The advent of increasingly large consumer collections of audio (e.g., iTunes), imagery (e.g., Flickr), and video (e.g., YouTube) is driving a need not only for multimedia retrieval but also information extraction from and across media. Furthermore, industrial and government collections fuel requirements for stock media access, media preservation, broadcast news retrieval, identity management, and video surveillance. While significant advances have been made in language processing for information extraction from unstructured multilingual text and extraction of objects from imagery and video, these advances have been explored in largely independent research communities who have addressed extracting information from single media (e.g., text, imagery, audio). And yet users need to search for concepts across individual media, author multimedia artifacts, and perform multimedia analysis in many domains.

This collection is intended to serve several purposes, including reporting the current state of the art, stimulating novel research, and encouraging cross-fertilization of distinct research disciplines. The collection and integration of a common base of intellectual material will provide an invaluable service from which to teach a future generation of cross disciplinary media scientists and engineers.

[From the Back Cover]

The definitive guide to the state of the art of multimedia information extraction

Government analysts, think tank researchers, managers at top websites--basically everyone--is searching for the best ways to access and exploit the vast amounts of multimedia data made available over large networks every day. Written by an international team of experts, Multimedia Information Extraction provides a detailed road map to how that's done.

The first book to address not only multimedia retrieval but also information extraction from and across media, it offers diverse perspectives on how this emerging technology can help meet the growing demand in industry and government for stock media access, media preservation, broadcast news retrieval, identity management, video surveillance, and more.

Including a Foreword by Professor Alan Smeaton, founding coordinator of the international TRECVid, Multimedia Information Extraction covers:

• The fundamental issues in processing and multimedia source extraction

• The history and state of the art of multimedia information extraction

• Image and video extraction, with tools ranging from visual feature localization to social redundancy

• Affect extraction in audio and imagery, from paralinguistic information retrieval to affect-based indexing

• Multimedia annotation and authoring

An inspiring, much-needed resource for researchers and developers in government, industry, and academia, this book also offers guidance on using the material in the core curriculum of ACM SIGCHI, ACM/IEEE Computer Science, and ACM/IEEE Information Technology.

About the Author

MARK T. MAYBURY, PhD, is an Executive Director at MITRE, a federally funded research and development center. In 2010, Dr. Maybury took a leave of absence from MITRE when appointed to the role of Chief Scientist of the United States Air Force. He is a former member of the board of directors of the Object Management Group and the Air Force Scientific Advisory Board. An IEEE Fellow, Dr. Maybury is a member of the ACM Intelligent User Interface Steering Committee and has served on the Advanced Visual Interfaces Program Committee for over ten years. He holds several patents and has edited, coedited, or coauthored a number of books on information retrieval and related topics.

越来越大的消费者音频（如iTunes）、图像（如Flickr）和视频（如YouTube）集合的出现，不仅推动了对多媒体检索的需求，也推动了从媒体和跨媒体的信息提取。此外，工业和政府收藏品也推动了对库存媒体访问、媒体保存、广播新闻检索、身份管理和视频监控的需求。虽然在从非结构化的多语言文本中提取信息的语言处理以及从图像和视频中提取物体方面已经取得了重大进展，但这些进展在很大程度上是由独立的研究团体探索的，他们解决的是从单一媒体（如文本、图像、音频）中提取信息的问题。然而，用户需要在单个媒体上搜索概念，编写多媒体作品，并在许多领域进行多媒体分析。

这个集合的目的有几个，包括报告当前的技术水平，刺激新的研究，并鼓励不同研究学科的交叉融合。收集和整合共同的知识材料基础将提供一个宝贵的服务，用来教导未来一代跨学科的媒体科学家和工程师。

[来自封底的消息］

多媒体信息提取技术现状的权威指南

政府分析人员、智囊团研究人员、顶级网站的管理人员--基本上每个人都在寻找获取和利用每天通过大型网络提供的大量多媒体数据的最佳方法。由一个国际专家小组撰写的《多媒体信息提取》为如何做到这一点提供了一个详细的路线图。

作为第一本不仅涉及多媒体检索，而且涉及从媒体和跨媒体提取信息的书，它提供了关于这一新兴技术如何帮助满足工业和政府对库存媒体访问、媒体保存、广播新闻检索、身份管理、视频监控等日益增长的需求的不同观点。

包括国际TRECVid的创始协调人Alan Smeaton教授的前言，多媒体信息提取涵盖。

- 处理和多媒体源提取中的基本问题

- 多媒体信息提取的历史和技术现状

- 图像和视频提取，包括从视觉特征定位到社会冗余的工具

- 音频和图像中的情感提取，从副语言学信息检索到基于情感的索引

- 多媒体注释和创作

本书是政府、工业界和学术界的研究人员和开发人员的一个鼓舞人心的、急需的资源，本书还为ACM SIGCHI、ACM/IEEE计算机科学和ACM/IEEE信息技术的核心课程中使用这些材料提供指导。

关于作者

MARK T. MAYBURY博士是MITRE的执行董事，MITRE是一个由联邦政府资助的研究和发展中心。2010年，梅伯里博士被任命为美国空军的首席科学家时，向MITRE请了假。他是对象管理集团董事会和空军科学顾问委员会的前成员。作为一名IEEE会员，梅伯里博士是ACM智能用户界面指导委员会的成员，并在高级视觉界面项目委员会任职超过10年。他拥有多项专利，并编辑、共同编辑或共同撰写了许多关于信息检索和相关主题的书籍。