3397135

Layth Nabeel Alrawi, Tolga Pusatli

引用次数: 2

Real-Time Long-Term Tracking with Adaptive Online Searching Model 基于自适应在线搜索模型的实时长期跟踪

Proceedings of the 2020 6th International Conference on Computer and Technology Applications Pub Date : 2020-04-14 DOI: 10.1145/3397125.3397136

Daniel Do, Giap Nguyen Vu, Minh Bui, Huong Ninh, Hai Tran Tien

引用次数: 2

Multi-Thread Frame Tiling Model in Concurrent Real-Time Object Detection for Resources Optimization in YOLOv3 面向YOLOv3并发实时目标检测的多线程帧平铺模型

Proceedings of the 2020 6th International Conference on Computer and Technology Applications Pub Date : 2020-04-14 DOI: 10.1145/3397125.3397139

Sara Abri, Rayan Abri, Anıl Yarıcı, S. Cetin

{"title":"Multi-Thread Frame Tiling Model in Concurrent Real-Time Object Detection for Resources Optimization in YOLOv3","authors":"Sara Abri, Rayan Abri, Anıl Yarıcı, S. Cetin","doi":"10.1145/3397125.3397139","DOIUrl":"https://doi.org/10.1145/3397125.3397139","url":null,"abstract":"In the process of object detection, You Look Only Once, version 3 (YOLOv3) approach has been applied as a more efficient solution than Convolutional Neural Network (CNN) methods in accuracy and speed. In some environments, there is a need to process multiple real-time object detection algorithms concurrently where each object detection algorithm receives a live stream from a camera. In this research, we aim to optimize the system resources including the Graphics Processing Unit(GPU) and the Central Processing Unit(CPU) where accuracy indicated using frames per second (FPS) has no change in the process of detection. We propose improvements in terms of architectural models for real-time object detection. In this way, a Multi-thread Frame Tiling model is proposed to optimize GPU and CPU usage per YOLO object to handle concurrent surveillance video streams. Thus, it can be covered a large scale of surveillance cameras on multiple live streams concurrently. To evaluate the proposed model, we investigate the efficiency of GPU and CPU system resources. The experiment results show that the detection algorithm with the Multi-thread Frame Tiling model is by an average of 116.6 in FPS for all video qualities (480p, 720p, and 1080p resolution) compared to the Original YOLOv3 by an average of 27.1 while there is no change in accuracy in the detection process by YOLOv3.","PeriodicalId":303304,"journal":{"name":"Proceedings of the 2020 6th International Conference on Computer and Technology Applications","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114709649","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

MotorIA: Automatic E-Learning Course Generation System MotorIA:自动电子学习课程生成系统

Proceedings of the 2020 6th International Conference on Computer and Technology Applications Pub Date : 2020-04-14 DOI: 10.1145/3397125.3397128

María del Carmen Rodríguez-Hernández, María de la Vega Rodrigálvarez-Chamarro, Jorge I. Vea-Murguia Merck, Ángel Esteban Ballano, Marta Arguedas Lafuente, R. del-Hoyo-Alonso

{"title":"MotorIA: Automatic E-Learning Course Generation System","authors":"María del Carmen Rodríguez-Hernández, María de la Vega Rodrigálvarez-Chamarro, Jorge I. Vea-Murguia Merck, Ángel Esteban Ballano, Marta Arguedas Lafuente, R. del-Hoyo-Alonso","doi":"10.1145/3397125.3397128","DOIUrl":"https://doi.org/10.1145/3397125.3397128","url":null,"abstract":"Recently, through the availability of open data sources and the existence of advanced techniques of Natural Language Processing (NLP) and Artificial Intelligence, several tools have emerged to support the educational learning process of students and lecturers (experts in different knowledge domains). However, there are very few works which propose tools that automate the e-learning course content development process. Hence, experts in the field of educational training have shown great interest in the emergence of applications that ease this type of process. This paper presents MotorIA, a system which uses NLP and Machine Learning techniques as a means to automate online course content generation from different domains (e.g., computer science, biology, mathematic, etc.). MotorIA is supplied with unstructured information extracted from both Wikipedia services and PDF documents. During the e-learning course content generation process, textual information is pre-processed and structured in a knowledge graph, which must satisfy a set of constraints predefined by experts in the field. In a posterior phase, MotorIA was validated by expert users obtaining good evaluation results.","PeriodicalId":303304,"journal":{"name":"Proceedings of the 2020 6th International Conference on Computer and Technology Applications","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123430990","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

An Augmented Reality Based Modular Platform for Solar Energy Education 基于增强现实的太阳能教育模块化平台

Proceedings of the 2020 6th International Conference on Computer and Technology Applications Pub Date : 2020-04-14 DOI: 10.1145/3397125.3397149

M. Dursun

{"title":"An Augmented Reality Based Modular Platform for Solar Energy Education","authors":"M. Dursun","doi":"10.1145/3397125.3397149","DOIUrl":"https://doi.org/10.1145/3397125.3397149","url":null,"abstract":"In recent years, renewable energy consumption has been rapidly increasing instead of fossil energy sources for countless reasons. Installation or maintenance of the renewable energy power plants are very important in terms of energy quality, installation and maintain personnel's safety. The same manner and in with the by same methods in each power plant installation the applying same standard is very important. Unfortunately, enough number personnel could not have been trained to meet this service as parallel with the rapid increased need for renewable energy. One of the areas with qualified personnel shortage is solar energy systems. It is seen in the literature that the use of virtual reality in education has become widespread. The use of augmented reality in engineering education increases the quality of education and shortens the learning process time. It is inevitable that sufficient number of personnel will be trained in this field in a short time. This training method will enable the personnel to follow the same standard and same process steps to be trained in a shorter time and safely. In this study, an augmented reality has been applied in the training of the personnel in the installation of the solar energy system. From the results obtained, it was concluded that it can be used as training material in certificate programs with vocational and technical school students doing solar energy education.","PeriodicalId":303304,"journal":{"name":"Proceedings of the 2020 6th International Conference on Computer and Technology Applications","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126480636","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Republic of Turkey Identity Card (TCKK): Banking Use Case in Authentication & Customer Onboarding 土耳其共和国身份证(TCKK):身份验证和客户入职中的银行用例

Proceedings of the 2020 6th International Conference on Computer and Technology Applications Pub Date : 2020-04-14 DOI: 10.1145/3397125.3397126

Mehmet Kıvılcım Keleş, S. Demirel

引用次数: 0