2021 16th International Workshop on Semantic and Social Media Adaptation & Personalization (SMAP)最新文献

Augmented and personalized digital narratives for Cultural Heritage under a tangible interface 在有形界面下增强和个性化的文化遗产数字叙事

2021 16th International Workshop on Semantic and Social Media Adaptation & Personalization (SMAP) Pub Date : 2021-11-04 DOI: 10.1109/SMAP53521.2021.9610815

G. Trichopoulos, John Aliprantis, M. Konstantakis, Konstantinos Michalakis, Phivos Mylonas, Yorghos Voutos, G. Caridakis

引用次数: 5

Exploiting Out-of-Domain Datasets and Visual Representations for Image Sentiment Classification 利用域外数据集和视觉表示进行图像情感分类

2021 16th International Workshop on Semantic and Social Media Adaptation & Personalization (SMAP) Pub Date : 2021-11-04 DOI: 10.1109/SMAP53521.2021.9610801

Alexandros Pournaras, Nikolaos Gkalelis, Damianos Galanopoulos, V. Mezaris

{"title":"Exploiting Out-of-Domain Datasets and Visual Representations for Image Sentiment Classification","authors":"Alexandros Pournaras, Nikolaos Gkalelis, Damianos Galanopoulos, V. Mezaris","doi":"10.1109/SMAP53521.2021.9610801","DOIUrl":"https://doi.org/10.1109/SMAP53521.2021.9610801","url":null,"abstract":"Visual sentiment analysis has recently gained attention as an important means of opinion mining, with many applications. It involves a high level of abstraction and subjectivity, which makes it a challenging task. The most recent works are based on deep convolutional neural networks, and exploit transfer learning from other image classification tasks. However, transferring knowledge from tasks other than image classification has not been investigated in the literature. Motivated by this, in this work we examine the potential of transferring knowledge from several pre-trained networks, some of which are out-of-domain. We show that by simply concatenating these diverse feature vectors we construct a rich image representation that can be used to train a classifier with state of the art performance on image sentiment analysis. We also evaluate a Mixture of Experts approach, for learning from this combination of representations, and highlight its performance advantages. We compare against the top-performing recently-published methods on four popular benchmark datasets and report new SOTA results on three of the four.","PeriodicalId":437320,"journal":{"name":"2021 16th International Workshop on Semantic and Social Media Adaptation & Personalization (SMAP)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123714190","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: 3

Issues and Challenges associated with Blockchain in Smart Cities 智慧城市中与区块链相关的问题和挑战

2021 16th International Workshop on Semantic and Social Media Adaptation & Personalization (SMAP) Pub Date : 2021-11-04 DOI: 10.1109/SMAP53521.2021.9610780

Gerasimos Vonitsanos, T. Panagiotakopoulos, Andreas Kanavos, M. Maragoudakis, Phivos Mylonas

引用次数: 3

Multimodal Lip- Reading for Tracheostomy Patients in the Greek Language 希腊语气管切开术患者的多模态唇读

2021 16th International Workshop on Semantic and Social Media Adaptation & Personalization (SMAP) Pub Date : 2021-11-04 DOI: 10.1109/SMAP53521.2021.9610767

Yorghos Voutos, G. Drakopoulos, G. Chrysovitsiotis, Z. Zachou, Dimitris Kikidis, E. Kyrodimos, T. Exarchos

{"title":"Multimodal Lip- Reading for Tracheostomy Patients in the Greek Language","authors":"Yorghos Voutos, G. Drakopoulos, G. Chrysovitsiotis, Z. Zachou, Dimitris Kikidis, E. Kyrodimos, T. Exarchos","doi":"10.1109/SMAP53521.2021.9610767","DOIUrl":"https://doi.org/10.1109/SMAP53521.2021.9610767","url":null,"abstract":"Loss of voice, may be due to problems in various organs of the human voice system is a major disability which commonly results in social isolation. By utilizing multimodal information sources such as video, audio and text, a sophisticated personalized voice reconstruction system can be created. In this work we collect multimodal information from patients before loss-of-voice medical procedures and design a complete system for lip-reading in the Greek language. In order to preprocess the data we apply lip-segmentation and frame-level sampling techniques. Text is matched with the corresponding video frames in order to create a word to frames dataset. Then deep learning methods are applied to create a sequence-to-sequence model for word prediction from lip-area frames. Our results show that the presented model achieves 85 % accuracy on the training set. Due to the limited availability of data the model overfits the training set resulting in worse performance on unseen data. Our model is the first deep learning model that is trained to recognize words from lip-are images in the Greek language. Overall it is necessary to collect more data and deal with the overfitting problem. In future work we plan to train the model in larger word sets from as many as 30 patients by the end of 2021.","PeriodicalId":437320,"journal":{"name":"2021 16th International Workshop on Semantic and Social Media Adaptation & Personalization (SMAP)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128288722","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

Augmented Reality children's book for intangible cultural heritage through participatory content creation and promotion. Case study: the pastoral life of Psiloritis as a UNESCO World Geopark 增强现实儿童非物质文化遗产图书通过参与式内容创作与推广。案例研究:作为联合国教科文组织世界地质公园的Psiloritis的田园生活

2021 16th International Workshop on Semantic and Social Media Adaptation & Personalization (SMAP) Pub Date : 2021-11-04 DOI: 10.1109/SMAP53521.2021.9610762

Antonios Ntagiantas, D. Manousos, M. Konstantakis, John Aliprantis, G. Caridakis

引用次数: 5

Users' Preferences of Profiling Attributes on Crowdsourcing Team Formation Systems 众包团队组建系统中用户对属性分析的偏好

2021 16th International Workshop on Semantic and Social Media Adaptation & Personalization (SMAP) Pub Date : 2021-11-04 DOI: 10.1109/SMAP53521.2021.9610773

F. Vinella, Ioanna Lykourentzou, J. Masthoff

{"title":"Users' Preferences of Profiling Attributes on Crowdsourcing Team Formation Systems","authors":"F. Vinella, Ioanna Lykourentzou, J. Masthoff","doi":"10.1109/SMAP53521.2021.9610773","DOIUrl":"https://doi.org/10.1109/SMAP53521.2021.9610773","url":null,"abstract":"People are increasingly making use of professional online services to outsource projects and remote teams through crowdsourcing tools. In these online self-assembly team formation settings, profiling information is vital to crowd users; it is focal to gathering knowledge about others and constructing virtual identities of themselves. This study investigates crowd users' preferences of profiling attributes displayed on online team formation systems. To evaluate participants' preferences, we looked at their willingness to see and their perceived usefulness across several profiling attributes grouped into surface-level and deep-level traits. These are classes of profiling traits quantifying group diversity that we use to distinguish between surface-level demographic and deep-level attitudinal traits. A total of 117 crowd participants answered close-ended questions about their preferences of profiling information concerning theirs and other crowd users' profiles on team self-assembly systems. Results indicate that crowd users significantly prefer disclosing surface-level attributes, both for themselves and others in terms of willingness to see and perceived usefulness. Surface-level attributes such as age, education, and availability are favored over deep-level attributes concerning crowd users' mental states, beliefs, and political affiliation. These results lay the foundation for future studies on the effectiveness and appropriateness of user-centered profiling information displayed on online crowdsourcing team formation systems.","PeriodicalId":437320,"journal":{"name":"2021 16th International Workshop on Semantic and Social Media Adaptation & Personalization (SMAP)","volume":"288 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114104386","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

Impact Of Covid-19 On Education Using Twitter Data 利用推特数据分析Covid-19对教育的影响

2021 16th International Workshop on Semantic and Social Media Adaptation & Personalization (SMAP) Pub Date : 2021-11-04 DOI: 10.1109/SMAP53521.2021.9610821

Anshita Makode, Alakananda Chakraborty, Avanti Darekar, Poojakumari Bist

{"title":"Impact Of Covid-19 On Education Using Twitter Data","authors":"Anshita Makode, Alakananda Chakraborty, Avanti Darekar, Poojakumari Bist","doi":"10.1109/SMAP53521.2021.9610821","DOIUrl":"https://doi.org/10.1109/SMAP53521.2021.9610821","url":null,"abstract":"With the rapid spread of Covid-19 cases throughout the world, all the nations have been sentenced to partial or complete lockdowns for their safety. Throughout this one section which has been almost completely under lockdown was the Education sector where students were hardly allowed to attend physical classes around 1.5 years now. Our aim in this paper is to use the social media tweets in understanding how the people have felt throughout this course of time, what difficulties they have faced, what are the advantages, disadvantages they feel are of this new normal. We will be extracting data from the social media using natural language processing, text mining techniques, sentiment analysis to determine various insights as to what they have faced and can this New Normal be actually normal someday. We have used Tableau Software to highlight the countries where concerned tweets have been posted more. Also using Word cloud we have tried to map the main concerns. We see that there have mixed concerns related to Education from fear of letting the students attend physical mode lectures to concerns as to what side-effects would be caused due to late conduction of exams and reaction to various government laws regarding the same.","PeriodicalId":437320,"journal":{"name":"2021 16th International Workshop on Semantic and Social Media Adaptation & Personalization (SMAP)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130050465","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

Automating road junction identification using Crowdsourcing and Machine Learning on GPS transformed data 利用众包和机器学习在GPS转换数据上自动识别道路交叉口

2021 16th International Workshop on Semantic and Social Media Adaptation & Personalization (SMAP) Pub Date : 2021-11-04 DOI: 10.1109/SMAP53521.2021.9610820

Constantinos Djouvas, Ioannis Despotis, Christos Christodoulou

引用次数: 1

A System for Collecting, Managing, Analyzing and Sharing Diverse, Multi-Faceted Cultural Heritage and Tourism Data 一个收集、管理、分析和共享多元、多面文化遗产和旅游数据的系统

2021 16th International Workshop on Semantic and Social Media Adaptation & Personalization (SMAP) Pub Date : 2021-11-04 DOI: 10.1109/SMAP53521.2021.9610777

Kimon Deligiannis, Paraskevi Raftopoulou, Christos Tryfonopoulos, C. Vassilakis

{"title":"A System for Collecting, Managing, Analyzing and Sharing Diverse, Multi-Faceted Cultural Heritage and Tourism Data","authors":"Kimon Deligiannis, Paraskevi Raftopoulou, Christos Tryfonopoulos, C. Vassilakis","doi":"10.1109/SMAP53521.2021.9610777","DOIUrl":"https://doi.org/10.1109/SMAP53521.2021.9610777","url":null,"abstract":"Today, social media platforms and other online sources, like forums and review sites, offer an abundance of cultural and touristic information that is voluntarily offered by travelers; this information, although helpful for other travelers, is typically fragmented and thus cannot be easily leveraged to exploitable knowledge by scientists and other tourism stakeholders. In this work, we present a novel, integrated system for collecting, managing, analyzing and sharing diverse, multi-faceted cultural heritage/tourism-related data that aims to assist scientists in the cultural heritage domain and tourism stakeholders to gather and synthesize scattered information to exploitable knowledge. The proposed system is tailored to the tourism domain needs, and allows users with minimum effort and zero IT expertise to (i) gather data from both structured and unstructured/semi-structured online sources, (ii) leverage the data to knowledge via appropriate analysis and visualization tools, and (iii) share the collected data and gathered knowledge with other stakeholders via appropriate publish-subscribe mechanisms. The proposed system is entirely open-source, designed upon big data tools and principles for the data store, the analytics production, and the knowledge sharing, and targets both performance and usability.","PeriodicalId":437320,"journal":{"name":"2021 16th International Workshop on Semantic and Social Media Adaptation & Personalization (SMAP)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116826068","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

[Blank page] (空白页)

2021 16th International Workshop on Semantic and Social Media Adaptation & Personalization (SMAP) Pub Date : 2021-11-04 DOI: 10.1109/smap53521.2021.9610757

引用次数: 0