2014 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)最新文献_第4页

Image annotation via social diffusion analysis with common interests 基于共同利益的社会扩散分析的图像标注

2014 IEEE International Conference on Multimedia and Expo Workshops (ICMEW) Pub Date : 2014-07-14 DOI: 10.1109/ICMEW.2014.6890535

Chenyi Lei, Dong Liu

{"title":"Image annotation via social diffusion analysis with common interests","authors":"Chenyi Lei, Dong Liu","doi":"10.1109/ICMEW.2014.6890535","DOIUrl":"https://doi.org/10.1109/ICMEW.2014.6890535","url":null,"abstract":"Automatic annotation of images is of crucial importance in image retrieval and management systems. Most of the existing annotation methods rely on content-based approach to annotation, whose effectiveness is restricted due to the semantic gap between low-level features and semantic annotations, as well as the irrelevance between annotations and image content. Recently, social media analysis has been investigated for image annotation. Inspired by the abundant social diffusion records of images in online social networks, we propose a novel image annotation approach based on social diffusion analysis. We present a common-interest model to interpret social diffusion, i.e. different images have different social diffusion routes due to the preferences of users, and such preferences are represented as common interests of pairwise users rather than personalized interests. We propose an image annotation framework that consists of learning of common interests, feature extraction from social diffusion records, and automatic annotation by learning to rank. Experimental results on a real-world dataset show that our proposed approach outperforms content-based and user-preference-based annotation methods.","PeriodicalId":178700,"journal":{"name":"2014 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124649885","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

Using image signature for effective and efficient reduced-reference image quality assessment 使用图像签名进行有效和高效的低参考图像质量评估

2014 IEEE International Conference on Multimedia and Expo Workshops (ICMEW) Pub Date : 2014-07-14 DOI: 10.1109/ICMEW.2014.6890666

Min Liu, Guangtao Zhai, Zhili Zhang, Shen Tan, Ke Gu, Xiaokang Yang

引用次数: 1

Information systems and management in media industries a first problem evaluation from a business perspective 从商业角度对媒体行业的信息系统和管理进行第一问题评估

2014 IEEE International Conference on Multimedia and Expo Workshops (ICMEW) Pub Date : 2014-07-14 DOI: 10.1109/ICMEW.2014.6890680

Christoph Scheib, A. Lugmayr

{"title":"Information systems and management in media industries a first problem evaluation from a business perspective","authors":"Christoph Scheib, A. Lugmayr","doi":"10.1109/ICMEW.2014.6890680","DOIUrl":"https://doi.org/10.1109/ICMEW.2014.6890680","url":null,"abstract":"Media industry is undergoing a very intensive transformation from traditional Media towards fully digital media environments. Within that market space, the environment as well as consumer behavior is changing very rapidly. In particular inside media houses various changes are taking place. One of these changes is the introduction or improvement of IT infrastructure to support business activities - in short, introducing or improving information systems and management in eMedia and creativity industry. In view a focus on advanced information management has a vital role of having a major impact in creating competitive advantage in media companies. In this respect, one of the biggest challenges is how to efficiently manage the ever changing massive amount of mostly unstructured and diverse data. This data consists of traditional business information (e.g. Customer Relationship Management (CRM), Supplier Relationship Management (SRM), Financial Supply Chain Management (FSCM)), information directly related to media content (e.g. media information, metadata, content information), as well as consumer data (e.g. social media, customer databases). Traditional media companies will need to invest in latest IT technology which is able to manage flexibly, quickly and efficiently the large amounts of structured and unstructured data. On the other hand the challenge is to deliver structured data in form of business intelligence throughout the organizational levels, between business partners, and the complete media eco-system. Within the scope of this paper we present a first problem definition of information systems and management in eMedia industries.","PeriodicalId":178700,"journal":{"name":"2014 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128615876","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

DRM-interoperable MPEG-dash end-to-end architecture 可drm互操作的MPEG-dash端到端架构

2014 IEEE International Conference on Multimedia and Expo Workshops (ICMEW) Pub Date : 2014-07-14 DOI: 10.1109/ICMEW.2014.6890615

Stefan Kaiser, S. Pham

引用次数: 2

Towards integrity protection of software for e-health data 迈向电子医疗数据软件的完整性保护

2014 IEEE International Conference on Multimedia and Expo Workshops (ICMEW) Pub Date : 2014-07-14 DOI: 10.1109/ICMEW.2014.6890681

S. Rahman

{"title":"Towards integrity protection of software for e-health data","authors":"S. Rahman","doi":"10.1109/ICMEW.2014.6890681","DOIUrl":"https://doi.org/10.1109/ICMEW.2014.6890681","url":null,"abstract":"The Integrity protection (IP) of software which deals with eHealth data, addresses the problem of static or dynamic code modification of the software. An attacker with the ability to modify the execution of software which deals with eHealth data can tamper with eHealth data. The target of IP is to protect the software assets; in this case it is to protect eHealth data. By modifying the binary source of an application, an attacker can produce a modified version of the application which can run in favor of the attacker objectives. Finally, if an attacker distributes the modified version of an application which deals with eHealth data, can harm eHealth environment (e.g., government agency) by disclosing the identity of the stake holders. The existing literatures (very few are disclosed and are available in academia) mainly focus on protection of tampering for static code of a software application. However, in practically, while an instance of software runs on unprotected memory environment, an attacker can launch dynamic modification of the running code and achieves the desired advantages. Therefore, the existing approaches do not tackle the tampering issues during the execution of a software application. The proposed research aims to explore this problem and proposes solutions based on a light-weight cryptographic methodology by generating secure cryptographic signature, which is a scrambled signature of a software application generated using cryptographic function and its security analysis has been investigated.","PeriodicalId":178700,"journal":{"name":"2014 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)","volume":"42 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129934488","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

Prediction unit depth selection based on statistic distribution for HEVC intra coding 基于统计分布的HEVC编码预测单元深度选择

2014 IEEE International Conference on Multimedia and Expo Workshops (ICMEW) Pub Date : 2014-07-14 DOI: 10.1109/ICMEW.2014.6890719

Xue Li, Xiaoyun Zhang, Yunyu Shi, Zhiyong Gao

{"title":"Prediction unit depth selection based on statistic distribution for HEVC intra coding","authors":"Xue Li, Xiaoyun Zhang, Yunyu Shi, Zhiyong Gao","doi":"10.1109/ICMEW.2014.6890719","DOIUrl":"https://doi.org/10.1109/ICMEW.2014.6890719","url":null,"abstract":"The new video coding standard, HEVC, achieves better compression performance relative to H.264 at the expense of a significant increase in computational complexity. It adopts coding tree structure, and implements partition and mode decision for each coding unit (CU) and prediction unit (PU). For intra coding, five levels of PUs from 64×64 to 4×4 should be searched and each PU selects one best mode from 35 candidate modes, which is very computation intensive. Therefore, reducing the number of levels for PUs, i.e., PU depth selection, is an efficient way to decrease intra coding complexity. In this paper, we fully investigate the relationship between the variances of different sizes of pixel blocks and the best partition of PUs. It is shown that 90th percentile of the variances distribution can be used to distinguish large PUs and small PUs. Furthermore, 16×16 PU search can be disabled for smooth area when variances of 64×64 pixel blocks are smaller than the 90th percentile of variances distribution of 64×64 PUs and this 90th percentile is smaller than an absolute threshold. Meanwhile, further split can be disabled if the variance of the current PU is smaller than 70th percentile of the variances of its parent-level PUs when the current PU is 16×16 or 8×8. The experimental results show that the proposed algorithm can reduce 55% encoding time of reference encoder HM10.0 at all Intra setting on average with negligible coding performance loss less than 1.22% BD-Rate for HD or Ultra-HD videos.","PeriodicalId":178700,"journal":{"name":"2014 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128880301","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: 8

Buffer status and content aware scheduling scheme for cloud gaming based on video streaming 基于视频流的云游戏缓冲状态和内容感知调度方案

2014 IEEE International Conference on Multimedia and Expo Workshops (ICMEW) Pub Date : 2014-07-14 DOI: 10.1109/ICMEW.2014.6890629

Lijun He, Guizhong Liu, Yuchen Chen

引用次数: 6

On a 10-bit coding profile for AVS2 standard 在AVS2标准的10位编码配置文件上

2014 IEEE International Conference on Multimedia and Expo Workshops (ICMEW) Pub Date : 2014-07-14 DOI: 10.1109/ICMEW.2014.6890699

Yinqing Zhao, Weimin Zeng, Eric Chai, Xiaozhen Zheng, Jianhua Zheng

引用次数: 1

Proportional fair resource allocation algorithm for video transmission in ofdma system ofdma系统中视频传输的比例公平资源分配算法

2014 IEEE International Conference on Multimedia and Expo Workshops (ICMEW) Pub Date : 2014-07-14 DOI: 10.1109/ICMEW.2014.6890724

Yimin Zhang, Guizhong Liu, Qinli Wang, Lijun He

引用次数: 2

Sequence-based bias analysis of spontaneous facial expression databases 基于序列的自发面部表情数据库偏差分析

2014 IEEE International Conference on Multimedia and Expo Workshops (ICMEW) Pub Date : 2014-07-14 DOI: 10.1109/ICMEW.2014.6890646

Zhaoyu Wang, Jun Wang, Shangfei Wang, Q. Ji

引用次数: 0