Internet Multimedia Search and Mining


by

Xian-S. Hua, Marcel Worring, Tat-S. Chua

DOI: 10.2174/97816080521581130101
eISBN: 978-1-60805-215-8, 2013
ISBN: 978-1-60805-766-5



Recommend this eBook to your Library



With the explosion of video and image data available on the Internet, desktops and mobile devices, multimedia search has gained immens...[view complete introduction]

Table of Contents

Foreword

- Pp. i-ii (2)

Ramesh Jain

Download Free

Preface

- Pp. iii-v (3)

Xian-Sheng Hua, Marcel Worring and Tat-Seng Chua

Download Free

List of Contributors

- Pp. vi-ix (4)

Xian-Sheng Hua, Marcel Worring and Tat-Seng Chua

Download Free

An Image Decomposition Approach to Large-scale Image Retrieval

- Pp. 3-25 (23)

Xiao Zhang, Zhiwei Li, Lei Zhang, Wei-Ying Ma and Heung-Yeung Shum

View Abstract Purchase Chapter

Near-Duplicate Web Video Detection

- Pp. 26-57 (32)

Xiao Wu, Wan-Lei Zhao, Chong-Wah Ngo and Alexander G. Hauptmann

View Abstract Purchase Chapter

An Efficient Visual Representation and Indexing Scheme for Large Scale Video Retrieval

- Pp. 58-79 (22)

Xiao Zhang, Gang Hua and Lei Zhang

View Abstract Purchase Chapter

Large-Scale Online Multi-Labeled Annotation for Multimedia Search and Mining

- Pp. 80-110 (31)

Guo-Jun Qi and Hong-Jiang Zhang

View Abstract Purchase Chapter

(Un)Tagged Social Image Retrieval

- Pp. 111-129 (19)

Xirong Li, Cees G.M. Snoek and Marcel Worring

View Abstract Purchase Chapter

Adapting Web-based Video Concept Detectors for Different Target Domains

- Pp. 130-167 (38)

Damian Borth, Adrian Ulges and Thomas M. Breuel

View Abstract Purchase Chapter

Social Tag Processing for Internet Images

- Pp. 168-203 (36)

Dong Liu, Xian-Sheng Hua and Hong-Jiang Zhang

View Abstract Purchase Chapter

Flickr Groups: Multimedia Communities for Multimedia Analysis

- Pp. 204-222 (19)

Radu-Andrei Negoescu and Daniel Gatica-Perez

View Abstract Purchase Chapter

Word2Image: A System for Visual Interpretation of Concepts

- Pp. 223-239 (17)

Haojie Li, Jinhui Tang, Guangda Li and Tat-Seng Chua

View Abstract Purchase Chapter

Flickr Distance for Internet Multimedia Search and Mining

- Pp. 240-272 (33)

Lei Wu and Xian-Sheng Hua

View Abstract Purchase Chapter

Geospatial Web Image Mining

- Pp. 273-305 (33)

Dirk Ahlers, Susanne Boll and Philipp Sandhaus

View Abstract Purchase Chapter

Weighted Data Fusion for CBMIR

- Pp. 306-352 (47)

Peter Wilkins and Alan F. Smeaton

View Abstract Purchase Chapter

Cross-modality Indexing, Browsing and Search of Distance Learning Media on the Web

- Pp. 353-366 (14)

Alon Efrat, Arnon Amir, Kobus Barnard and Quanfu Fan

View Abstract Purchase Chapter

Web Music Indexing and Search

- Pp. 367-396 (30)

Lie Lu and Zhiwei Li

View Abstract Purchase Chapter

Video Recommendation

- Pp. 397-414 (18)

Tao Mei and Kiyoharu Aizawa

View Abstract Purchase Chapter

Visual Query Suggestion for Internet Image Search

- Pp. 415-433 (19)

Zheng-Jun Zha, Linjun Yang and Meng Wang

View Abstract Purchase Chapter

Image Search by Color Sketch

- Pp. 434-455 (22)

Jingdong Wang, Yinghai Zhao and Xian-Sheng Hua

View Abstract Purchase Chapter

Index

- Pp. 456-471 (16)

Xian-Sheng Hua, Marcel Worring and Tat-Seng Chua

Download Free

Foreword

Multimedia information started receiving serious attention only about 20 years ago. It was that time that researchers started exploring how to deal with increasing volumes of multimedia document. The rise of search and mining of multimedia information grew in parallel to text search, but was slower in the early stages. In the last decade, it has accelerated to the stage where much of the new information being created is multimedia. Research in search and mining of multimedia contents has been intensifying over the last few years. The need for this technology has become essential, rather than just desirable, due to the volumes and diversity of information being created. Several factors have contributed to this surge in the volume of information and hence urgent need for research in multimedia search and mining. The first factor is the low-cost and widespread use of Internet and intelligent mobile devices. This allows most urban users to access, search and share media contents conveniently at any time and from any location. This gives rise to the second factor which is the popularity of media sharing services and mobile media apps. People are now sharing a huge amount of multimedia contents on the social network sites, though primarily on their personal activities, but increasingly include social events, social commentaries, and informational contents such as the “howto” videos. This offers a huge repository of multimedia and social contents that permits a wide variety of knowledge to be extracted to facilitate better media search, recommendation and social analysis applications. The third factor for the surge in media research is due to the maturity and success of some media technologies for internet applications. This includes media indexing, search, duplicate detection and recommendation techniques, which are adopted in many large-scale public search engines, media social sharing sites and online shopping sites. These partial successes motivated further research in internet media applications.

As a result of the above three factors, active research has gone beyond the traditional areas of media content analysis and search, to the new topics motivated by the emergence of social media and mobile devices. These include research on social media analysis and mining, techniques for Web-scale media indexing and sharing, personalization and recommendations, as well as new user interface and interaction techniques to meet the need of social mobile media applications. These ii works are currently reported in diverse forums, such as the latest conference proceedings and journals, and are not easily accessible and comprehensible to most people. There was an urgent need to bring together this variety of research into a single complied volume.

This is therefore a long awaited eBook that addresses a comprehensive range of modern topics in search and mining of multimedia contents over the internet. It organizes both the traditional as well as social media research topics into a structure suitable for both researchers and practitioners in the field. It will be of great benefits to the community as a useful guide for latest research and practices in this exciting emerging field. To make it useful and authoritative, this collection is edited by three very active researchers in the field who are expert in different aspects of multimedia search and mining. I believe that this eBook will be very useful to researchers in the field to find all relevant information at one place and thus be a strong reference source.

Ramesh Jain
University of California
Irvine USA


Preface

With the explosion of video and image data available on the Internet, desktops, and mobile devices, multimedia search is becoming more and more important. Mining semantics and other useful information from large-scale multimedia data to facilitate online and local multimedia content analysis, search, and related applications is gaining attention from both academia and industry.

On the one hand, the rapid growth of multimedia data brings new challenges to multimedia content analysis and retrieval, especially in terms of scalability. Both computational costs and accuracy are still far from satisfactory. On the other hand, large-scale multimedia data provides new ways to meet these challenges and solve conventional problems in media analysis and computer vision. That is, the massive associated metadata, context, and social information available on the Internet, desktops, and mobile devices, as well as the massive number of grassroots users, are valuable resources that can be leveraged to address the aforementioned difficulties.

Today, researchers are realizing that both the challenges and the opportunities presented by the rapid growth of multimedia content, users, metadata, context, and social information. This eBook brings together high-quality research and recent insights into multimedia search and mining. It focuses on online and social multimedia techniques, systems, and applications in order to advance research and development in this promising area. The eBOOK is organized into five sections with a total of seventeen chapters.

Section I introduces recent research on content-based image and video indexing, and consists of three chapters. In the first chapter, Zhang et al. present an efficient visual indexing technique for large-scale image search, the basic idea of which is to decompose a document-like representation of an image into two components, one for dimension reduction and the other for residual information preservation. In the second, Wu et al. review various approaches to near-duplicate web video detection, including combining global features and local features, integrating content and contextual information, and visual-word based scalable retrieval. Finally, Zhang et al. present recent advancements in web scale video retrieval and discuss two methods for efficient visual representation and efficient visual indexing of web videos.

Section II has four chapters addressing concept and tag based multimedia indexing. The first chapter, by Qi et al. introduces large-scale online active annotation for iv Internet multimedia using the two basic techniques - active learning and online computing, and proposes to combine these two techniques in a unified framework, where scalable multimedia annotation can be achieved in an online manner so that both annotation accuracy and efficiency are able to be significantly improved. Li et al. in the second chapter, tackle two issues in social image indexing, that is, the subjectiveness and the incompleteness of the social tags. The third chapter, authored by Borth et al. introduces visual learning of automatic concept detectors from web video as available from services like YouTube, where domain change problem is addressed and a novel approach, which performs a highly efficient online adaptation on the target domain after an initial training on web content. In the last chapter of this section, Liu et al. present techniques to improve the quality of social tags on social media websites, including filtering, refinement and ranking.

Section III, containing four chapters, discusses data mining from Internet multimedia content. Negoescu et al. present a review of current work that leverages on large online social networks’ meta-information, in particular Flickr Groups, in the first chapter. The second chapter, by Li et al. explores how to leverage the web image collection and knowledge databases to convert a textual word into its visual counterpart with sets of high quality, precise, diverse and representative images. In the third chapter, Wu et al. estimate semantic distance of two textual terms through mining visual content from the Internet, where semantic concepts are modeled based on visual language models. And last, Ahlers et al. introduce techniques for mining location of a web image and mining images of a location.

Section IV mainly addresses search and recommendation problems for Internet multimedia with four chapters. Wilkins et al. present an overview of data fusion and how it can be applied to the internet multimedia search, specifically content-based multimedia search. Efrat et al. introduce cross-modality indexing, browsing and search of distance learning media on the Web. Lu and Li present a music indexing scheme by exploiting and utilizing two data sources: surrounding text of the music on web pages and mete-data describing music attributes. Mei and Aizawa introduce the basic techniques for general recommender systems and specific research for video recommendation.

The last section introduces two novel search interfaces for Internet media. The first chapter, authored by Zha et al. proposes a new query suggestion scheme named visual query suggestion to help users precisely express their search intents by joint text and image suggestions. In the second chapter, Wang et al. present an interactive image search interface, color sketch, which enables users to interactively indicate the search intention, in particular, how the colors are spatially distributed in desired 5 images, by scribbling a few color strokes or dragging an image and highlighting a few regions of interest in an intuitive way.

This eBook is well suited for graduate students and senior researchers working in the field of multimedia search and mining, as well as practitioners, including search engine developers, and multimedia content providers. We hope readers find that this eBook enhances their study of and work in internet multimedia search and mining.

Many exceptional colleagues made a significant impact on the development of this eBook. First of all, we would like to thank all the authors for their irreplaceable contributions to the eBook and their patience for the long process of editing this eBook. We would also like to acknowledge our reviewers for their insightful and valuable comments that improved the quality and readability of the eBook: Kiyoharu Aizawa, Susanne Boll, Daniel Gatica-Perez, Winston Hsu, Gang Hua, Xirong Li, Zhu Li, Wei Liu, Yan Lu, Jiebo Luo, Tao Mei, Chong-Wah Ngo, Shin’ichi Satoh, Nicu Sebe, Jialie Shen, Alan Smeaton, Cees Snoek, Dacheng Tao, Meng Wang, Lei Wu, Xing Xie, Changsheng Xu, Rong Yan, and Lei Zhang. Special thanks to Dr. Kuiyuan Yang, who helped us check and correct all the format issues and integrated all the chapters into the final version.

Finally, we are deeply indebted to each of our family members for their patience and understanding as we were creating this eBook.

Xian-Sheng Hua
Microsoft Research
USA

Marcel Worring
University of Amsterdam
The Netherlands

Tat-Seng Chua
National University of Singapore
Singapore

List of Contributors

Editor(s):
Xian-S. Hua


Marcel Worring


Tat-S. Chua




Contributor(s):
Alexander G. Hauptmann
Carnegie Mellon University
5000 Forbes Avenue
Pittsburgh
PA , 15213
USA


Adrian Ulges
German Research Center for Artificial Intelligence
Gemany


Alan F. Smeaton
Centre for Sensor Web Technologies
Dublin City University
Ireland


Alon Efrat
The University of Arizona
Tucson
AZ , 85721
USA


Arnon Amir
IBM Almaden Research Center
San Jose
CA , 95120
USA


Chong-Wah Ngo
City University of Hong Kong
Hong Kong


Cees G.M. Snoek
University of Amsterdam
The Netherlands


Damian Borth
University of Kaiserslautern & German Research Center for Artificial Intelligence
Germany


Dong Liu
Department of Electrical Engineering
Columbia University
New York
NY , 10027
USA


Daniel Gatica-Perez
Idiap Research Institute and Ecole Polytechnique Fédérale de Lausanne
Switzerland


Dirk Ahlers
NTNU - Norwegian University of Science and Technology
Trondheim
Norway


Gang Hua
Stevens Institute of Technology
Hoboken
NJ , 07030-5991
USA


Guo-Jun Qi
Beckman Institute, University of Illinois at Urbana-Champaign
Urbana
IL , 61801
USA


Guangda Li
School of Computing, National University of Singapore
Singapore


Heung-Yeung Shum
Microsoft Research Asia
Beijing
China


Hong-Jiang Zhang
Microsoft Advanced Technology Center
Beijing
China


Haojie Li
School of Software, Dalian University of Technology
Liaoning
China


Jinhui Tang
School of Computer Science, Nanjing University of Science and Technology
Nanjing
China


Jingdong Wang
Microsoft Research Asia
Beijing
China


Kobus Barnard
The University of Arizon
Tucson
AZ , 85721
USA


Kiyoharu Aizawa
University of Tokyo
Tokyo
Japan


Lei Zhang
Microsoft Research Asia
Beijing
China


Lei Wu
University of Pittsbugh
PA , 15213
USA


Lie Lu
Dolby Laboratories
Beijing
China


Linjun Yang
Microsoft Research Asia
Beijing
China


Marcel Worring
University of Amsterdam
The Netherlands


Meng Wang
Hefei University of Technology
Anhui
China


Philipp Sandhaus
CEWE Color AG & Co. OHG
Oldenburg
Germany


Peter Wilkins
Centre for Sensor Web Technologies
Dublin City University
Ireland


Quanfu Fan
Exploratory Computer Vision Group
Thomas J. Watson Research Center
Hawthorne
NY , 10532
USA


Radu-Andrei Negoescu
Idiap Research Institute and Ecole Polytechnique Fédérale de Lausanne
Swizerland


Susanne Boll
University of Oldenburg
Oldenberg
Germany


Tat-Seng Chua
National University of Singapore
Singapore


Thomas M. Breuel
University of Kaiserslautern
Germany


Tao Mei
Microsoft Research Asia
Beijing
China


Wei-Ying Ma
Microsoft Research Asia
Beijing
China


Wan-Lei Zhao
City University of Hong Kong
Hong Kong


Xian-Sheng Hua
Microsoft Research Asia
Beijing
China


Xiao Wu
Southwest Jiaotong University, Chengdu
Sichuan
China


Xiao Zhang
Institute for Advanced Study, Tsinghua University
Beijing
China


Xirong Li
Renmin University of China
Beijing
China


Yinghai Zhao
University of Science and Technology of China
Hefei
China


Zhiwei Li
Microsoft Research Asia
Beijing
China


Zheng-Jun Zha
Institute of Intelligent Machines, Chinese Academy of Science
Hefei
China




Advertisement


Related Journals



Related Books



Webmaster Contact: urooj@benthamscience.org Copyright © 2016 Bentham Science