首页 > 最新文献

Proceedings of the Brazilian Symposium on Multimedia and the Web最新文献

英文 中文
Once Learning for Looking and Identifying Based on YOLO-v5 Object Detection 基于YOLO-v5目标检测的一次学习查找与识别
Pub Date : 2022-11-07 DOI: 10.1145/3539637.3557929
Lucas S. Althoff, Mylène C. Q. Farias, L. Weigang
Object detection is an essential capacity of computer vision solutions. It has gained attention over the last years by using a core component of the “Once learning” and “Few-shot learning” mechanism. This research analyzes the ability of a machine learning framework named “You Only Look Once,” to perform object localization task in a “Heuristic once learning” context. It will also study the advantages and practical limitations of YOLO by experimenting with two types of implementation: 1) the simplest one (a.k.a tiny YOLO), and 2) the first version of YOLO. The case studies are carried out in various visual data types and object contexts, such as object deformation caused by fast-forward frame, spatial distortion caused by isometric projection, and gaming images with abnormal objects. Finally, we build a dataset accounting for a new task so-called “Heuristic once learning”. Results using YOLO-v5 in such conditions showed that YOLO had difficulties to generalize simple abstractions of the characters, pointing to the necessity of new approaches to solve such challenges.
目标检测是计算机视觉解决方案的基本能力。在过去的几年里,它通过使用“一次学习”和“几次学习”机制的核心组成部分而受到关注。本研究分析了名为“你只看一次”的机器学习框架在“启发式一次学习”环境中执行对象定位任务的能力。它还将通过试验两种类型的实现来研究YOLO的优点和实际局限性:1)最简单的(也称为微型YOLO)和2)YOLO的第一版。案例研究是在各种视觉数据类型和对象背景下进行的,例如由快进帧引起的对象变形,由等距投影引起的空间扭曲,以及具有异常对象的游戏图像。最后,我们建立了一个数据集,用于描述所谓的“启发式一次学习”的新任务。在这种情况下使用YOLO-v5的结果表明,YOLO难以概括简单的字符抽象,这表明需要新的方法来解决这一挑战。
{"title":"Once Learning for Looking and Identifying Based on YOLO-v5 Object Detection","authors":"Lucas S. Althoff, Mylène C. Q. Farias, L. Weigang","doi":"10.1145/3539637.3557929","DOIUrl":"https://doi.org/10.1145/3539637.3557929","url":null,"abstract":"Object detection is an essential capacity of computer vision solutions. It has gained attention over the last years by using a core component of the “Once learning” and “Few-shot learning” mechanism. This research analyzes the ability of a machine learning framework named “You Only Look Once,” to perform object localization task in a “Heuristic once learning” context. It will also study the advantages and practical limitations of YOLO by experimenting with two types of implementation: 1) the simplest one (a.k.a tiny YOLO), and 2) the first version of YOLO. The case studies are carried out in various visual data types and object contexts, such as object deformation caused by fast-forward frame, spatial distortion caused by isometric projection, and gaming images with abnormal objects. Finally, we build a dataset accounting for a new task so-called “Heuristic once learning”. Results using YOLO-v5 in such conditions showed that YOLO had difficulties to generalize simple abstractions of the characters, pointing to the necessity of new approaches to solve such challenges.","PeriodicalId":350776,"journal":{"name":"Proceedings of the Brazilian Symposium on Multimedia and the Web","volume":"124 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115884290","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: 5
An Interface for Visualizing Applied Interventions Data through Mobile Devices 通过移动设备可视化应用干预数据的接口
Pub Date : 2022-11-07 DOI: 10.1145/3539637.3558231
L. Scalco, Kamila R. H. Rodrigues, M. G. Pimentel
Professionals or researchers who, in diverse areas, need to accompany users (e.g., patients or students), and they use approaches that allow to collect daily data from their users. These specialists accompany and carry out collection through the planning and implementation of intervention programs. The objective of this work is to understand how the specialists visualize and analyze data, offering an alternative visualization form, based on the combination of different techniques, that allows the specialists to make use of the structure of the intervention programs to follow the application of these programs. A study was carried out with healthcare professionals and through the analysis of a visualization prototype and graph structures, it was possible to understand how these specialists interpret their data. We also identified requirements for our visualization interface.
在不同领域需要陪伴用户(例如患者或学生)的专业人员或研究人员,他们使用允许从用户那里收集日常数据的方法。这些专家通过干预方案的规划和实施来陪伴和执行收集工作。这项工作的目的是了解专家如何可视化和分析数据,提供一种基于不同技术组合的替代可视化形式,使专家能够利用干预程序的结构来跟踪这些程序的应用。我们与医疗保健专业人员进行了一项研究,通过对可视化原型和图形结构的分析,可以了解这些专家如何解释他们的数据。我们还确定了可视化界面的需求。
{"title":"An Interface for Visualizing Applied Interventions Data through Mobile Devices","authors":"L. Scalco, Kamila R. H. Rodrigues, M. G. Pimentel","doi":"10.1145/3539637.3558231","DOIUrl":"https://doi.org/10.1145/3539637.3558231","url":null,"abstract":"Professionals or researchers who, in diverse areas, need to accompany users (e.g., patients or students), and they use approaches that allow to collect daily data from their users. These specialists accompany and carry out collection through the planning and implementation of intervention programs. The objective of this work is to understand how the specialists visualize and analyze data, offering an alternative visualization form, based on the combination of different techniques, that allows the specialists to make use of the structure of the intervention programs to follow the application of these programs. A study was carried out with healthcare professionals and through the analysis of a visualization prototype and graph structures, it was possible to understand how these specialists interpret their data. We also identified requirements for our visualization interface.","PeriodicalId":350776,"journal":{"name":"Proceedings of the Brazilian Symposium on Multimedia and the Web","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129800531","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
Full Reference Stereoscopic Objective Quality Assessment using Lightweight Machine Learning 使用轻量级机器学习的全参考立体客观质量评估
Pub Date : 2022-11-07 DOI: 10.1145/3539637.3557936
Narúsci S. Bastos, Lucas Seidy Ribeiro Dos Santos Ikenoue, D. Palomino, G. Corrêa, Tatiana Tavares, B. Zatt
Decades of research on Image Quality Assessment (IQA) have promoted the creation of a variety of objective quality metrics that strongly correlate to subjective image quality. However, challenges remain when considering quality assessment of 3D/stereo images. Multiple objective quality metrics for 3D images were designed by extending the well-known 2D metrics. As a result, these solutions tend to present weaknesses under 3D-specific artifacts. Recent works demonstrate the effectiveness of machine-learning techniques in the design of 3D quality metrics. Although effective, some machine learning-based solutions may lead to high computational effort and restrict its adoption in low-latency lightweight systems/applications. This paper presents a study on full-reference stereoscopic objective quality assessment considering lightweight machine learning. We evaluated four different decision tree-based algorithms considering eight distinct sets of image features. The classifiers were trained using data from the Waterloo IVC 3D Image Quality Database to determine the subjective quality score measured using Mean Opinion Score (MOS). The results show that RandomForest generally obtains the best accuracy. Our study demonstrates the feasibility of decision tree-based solutions as an accurate and lightweight approach for 3D image quality assessment.
几十年来对图像质量评估(IQA)的研究促进了各种与主观图像质量密切相关的客观质量指标的创建。然而,在考虑3D/立体图像的质量评估时,挑战仍然存在。通过对二维图像质量度量的扩展,设计了三维图像的多目标质量度量。因此,这些解决方案往往在3d特定工件下呈现弱点。最近的工作证明了机器学习技术在3D质量度量设计中的有效性。虽然有效,但一些基于机器学习的解决方案可能会导致高计算工作量,并限制其在低延迟轻量级系统/应用程序中的采用。提出了一种考虑轻量级机器学习的全参考立体客观质量评价方法。我们评估了四种不同的基于决策树的算法,考虑了八组不同的图像特征。分类器使用来自Waterloo IVC 3D图像质量数据库的数据进行训练,以确定使用平均意见分数(Mean Opinion score, MOS)测量的主观质量分数。结果表明,随机森林总体上获得了最好的准确率。我们的研究证明了基于决策树的解决方案作为一种准确和轻量级的3D图像质量评估方法的可行性。
{"title":"Full Reference Stereoscopic Objective Quality Assessment using Lightweight Machine Learning","authors":"Narúsci S. Bastos, Lucas Seidy Ribeiro Dos Santos Ikenoue, D. Palomino, G. Corrêa, Tatiana Tavares, B. Zatt","doi":"10.1145/3539637.3557936","DOIUrl":"https://doi.org/10.1145/3539637.3557936","url":null,"abstract":"Decades of research on Image Quality Assessment (IQA) have promoted the creation of a variety of objective quality metrics that strongly correlate to subjective image quality. However, challenges remain when considering quality assessment of 3D/stereo images. Multiple objective quality metrics for 3D images were designed by extending the well-known 2D metrics. As a result, these solutions tend to present weaknesses under 3D-specific artifacts. Recent works demonstrate the effectiveness of machine-learning techniques in the design of 3D quality metrics. Although effective, some machine learning-based solutions may lead to high computational effort and restrict its adoption in low-latency lightweight systems/applications. This paper presents a study on full-reference stereoscopic objective quality assessment considering lightweight machine learning. We evaluated four different decision tree-based algorithms considering eight distinct sets of image features. The classifiers were trained using data from the Waterloo IVC 3D Image Quality Database to determine the subjective quality score measured using Mean Opinion Score (MOS). The results show that RandomForest generally obtains the best accuracy. Our study demonstrates the feasibility of decision tree-based solutions as an accurate and lightweight approach for 3D image quality assessment.","PeriodicalId":350776,"journal":{"name":"Proceedings of the Brazilian Symposium on Multimedia and the Web","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130300563","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
Interactive POI Recommendation: applying a Multi-Armed Bandit framework to characterise and create new models for this scenario 交互式POI建议:应用多武装强盗框架来描述和创建此场景的新模型
Pub Date : 2022-11-07 DOI: 10.1145/3539637.3557060
Thiago Silva, N. Silva, Carlos Mito, A. Pereira, Leonardo Rocha
Nowadays, instead of the traditional batch paradigm where the system trains and predicts a model at scheduled times, new Recommender Systems (RSs) have become interactive models. In this case, the RS should continually recommend the most relevant item(s), receive the user feedback(s), and constantly update itself as a sequential decision model. Thus, the literature has modeled each recommender as a Multi-Armed Bandit (MAB) problem to select new arms (items) at each iteration. However, despite recent advances, MAB models have not yet been studied in some classical scenarios, such as the points-of-interest (POIs) recommendation. For this reason, this work intends to fill this scientific gap, adapting classical MAB algorithms for this context. This process is performed through an interactive recommendation framework called iRec. iRec provides three modules to prepare the dataset, create new recommendation agents, and simulate the interactive scenario. This framework contains several MAB state-of-the-art algorithms, a hyperparameter adjustment module, different evaluation metrics, different visual metaphors to present the results, and statistical validation. By instantiating and adapting iRec to our context, we can assess the quality of different interactive recommenders for the POI recommendation scenario.
如今,新的推荐系统(RSs)已经成为交互式模型,而不是传统的批处理范式,即系统在预定的时间内训练和预测模型。在这种情况下,RS应该不断推荐最相关的项目,接收用户反馈,并作为顺序决策模型不断更新自身。因此,文献将每个推荐器建模为一个多臂强盗(MAB)问题,以在每次迭代中选择新的臂(项目)。然而,尽管最近取得了进展,MAB模型尚未在一些经典场景中进行研究,例如兴趣点(poi)推荐。出于这个原因,这项工作打算填补这一科学空白,适应经典的MAB算法在这种情况下。这个过程是通过一个名为iRec的交互式推荐框架执行的。iRec提供了三个模块来准备数据集、创建新的推荐代理和模拟交互场景。该框架包含几个MAB最先进的算法,一个超参数调整模块,不同的评估指标,不同的视觉隐喻来呈现结果,以及统计验证。通过实例化iRec并使其适应我们的上下文,我们可以评估POI推荐场景中不同交互式推荐器的质量。
{"title":"Interactive POI Recommendation: applying a Multi-Armed Bandit framework to characterise and create new models for this scenario","authors":"Thiago Silva, N. Silva, Carlos Mito, A. Pereira, Leonardo Rocha","doi":"10.1145/3539637.3557060","DOIUrl":"https://doi.org/10.1145/3539637.3557060","url":null,"abstract":"Nowadays, instead of the traditional batch paradigm where the system trains and predicts a model at scheduled times, new Recommender Systems (RSs) have become interactive models. In this case, the RS should continually recommend the most relevant item(s), receive the user feedback(s), and constantly update itself as a sequential decision model. Thus, the literature has modeled each recommender as a Multi-Armed Bandit (MAB) problem to select new arms (items) at each iteration. However, despite recent advances, MAB models have not yet been studied in some classical scenarios, such as the points-of-interest (POIs) recommendation. For this reason, this work intends to fill this scientific gap, adapting classical MAB algorithms for this context. This process is performed through an interactive recommendation framework called iRec. iRec provides three modules to prepare the dataset, create new recommendation agents, and simulate the interactive scenario. This framework contains several MAB state-of-the-art algorithms, a hyperparameter adjustment module, different evaluation metrics, different visual metaphors to present the results, and statistical validation. By instantiating and adapting iRec to our context, we can assess the quality of different interactive recommenders for the POI recommendation scenario.","PeriodicalId":350776,"journal":{"name":"Proceedings of the Brazilian Symposium on Multimedia and the Web","volume":"89 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125105060","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
How Politicians Communicate in Social Media: A Cross-Platform Study 政治家如何在社交媒体上沟通:一个跨平台的研究
Pub Date : 2022-11-07 DOI: 10.1145/3539637.3558232
L. S. Oliveira, Wesley Costa, Pedro O. S. Vaz de Melo, Fabrício Benevenuto
With the advent of social media, politicians have access to a new way of communicating with their constituents. It made it possible for politicians without television time, considered essential for a campaign, to expose their ideas and reach a large part of the electorate. As it is a relatively recent phenomenon, researchers from different areas of knowledge have found fertile ground to carry out their research. However, most studies focus on analyzing politicians’ communication on only one social media. In this work, we performed a cross-platform analysis of the communication of Brazilian politicians on Facebook, Instagram, and Twitter. We quantified the posts of these politicians, how much they replicate content and the level of engagement on each of the three social networks. In addition, we grouped and characterized the profiles and communication strategies used by these politicians. As a result, we observed that the majority post on the three social networks, there is diversity in the strategic choice of the main media and there are many politicians who only replicate content on the three networks. However, some post a lot of messages and adapt the content for each network, which suggests management by communication professionals on social media. We also verified that there are several communication profiles, from comical to controversial, with the eclectic profile prevailing, which diversifies the style of the posts.
随着社交媒体的出现,政客们有了一种与选民沟通的新方式。这使得没有电视时间的政客们有可能展示他们的想法,并接触到大部分选民,而电视时间被认为是竞选必不可少的。由于这是一个相对较新的现象,来自不同知识领域的研究人员都找到了开展研究的沃土。然而,大多数研究只关注于分析政治家在一种社交媒体上的沟通。在这项工作中,我们对巴西政客在Facebook、Instagram和Twitter上的交流进行了跨平台分析。我们量化了这些政客的帖子,他们复制了多少内容,以及他们在这三个社交网络上的参与度。此外,我们对这些政治家的个人资料和沟通策略进行了分组和描述。因此,我们观察到大多数人在三个社交网络上发帖,主要媒体的战略选择存在多样性,并且有许多政治家只在三个社交网络上复制内容。然而,一些人发布了大量的消息,并根据每个网络调整内容,这表明社交媒体上的传播专业人士进行管理。我们还证实,有几种传播概况,从滑稽的到有争议的,以折衷的概况为主,这使得帖子的风格多样化。
{"title":"How Politicians Communicate in Social Media: A Cross-Platform Study","authors":"L. S. Oliveira, Wesley Costa, Pedro O. S. Vaz de Melo, Fabrício Benevenuto","doi":"10.1145/3539637.3558232","DOIUrl":"https://doi.org/10.1145/3539637.3558232","url":null,"abstract":"With the advent of social media, politicians have access to a new way of communicating with their constituents. It made it possible for politicians without television time, considered essential for a campaign, to expose their ideas and reach a large part of the electorate. As it is a relatively recent phenomenon, researchers from different areas of knowledge have found fertile ground to carry out their research. However, most studies focus on analyzing politicians’ communication on only one social media. In this work, we performed a cross-platform analysis of the communication of Brazilian politicians on Facebook, Instagram, and Twitter. We quantified the posts of these politicians, how much they replicate content and the level of engagement on each of the three social networks. In addition, we grouped and characterized the profiles and communication strategies used by these politicians. As a result, we observed that the majority post on the three social networks, there is diversity in the strategic choice of the main media and there are many politicians who only replicate content on the three networks. However, some post a lot of messages and adapt the content for each network, which suggests management by communication professionals on social media. We also verified that there are several communication profiles, from comical to controversial, with the eclectic profile prevailing, which diversifies the style of the posts.","PeriodicalId":350776,"journal":{"name":"Proceedings of the Brazilian Symposium on Multimedia and the Web","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129249427","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
Collaboration as a Driving Factor for Hit Song Classification 合作是热门歌曲分类的驱动因素
Pub Date : 2022-11-07 DOI: 10.1145/3539637.3556993
Mariana O. Silva, Gabriel P. Oliveira, Danilo B. Seufitelli, A. Lacerda, M. Moro
The Web has transformed many services and products, including the way we consume music. In a currently streaming-oriented era, predicting hit songs is a major open issue for the music industry. Indeed, there are many efforts in finding the driving factors that shape the success of songs. Yet another feature that may improve such efforts is artistic collaboration, as it allows the songs to reach a wider audience. Therefore, we propose a multi-perspective approach that includes collaboration between artists as a factor for hit song prediction. Specifically, by combining online data from Billboard and Spotify, we model the issue as a binary classification task by using different model variants. Our results show that relying only on music-related features is not enough, whereas models that also consider collaboration features produce better results.
网络已经改变了许多服务和产品,包括我们消费音乐的方式。在当前以流媒体为导向的时代,预测热门歌曲是音乐行业面临的一个重大问题。事实上,人们在寻找影响歌曲成功的驱动因素方面做了很多努力。然而,另一个可能改善这种努力的特点是艺术合作,因为它可以让歌曲接触到更广泛的听众。因此,我们提出了一种多视角的方法,将艺术家之间的合作作为热门歌曲预测的一个因素。具体来说,通过结合Billboard和Spotify的在线数据,我们通过使用不同的模型变体将问题建模为二元分类任务。我们的研究结果表明,仅仅依赖与音乐相关的特征是不够的,而同时考虑协作特征的模型会产生更好的结果。
{"title":"Collaboration as a Driving Factor for Hit Song Classification","authors":"Mariana O. Silva, Gabriel P. Oliveira, Danilo B. Seufitelli, A. Lacerda, M. Moro","doi":"10.1145/3539637.3556993","DOIUrl":"https://doi.org/10.1145/3539637.3556993","url":null,"abstract":"The Web has transformed many services and products, including the way we consume music. In a currently streaming-oriented era, predicting hit songs is a major open issue for the music industry. Indeed, there are many efforts in finding the driving factors that shape the success of songs. Yet another feature that may improve such efforts is artistic collaboration, as it allows the songs to reach a wider audience. Therefore, we propose a multi-perspective approach that includes collaboration between artists as a factor for hit song prediction. Specifically, by combining online data from Billboard and Spotify, we model the issue as a binary classification task by using different model variants. Our results show that relying only on music-related features is not enough, whereas models that also consider collaboration features produce better results.","PeriodicalId":350776,"journal":{"name":"Proceedings of the Brazilian Symposium on Multimedia and the Web","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127350403","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: 5
Homogeneous and Automated Migration of Virtual Machines Between Multiple Public Clouds 在多个公有云之间实现虚拟机同构和自动化迁移
Pub Date : 2022-11-07 DOI: 10.1145/3539637.3558043
Marc Xavier, I. S. Sette, C. Ferraz
The objective of this work is to analyze the required steps for automated migration of Virtual Machines (VMs) using a proposed solution, called Kumo, through scenarios using public clouds, such as Amazon Web Services (AWS), Microsoft Azure (AZ) and Google Cloud Platform (GCP). A performance evaluation is carried out considering the Total Migration Time (TTM) metric between homogeneous and heterogeneous clouds. Among the homogeneous scenarios, which are those in which the source and destination clouds are from the same provider, but in different data centers, the best result occurred in migrations between Azure clouds, with average TTM of 45m59s. For heterogeneous, the best scenario was the GCP-AWS migration, with TTM of 45m56s. The nine steps for the automated migration of VMs were analyzed, showing that five of them combined significantly impacted, between 94.01% and 99.44%, the TTM of the 9 scenarios tested.
这项工作的目的是通过使用公共云(如亚马逊网络服务(AWS)、微软Azure (AZ)和谷歌云平台(GCP))的场景,分析使用称为Kumo的拟议解决方案自动迁移虚拟机(vm)所需的步骤。考虑同构云和异构云之间的总迁移时间(TTM)度量,进行了性能评估。在同质场景中,即源云和目标云来自同一提供商,但位于不同的数据中心的场景,在Azure云之间的迁移效果最好,平均TTM为45m59秒。对于异构,最佳场景是GCP-AWS迁移,TTM为45m56秒。对虚拟机自动化迁移的9个步骤进行了分析,发现其中5个步骤对测试的9个场景的TTM有显著影响,在94.01%到99.44%之间。
{"title":"Homogeneous and Automated Migration of Virtual Machines Between Multiple Public Clouds","authors":"Marc Xavier, I. S. Sette, C. Ferraz","doi":"10.1145/3539637.3558043","DOIUrl":"https://doi.org/10.1145/3539637.3558043","url":null,"abstract":"The objective of this work is to analyze the required steps for automated migration of Virtual Machines (VMs) using a proposed solution, called Kumo, through scenarios using public clouds, such as Amazon Web Services (AWS), Microsoft Azure (AZ) and Google Cloud Platform (GCP). A performance evaluation is carried out considering the Total Migration Time (TTM) metric between homogeneous and heterogeneous clouds. Among the homogeneous scenarios, which are those in which the source and destination clouds are from the same provider, but in different data centers, the best result occurred in migrations between Azure clouds, with average TTM of 45m59s. For heterogeneous, the best scenario was the GCP-AWS migration, with TTM of 45m56s. The nine steps for the automated migration of VMs were analyzed, showing that five of them combined significantly impacted, between 94.01% and 99.44%, the TTM of the 9 scenarios tested.","PeriodicalId":350776,"journal":{"name":"Proceedings of the Brazilian Symposium on Multimedia and the Web","volume":"203 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128403318","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
Improving Multilabel Text Classification with Stacking and Recurrent Neural Networks 用堆叠和递归神经网络改进多标签文本分类
Pub Date : 2022-11-07 DOI: 10.1145/3539637.3557000
R. M. Nunes, M. A. Domingues, V. D. Feltrim
Multilabel text classification can be defined as a mapping function that categorizes a text in natural language into one or more labels defined by the scope of a problem. In this work we propose an architecture of stacked classifiers for multilabel text classification. The proposed models use an LSTM recurrent neural network in the first stage of the stack and different multilabel classifiers in the second stage. We evaluated our proposal in two datasets well-known in the literature (TMDB and EUR-LEX Subject Matters), and the results showed that the proposed stack consistently outperforms the baselines.
多标签文本分类可以定义为一种映射函数,它将自然语言中的文本分类为由问题范围定义的一个或多个标签。在这项工作中,我们提出了一种用于多标签文本分类的堆叠分类器架构。提出的模型在堆栈的第一阶段使用LSTM递归神经网络,在第二阶段使用不同的多标签分类器。我们在两个文献中知名的数据集(TMDB和EUR-LEX Subject Matters)中评估了我们的提议,结果表明提议的堆栈始终优于基线。
{"title":"Improving Multilabel Text Classification with Stacking and Recurrent Neural Networks","authors":"R. M. Nunes, M. A. Domingues, V. D. Feltrim","doi":"10.1145/3539637.3557000","DOIUrl":"https://doi.org/10.1145/3539637.3557000","url":null,"abstract":"Multilabel text classification can be defined as a mapping function that categorizes a text in natural language into one or more labels defined by the scope of a problem. In this work we propose an architecture of stacked classifiers for multilabel text classification. The proposed models use an LSTM recurrent neural network in the first stage of the stack and different multilabel classifiers in the second stage. We evaluated our proposal in two datasets well-known in the literature (TMDB and EUR-LEX Subject Matters), and the results showed that the proposed stack consistently outperforms the baselines.","PeriodicalId":350776,"journal":{"name":"Proceedings of the Brazilian Symposium on Multimedia and the Web","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129905971","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
Characterizing Brazilian Political Ads on Facebook Facebook上巴西政治广告的特征
Pub Date : 2022-11-07 DOI: 10.1145/3539637.3557935
Cora Silberschneider, Samuel S. Guimarães, Fabrício Benevenuto, Márcio Silva
Most of politicians, public figures and political candidates use online advertising platforms to spread their political values and messages. Since 2018, Facebook has made available an Ad Library providing advertising transparency to prevent interference in elections and other political issues. However, it is not explicit how the ads are selected to incorporate this database and to what extent there is an artificial intelligence applied to this selection. In this work, we provide a categorization of the ads data in Brazil to understand the dynamic of political advertisements and what type of ads are present in this ad library. We analyze impressions, the money spent and who are the advertisers on ads from 2018 to 2021. Among our findings, we show that during the election months of 2018 and 2020 the volume of ads correspond to approximately 30% of the ads in the dataset and the moving average of the money spent per ads increases about 200% after the first round of brazilian elections.
大多数政治家、公众人物和政治候选人使用网络广告平台来传播他们的政治价值观和信息。自2018年以来,脸书提供了一个广告库,提供广告透明度,以防止干预选举和其他政治问题。然而,目前还不清楚如何选择广告以纳入该数据库,以及人工智能在多大程度上应用于这种选择。在这项工作中,我们对巴西的广告数据进行了分类,以了解政治广告的动态以及该广告库中存在的广告类型。我们分析了从2018年到2021年的广告印象、花费的钱以及谁是广告客户。在我们的研究结果中,我们表明,在2018年和2020年的选举月份,广告的数量相当于数据集中约30%的广告,而在巴西第一轮选举后,每个广告花费的移动平均值增加了约200%。
{"title":"Characterizing Brazilian Political Ads on Facebook","authors":"Cora Silberschneider, Samuel S. Guimarães, Fabrício Benevenuto, Márcio Silva","doi":"10.1145/3539637.3557935","DOIUrl":"https://doi.org/10.1145/3539637.3557935","url":null,"abstract":"Most of politicians, public figures and political candidates use online advertising platforms to spread their political values and messages. Since 2018, Facebook has made available an Ad Library providing advertising transparency to prevent interference in elections and other political issues. However, it is not explicit how the ads are selected to incorporate this database and to what extent there is an artificial intelligence applied to this selection. In this work, we provide a categorization of the ads data in Brazil to understand the dynamic of political advertisements and what type of ads are present in this ad library. We analyze impressions, the money spent and who are the advertisers on ads from 2018 to 2021. Among our findings, we show that during the election months of 2018 and 2020 the volume of ads correspond to approximately 30% of the ads in the dataset and the moving average of the money spent per ads increases about 200% after the first round of brazilian elections.","PeriodicalId":350776,"journal":{"name":"Proceedings of the Brazilian Symposium on Multimedia and the Web","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126770061","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
An Approach for Sensory Effects Dispersion Simulation with Computational Fluid Dynamics 一种基于计算流体力学的感觉效应色散模拟方法
Pub Date : 2022-11-07 DOI: 10.1145/3539637.3556999
Renato O. Rodrigues, José Ricardo da Silva, Diego N. Brandão, J. Santos
The inclusion of sensory effects in multimedia applications has the potential to increase the Quality of Experience (QoE) and improve users immersion. However, authoring such applications presents challenges arising from the need to control the rendering of sensory effects in the physical environment along with the presentation of their counterpart in the multimedia application and the constantly changing sensory effects state according to user interaction. Computational Fluid Dynamics (CFD) techniques can be used to simulate the sensory effects in a virtual environment and use the generated data to automatically control actuators. In this work, we propose an architecture to simulate wind sensory effects in an interactive real-time application and validate it using a CFD method. Data from simulation is then used to infer propagation delay and the wind temperature at the user position.
在多媒体应用程序中加入感官效果有可能提高体验质量(QoE)并改善用户沉浸感。然而,编写这样的应用程序提出了挑战,因为需要控制物理环境中感官效果的呈现,以及在多媒体应用程序中对应的呈现,以及根据用户交互不断变化的感官效果状态。计算流体动力学(CFD)技术可用于模拟虚拟环境中的感官效果,并利用生成的数据自动控制执行器。在这项工作中,我们提出了一个架构来模拟风的感官效应在一个交互式的实时应用程序,并使用CFD方法验证它。然后使用模拟数据推断传播延迟和用户位置的风温。
{"title":"An Approach for Sensory Effects Dispersion Simulation with Computational Fluid Dynamics","authors":"Renato O. Rodrigues, José Ricardo da Silva, Diego N. Brandão, J. Santos","doi":"10.1145/3539637.3556999","DOIUrl":"https://doi.org/10.1145/3539637.3556999","url":null,"abstract":"The inclusion of sensory effects in multimedia applications has the potential to increase the Quality of Experience (QoE) and improve users immersion. However, authoring such applications presents challenges arising from the need to control the rendering of sensory effects in the physical environment along with the presentation of their counterpart in the multimedia application and the constantly changing sensory effects state according to user interaction. Computational Fluid Dynamics (CFD) techniques can be used to simulate the sensory effects in a virtual environment and use the generated data to automatically control actuators. In this work, we propose an architecture to simulate wind sensory effects in an interactive real-time application and validate it using a CFD method. Data from simulation is then used to infer propagation delay and the wind temperature at the user position.","PeriodicalId":350776,"journal":{"name":"Proceedings of the Brazilian Symposium on Multimedia and the Web","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126635913","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
期刊
Proceedings of the Brazilian Symposium on Multimedia and the Web
全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1