2014 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)最新文献_第7页

Chebyshev and conjugate gradient filters for graph image denoising 图图像去噪的切比雪夫和共轭梯度滤波器

2014 IEEE International Conference on Multimedia and Expo Workshops (ICMEW) Pub Date : 2014-07-14 DOI: 10.1109/ICMEW.2014.6890711

Dong Tian, H. Mansour, A. Knyazev, A. Vetro

引用次数: 22

Interactive body part contrast mining for human interaction recognition 面向人机交互识别的交互式身体部位对比挖掘

2014 IEEE International Conference on Multimedia and Expo Workshops (ICMEW) Pub Date : 2014-07-14 DOI: 10.1109/ICMEW.2014.6890714

Yanli Ji, Guo Ye, Hong Cheng

{"title":"Interactive body part contrast mining for human interaction recognition","authors":"Yanli Ji, Guo Ye, Hong Cheng","doi":"10.1109/ICMEW.2014.6890714","DOIUrl":"https://doi.org/10.1109/ICMEW.2014.6890714","url":null,"abstract":"The recognition of multi-person interactions still remains a challenge because of the mutual occlusion and redundant poses. We propose an interactive body part contrast mining method based on joints for human interaction recognition. To efficiently describe interactions, we propose an interactive body part model which connects the interactive limbs of different participants to represent the relationship of interactive body parts. Then we calculate the spatial-temporal joint features for 8 interactive limb pairs in a short frame set for motion description (poselets). Employing contrast mining, we determine the essential interactive pairs and poselets for each interaction class to delete the redundant action information, and use these poselets to generate a poselet dictionary for interaction representation following bag-of-words. SVM with RBF kernel is adopted for recognition. We evaluate the proposed algorithm on two databases, the SBU interaction database and a newly collected RGBD-skeleton interaction database. Experiment results indicate the effectiveness of the proposed algorithm. The recognition accuracy reaches 85.4% on our interaction database, and 86.8% on SBU interaction database, 6% higher than the method in [1].","PeriodicalId":178700,"journal":{"name":"2014 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)","volume":"86 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":"132373347","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: 125

Smart authoring and sharing of multimedia content in personal area networks based on Subject of Interest 基于兴趣主题的个人局域网多媒体内容智能创作与共享

2014 IEEE International Conference on Multimedia and Expo Workshops (ICMEW) Pub Date : 2014-07-14 DOI: 10.1109/ICMEW.2014.6890603

Belal Abu-Naim, W. Klas

{"title":"Smart authoring and sharing of multimedia content in personal area networks based on Subject of Interest","authors":"Belal Abu-Naim, W. Klas","doi":"10.1109/ICMEW.2014.6890603","DOIUrl":"https://doi.org/10.1109/ICMEW.2014.6890603","url":null,"abstract":"The evolution of smart phones' hardware and operating systems, users tendency to join social networks and to share multimedia content and daily life events, well-established methods and technologies of Semantic web, and the increasing establishment of Linked Open Data (LOD) APIs, motivate us to introduce a new approach in multimedia content composition and sharing in personal area networks that automatically analyzes, selects, composes, and shares the authored content. The capabilities of social network applications and the applications that address multimedia document composition, retrieval and presentation, and multimedia content sharing, do not go beyond allowing the users to share text, pictures, or other types of media content in social networks, performing manual or semi-automatic multimedia document composition, retrieving a list of pre-composed multimedia documents that eventually include datasets retrieved from DBpedia based on the geographic location. There is a lack of applications that are capable to automatically analyze the multimedia content on the devices of the users, compose multimedia documents about the Subject of Interest (SOI), retrieve and use additional data from LOD sources, and achieve a cross-multimedia document models authoring. In this paper we introduce our innovative approach of automatic analysis, composition, and sharing of multimedia content driven by a user's subject of interest (SOI). Our new approach enables us to achieve a smart multimedia authoring and sharing by incorporating new phases within the authoring process, which have not yet been applied by other applications.","PeriodicalId":178700,"journal":{"name":"2014 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)","volume":"433 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":"132864273","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

Butterfly-like D-tree fusion strategy for real-time speech and music classification 实时语音和音乐分类的类蝴蝶d树融合策略

2014 IEEE International Conference on Multimedia and Expo Workshops (ICMEW) Pub Date : 2014-07-14 DOI: 10.1109/ICMEW.2014.6890706

Min Lu, W. Dou

引用次数: 2

Two dimensional non-negative sparse Partial Least Squares for face recognition 二维非负稀疏偏最小二乘人脸识别

2014 IEEE International Conference on Multimedia and Expo Workshops (ICMEW) Pub Date : 2014-07-14 DOI: 10.1109/ICMEW.2014.6890696

Yongxin Ge, Sheng Huang, Xin Feng, Jiehui Zhang, Wenbin Bu, Dan Yang

引用次数: 1

Visualization of user interests in online music services 可视化用户对在线音乐服务的兴趣

2014 IEEE International Conference on Multimedia and Expo Workshops (ICMEW) Pub Date : 2014-07-14 DOI: 10.1109/ICMEW.2014.6890536

Jingxian Zhang, Dong Liu

引用次数: 4

A panoramic video system by direct manipulation video navigation 一个通过直接操作视频导航的全景视频系统

2014 IEEE International Conference on Multimedia and Expo Workshops (ICMEW) Pub Date : 2014-07-14 DOI: 10.1109/ICMEW.2014.6890611

Chi-Cheng Ju, Ding-Yun Chen, Chen-Tsai Ho, Chung-Hung Tsai

引用次数: 0

Recognition by detection: Perceiving human motion through part-configured feature maps 通过检测识别:通过部分配置的特征映射来感知人体运动

2014 IEEE International Conference on Multimedia and Expo Workshops (ICMEW) Pub Date : 2014-07-14 DOI: 10.1109/ICMEW.2014.6890599

Lei Wang, Jun Wu, Zhimin Zhou, Yuncai Liu, Xu Zhao

引用次数: 1

Online video session progress prediction using low-rank matrix completion 使用低秩矩阵补全的在线视频会话进度预测

2014 IEEE International Conference on Multimedia and Expo Workshops (ICMEW) Pub Date : 2014-07-14 DOI: 10.1109/ICMEW.2014.6890668

Gang Wu, Viswanathan Swaminathan, Saayan Mitra, Ratnesh Kumar

{"title":"Online video session progress prediction using low-rank matrix completion","authors":"Gang Wu, Viswanathan Swaminathan, Saayan Mitra, Ratnesh Kumar","doi":"10.1109/ICMEW.2014.6890668","DOIUrl":"https://doi.org/10.1109/ICMEW.2014.6890668","url":null,"abstract":"The prediction of online video session progress is useful for both optimizing and personalizing end-user experience. Our approach for online video recommendation is to use the session progress information instead of using a traditional rating system. We approach the prediction of session progress as a matrix completion problem, and complete the session progress matrix using noisy low-rank matrix completion (NLMC). Events collected from the end-user video sessions are tracked and logged in a server. We process a large number of logs, represent them as a partially observed user by video matrix, and use regularized nuclear norm minimization for matrix completion. Our initial results show improvement over baseline methods of prediction using just the means. We further investigate the reason for the difference in performance for the same prediction methods between our dataset and the dataset used in the Netflix challenge. Our experiments indicate that the number of observed entries at a given sparsity is a good indicator of the performance of the Singular Value Decomposition (SVD) based matrix completion methods. This implies that the results for our dataset would further improve by either observing more entries for the same set of users and videos or by including new users or videos at the same sparsity level. Moreover, we introduce an algorithm to generate submatrices of any required sparsity and size from a given matrix to fairly compare algorithm performances on datasets of varying characteristics.","PeriodicalId":178700,"journal":{"name":"2014 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)","volume":"104 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":"115759931","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: 7

Efficient image reranking by leveraging click data 有效的图像重新排序利用点击数据

2014 IEEE International Conference on Multimedia and Expo Workshops (ICMEW) Pub Date : 2014-07-14 DOI: 10.1109/ICMEW.2014.6890605

Shusheng Cen, Lezi Wang, Yanchao Feng, Hongliang Bai, Yuan Dong

引用次数: 5