2015 IEEE International Conference on Multimedia Big Data

20-22 April 2015

Filter Results

Displaying Results 1 - 25 of 94
  • [Front cover]

    Publication Year: 2015, Page(s): C4
    Request permission for commercial reuse | PDF file iconPDF (1173 KB)
    Freely Available from IEEE
  • [Title page i]

    Publication Year: 2015, Page(s): i
    Request permission for commercial reuse | PDF file iconPDF (99 KB)
    Freely Available from IEEE
  • [Title page iii]

    Publication Year: 2015, Page(s): iii
    Request permission for commercial reuse | PDF file iconPDF (248 KB)
    Freely Available from IEEE
  • [Copyright notice]

    Publication Year: 2015, Page(s): iv
    Request permission for commercial reuse | PDF file iconPDF (231 KB)
    Freely Available from IEEE
  • Table of contents

    Publication Year: 2015, Page(s):v - xi
    Request permission for commercial reuse | PDF file iconPDF (149 KB)
    Freely Available from IEEE
  • Message from General Chairs

    Publication Year: 2015, Page(s): xii
    Request permission for commercial reuse | PDF file iconPDF (219 KB) | HTML iconHTML
    Freely Available from IEEE
  • Message from Program Chairs

    Publication Year: 2015, Page(s): xiii
    Request permission for commercial reuse | PDF file iconPDF (216 KB) | HTML iconHTML
    Freely Available from IEEE
  • Conference Organization

    Publication Year: 2015, Page(s):xiv - xvi
    Request permission for commercial reuse | PDF file iconPDF (195 KB)
    Freely Available from IEEE
  • Technical Program Committee

    Publication Year: 2015, Page(s):xvii - xix
    Request permission for commercial reuse | PDF file iconPDF (195 KB)
    Freely Available from IEEE
  • Reviewers

    Publication Year: 2015, Page(s):xx - xxi
    Request permission for commercial reuse | PDF file iconPDF (182 KB)
    Freely Available from IEEE
  • Fuelling Big Data Intelligence into Future Multimedia System: Reflection and Outlook

    Publication Year: 2015, Page(s):1 - 4
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (246 KB) | HTML iconHTML

    The last decade has witnessed an explosive growth in multimedia big data, with the invention of big data analytics technologies, such as Hadoop, Spark, Storm. All these technologies are valuable to mine intelligence from multimedia big data, and further shed new insights into multimedia networks. This paper presents an outlook on the development of future multimedia networks and discuss utilizing ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • On Analyzing the 'Variety' of Big Social Multimedia

    Publication Year: 2015, Page(s):5 - 8
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (308 KB) | HTML iconHTML

    Social media contributes significantly to the arrival of the Big Data era. It is interesting to re-examine "multimedia" in the context of social media. This positioning paper proposes to analyzing into Variety of big social multimedia from the perspective of various sources, which is the study of heterogeneous data generated and consumed in various social media networks that receives little attent... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • RAISE: A Whole Process Modeling Method for Unstructured Data Management

    Publication Year: 2015, Page(s):9 - 12
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (750 KB) | HTML iconHTML

    Nowadays, unstructured data, e.g., texts, images, and videos, is growing in an explosive speed with the development of Internet and social network. Due to the variety of unstructured data, it is strongly desirable to design a generalized model to represent all kinds of unstructured data and build a system to organize them effectively. In this paper, we first define a generalized data model to repr... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Categorizing Big Video Data on the Web: Challenges and Opportunities

    Publication Year: 2015, Page(s):13 - 15
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (125 KB) | HTML iconHTML

    Video categorization is a very important problem with many applications like content search and organization, smart content-aware advertising, open-source intelligence analysis, etc. This paper discusses selected representative research progresses in categorizing big video data, with a focus on the user-generated videos on the Internet. We identify two major challenges in this vibrant field and en... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Prospects and Challenges of Deep Understanding Social Users and Urban Services - A Position Paper

    Publication Year: 2015, Page(s):16 - 19
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (520 KB) | HTML iconHTML

    With the boom of social media, it is a very popular trend for people to share their consumption experiences and rate the items on the review site. Users can share their experiences, reviews, ratings, photos, check-ins, moods, and so on. The information they shared is valuable for new users to judge whether the items have high-quality services. Nowadays, many researchers focus on personalized recom... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Multimedia Analysis with Deep Learning

    Publication Year: 2015, Page(s):20 - 23
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (151 KB) | HTML iconHTML

    Recently, deep learning method has been attracting more and more researchers due to its great success in various computer vision tasks. Particularly, some researchers focus on the study of multimedia analysis by deep learning method, and the research tasks mainly include the following six aspects: classification, retrieval, segmentation, tracking, detection and recommendation. As far as we know, t... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Structure-Based Learning in Sampling, Representation and Analysis for Multimedia Big Data

    Publication Year: 2015, Page(s):24 - 27
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (179 KB) | HTML iconHTML

    This paper presents disruptive insights and techniques on structure-based learning for multimedia big data. Along this viewpoint, significant technical challenges for multimedia big data are investigated, including sampling and reconstruction, representation, and analysis. For multi-dimensional compressive sampling, the union of data-driven subspace is addressed via subspace learning with structur... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Cross-Modality Sentiment Analysis for Social Multimedia

    Publication Year: 2015, Page(s):28 - 31
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (592 KB)

    Sentiment analysis is important for understanding the social media contents and user opinions. Along with the development of social media applications, an increasing number of people combine texts and images to express their opinions. However, text based sentiment analysis methods cannot process other medias except texts. Therefore, visual sentiment analysis is born at the right moment. In this ar... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Semi-supervised Multimodal Clustering Algorithm Integrating Label Signals for Social Event Detection

    Publication Year: 2015, Page(s):32 - 39
    Cited by:  Papers (2)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (485 KB) | HTML iconHTML

    Photo-sharing social media sites provide new ways for users to share their experiences and interests on the Web, which aggregate large amounts of multimedia resources associated with a wide variety of real-world events in different types and scales. In this work, we aim to tackle social event detection from these large amounts of image collections by devising a semi-supervised multimodal clusterin... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Constructing Social Networks Based on Near-Duplicate Detection in YouTube Videos

    Publication Year: 2015, Page(s):40 - 47
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (850 KB) | HTML iconHTML

    With the video-sharing websites springing up, more and more people would like to upload and share either their own videos or remix others'. Meanwhile, they could view and comment the videos that they are interested in. Therefore, social networks among videos and users exist implicitly. In this work, we construct two types of social networks, video networks (VN) and topic participant networks (TPN)... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Food Category Representatives: Extracting Categories from Meal Names in Food Recordings and Recipe Data

    Publication Year: 2015, Page(s):48 - 55
    Cited by:  Papers (6)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1277 KB) | HTML iconHTML

    Food Log is a multimedia recording tool for producing food records for many individuals. In one year of operation, Food Log has produced more than one million food records for meals eaten by users. We found nearly 70,000 unique food records among these data. In analyzing them, one of the challenges is to extract meal categories from such a large number of records. In this paper, we propose a metho... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Predicting Retweet Scale Using Log-Normal Distribution

    Publication Year: 2015, Page(s):56 - 63
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (248 KB) | HTML iconHTML

    In social network analysis, retweet scale prediction is one important studying focus. Generally speaking, there are two different approaches to predict the retweet scale: time-series approach and non-time-series approach. In this paper, we conduct a research on the distribution of the reaction time in retweeting activity and introduce a time-series prediction model. We show that in retweeting acti... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Temporal Multiple Correspondence Analysis for Big Data Mining in Soccer Videos

    Publication Year: 2015, Page(s):64 - 71
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (938 KB) | HTML iconHTML

    A multimedia big data mining framework consisting of two phases for interesting event detection in soccer videos has been proposed in this paper. In the pre-processing phase, it utilizes the multi-modal multi-filtering content analysis techniques for shot boundary detection and feature extraction. A pre-filtering process based on domain knowledge analysis is then applied to clean the noise and obt... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Utilizing Indirect Associations in Multimedia Semantic Retrieval

    Publication Year: 2015, Page(s):72 - 79
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (706 KB) | HTML iconHTML

    Technological developments have lead to the propagation of massive amounts of data in the form of text, image, audio, and video. The unstoppable trend draws researchers' attention to develop approaches to efficiently retrieve and manage multimedia data. The inadequacy of keyword-based search in multimedia data retrieval due to non-existent or incomplete text annotations has called for the developm... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Multi2Rank: Multimedia Multiview Ranking

    Publication Year: 2015, Page(s):80 - 87
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (492 KB) | HTML iconHTML

    Multimedia retrieval is a search and ranking task defined over multiple modalities. These modalities include speech, image, and text, which provide different views of the multimedia object. Queries to a multimedia retrieval system often take the form of a text only query and return a ranked result set which combines these multiple views. The text only query includes multiple phrases which identify... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.