2018 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR)最新文献_第3页

Entity Resolution Using Logistic Regression as an extension to the Rule-Based Oyster System 使用逻辑回归作为基于规则的牡蛎系统的扩展的实体解析

2018 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR) Pub Date : 2018-04-10 DOI: 10.1109/MIPR.2018.00033

Fumiko Kobayashi, Aziz Eram, J. Talburt

引用次数: 8

GeoSClean: Secure Cleaning of GPS Trajectory Data Using Anomaly Detection GeoSClean:利用异常检测安全清洗GPS轨迹数据

2018 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR) Pub Date : 2018-04-10 DOI: 10.1109/MIPR.2018.00037

Vikram Patil, Priyanka Singh, Shivam B. Parikh, P. Atrey

引用次数: 15

Who Is Earning? Understanding and Modeling the Virtual Gifts Behavior of Users in Live Streaming Economy 谁在赚钱?流媒体经济中用户虚拟礼物行为的理解与建模

2018 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR) Pub Date : 2018-04-10 DOI: 10.1109/MIPR.2018.00028

Wei Tu, Chen Yan, Yiping Yan, Xuan Ding, Lifeng Sun

{"title":"Who Is Earning? Understanding and Modeling the Virtual Gifts Behavior of Users in Live Streaming Economy","authors":"Wei Tu, Chen Yan, Yiping Yan, Xuan Ding, Lifeng Sun","doi":"10.1109/MIPR.2018.00028","DOIUrl":"https://doi.org/10.1109/MIPR.2018.00028","url":null,"abstract":"Recently, live streaming is gaining increasing en- thusiasm, like Twitch, Inke and YouTube. Online streamers can interact with viewers in real time in live platforms with audio, video and text. The virtual gift is one of the most important business models for these live streaming platforms. The viewers can purchase and send virtual gifts to the streamers during the live process. These behaviors have great market potential and economic value, but little previous research paid attention about this. In this paper, we measured the basic information and economic behavior of users on a large representative live streaming platform (Inke1). To be specific, we discovered 20% of viewers contributed 97% of all gifts, and 77% of viewers only present for top three streamers. Especially, we also found that most gifting behaviors broke out in short periods when barrage increased, and gifting behaviors could be inspired by others due to competitiveness. Moreover, we investigated the correlation of various factors, proposed a decision tree based prediction model to infer the future revenue of the streamers. The result will bring benefit for both industrial entrepreneurs (for improving the design of the system operating mechanism of live platforms) and researchers (for interesting problems in personalized recommendation, etc.).","PeriodicalId":320000,"journal":{"name":"2018 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125910174","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: 19

DeepRailway: A Deep Learning System for Forecasting Railway Traffic 深度铁路:预测铁路交通的深度学习系统

2018 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR) Pub Date : 2018-04-10 DOI: 10.1109/MIPR.2018.00017

Tianqi Xia, Xuan Song, Z. Fan, H. Kanasugi, Quanjun Chen, Renhe Jiang, R. Shibasaki

{"title":"DeepRailway: A Deep Learning System for Forecasting Railway Traffic","authors":"Tianqi Xia, Xuan Song, Z. Fan, H. Kanasugi, Quanjun Chen, Renhe Jiang, R. Shibasaki","doi":"10.1109/MIPR.2018.00017","DOIUrl":"https://doi.org/10.1109/MIPR.2018.00017","url":null,"abstract":"Urban railway transit is of great significance in the daily lives of Metropolitan residents. Therefore, forecasting rail- way traffic is fundamental to urban management. However, very few research has been focused on collectively forecast railway transit in a citywide scale. With the development of location based service, the huge volume of GPS trajectory data make it possible for a citywide prediction of railway traffic. In this paper, we propose a deep-learning-based system named DeepRailway to predict and simulate rail- way traffic through heterogeneous data sources. Our data sources include huge volume of trajectory data and rail- way network. In our system, we firstly match the trajectory points to the railway network. And then the patterns of these trajectories are found using a network-based kernel density estimation (KDE), which converts the forecasting task into a sequence prediction problem. An LSTM recurrent neu- ral network model is built to predict the densities through- out the whole network. We evaluate our system in differ- ent timespan and prediction steps to verify its performance against other prediction methods.","PeriodicalId":320000,"journal":{"name":"2018 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127708931","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: 4

SecMed: A Secure Approach for Proving Rightful Ownership of Medical Images in Encrypted Domain over Cloud SecMed:一种在云上加密域证明医学图像合法所有权的安全方法

2018 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR) Pub Date : 2018-04-10 DOI: 10.1109/MIPR.2018.00085

Aishwarya Pandey, Priyanka Singh, Nishant Agarwal, B. Raman

{"title":"SecMed: A Secure Approach for Proving Rightful Ownership of Medical Images in Encrypted Domain over Cloud","authors":"Aishwarya Pandey, Priyanka Singh, Nishant Agarwal, B. Raman","doi":"10.1109/MIPR.2018.00085","DOIUrl":"https://doi.org/10.1109/MIPR.2018.00085","url":null,"abstract":"The wide attacking surface of the public cloud poses threats to the security of sensitive information such as medical information stored at these distributed cloud data centers. Obscuring this information using traditional encryption schemes would limit the processing capabilities in encrypted domain that are provided via various cloud services. Moreover, it is vital to address the issue of rightful ownership so that the person to which the medical information belongs to can be determined. To address these issues, Chinese Remainder Theorem (CRT) based secret sharing scheme has been employed to divide the medical images into multiple random looking shares which are information theoretically secure and reveal no information about the images. Based on a secret key, some of these encrypted shares are embedded with the secret owner specific information in the encrypted domain itself prior to outsourcing. To prove rightful ownership at the receiver end, this secret information can be extracted either directly from the shares stored at the cloud data centers or obtained after recovery of the medical information at the authentic entity end which possesses the secret keys. The robustness of the scheme against different attack scenarios while stored at the cloud,,,, data centers in encrypted domain has been tested to validate the efficacy of the proposed scheme.","PeriodicalId":320000,"journal":{"name":"2018 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR)","volume":" 44","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120826951","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: 4

Real-Time Lightweight CNN for Detecting Road Object of Various Size 用于检测各种尺寸道路物体的实时轻量级CNN

2018 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR) Pub Date : 2018-04-10 DOI: 10.1109/MIPR.2018.00044

Byeonghak Lim, Sean Bin Yang, Hakil Kim

引用次数: 6

Client Side Secure Image Deduplication Using DICE Protocol 客户端安全图像重复数据删除使用DICE协议

2018 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR) Pub Date : 2018-04-10 DOI: 10.1109/MIPR.2018.00089

Ashish Agarwala, Priyanka Singh, P. Atrey

{"title":"Client Side Secure Image Deduplication Using DICE Protocol","authors":"Ashish Agarwala, Priyanka Singh, P. Atrey","doi":"10.1109/MIPR.2018.00089","DOIUrl":"https://doi.org/10.1109/MIPR.2018.00089","url":null,"abstract":"With the advent of cloud computing, secured data deduplication has gained a lot of popularity. Many techniques have been proposed in the literature of this ongoing research area. Among these techniques, the Message Locked Encryption (MLE) scheme is often mentioned. Researchers have introduced MLE based protocols which provide secured deduplication of data, where the data is generally in text form. As a result, multimedia data such as images and video, which are larger in size compared to text files, have not been given much attention. Applying secured data deduplication to such data files could significantly reduce the cost and space required for their storage. In this paper we present a secure deduplication scheme for near identical (NI) images using the Dual Integrity Convergent Encryption (DICE) protocol, which is a variant of the MLE based scheme. In the proposed scheme, an image is decomposed into blocks and the DICE protocol is applied on each block separately rather than on the entire image. As a result, the blocks that are common between two or more NI images are stored only once at the cloud. We provide detailed analyses on the theoretical, experimental and security aspects of the proposed scheme.","PeriodicalId":320000,"journal":{"name":"2018 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128161172","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

Personalizing a Generic ECG Heartbeat Classification for Arrhythmia Detection: A Deep Learning Approach 用于心律失常检测的个性化通用心电图心跳分类:一种深度学习方法

2018 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR) Pub Date : 2018-04-10 DOI: 10.1109/MIPR.2018.00024

Meng-Hsi Wu, Emily Chang, Tzu-Hsuan Chu

引用次数: 15

Object-Centric Scene Understanding for Image Memorability Prediction 以对象为中心的场景理解图像记忆预测

2018 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR) Pub Date : 2018-04-10 DOI: 10.1109/MIPR.2018.00070

Sejong Yoon, Jongpil Kim

引用次数: 5

Integrating Visual and Textual Affective Descriptors for Sentiment Analysis of Social Media Posts 整合视觉和文本情感描述符的社交媒体帖子情感分析

2018 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR) Pub Date : 2018-04-10 DOI: 10.1109/MIPR.2018.00011

Shuanglu Dai, H. Man

{"title":"Integrating Visual and Textual Affective Descriptors for Sentiment Analysis of Social Media Posts","authors":"Shuanglu Dai, H. Man","doi":"10.1109/MIPR.2018.00011","DOIUrl":"https://doi.org/10.1109/MIPR.2018.00011","url":null,"abstract":"Social media posts often contain a mixture of images and texts. This paper proposes an affective visual descriptor and an integrated visual-textual classification method for sentiment analysis in social media. Firstly a set of affective visual features is explored based on the theory of psychology and art. Secondly, a structured forest is proposed to generate bag of affective words (BoAW) from the joint distribution of ANP. The generated BoAW provides basic “visual cues” for sentiment analysis. Then a set of sentiment part (SSP) feature is introduced to integrate the visual and textual descriptors on multiple statistic manifolds. Multi-scale sentiment classification is finally applied through metric learning on the manifold kernels. In the proposed method, the re-trained class-activation map (CAM) on ILSVRC 2014 is applied and re-trained on an Adjective-Noun-Pair (ANP) labelled affective visual data set. The global average pooling (GAP) layer of CAM is used for discriminative localization, and the fully-connected layer is able to generate objective visual descriptors. 300 tweets with mixed images and texts are manually labelled and evaluated. The proposed structured forest is evaluated on ANP labelled image data set. Promising experimental results have been obtained, which shows the effectiveness of the proposed method for sentiment analysis on social media posts.","PeriodicalId":320000,"journal":{"name":"2018 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124189278","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