TY - CHAP
T1 - A Unified Framework for Video Summarization, Browsing, and Retrieval
AU - Xiong, Ziyou
AU - Rui, Yong
AU - Radhakrishnan, Regunathan
AU - Divakaran, Ajay
AU - Huang, Thomas S.
N1 - Funding Information:
Part of this work (Rui and Huang) was supported in part by ARL Cooperative Agreement No. DAAL01-96-2-0003, and in part by a CSE Fellowship, College of Engineering, UIUC. The authors (Xiong, Radhakrishnan and Divakaran) would like to thank Dr. Mike Jones of MERL for his help in visual marker detection. They also would like to thank Mr. Kohtaro Asai of Mitsubishi Electric Corporation (MELCO), Japan for his support and encouragement and Mr. Isao Otsuka of MELCO, for his valuable application-oriented comments and suggestions. The authors (Rui and Huang) would like to thank Sean X. Zhou, Atulya Velivelli, and Roy R. Wang for their contribution.
PY - 2005
Y1 - 2005
N2 - This chapter presents techniques for constructing the video "table of contents" (ToC), video highlights, and video index as well as the ways to integrate them into a unified framework. It reviews video analysis, representation, summarization, and retrieval. Further, a unified framework for video summarization and retrieval is described, followed by algorithms and experimental results on real-world video clips. Video content can be accessed by using either a top-down approach or a bottom-up approach. The top-down approach-that is, video browsing-is useful when one needs to get an "essence" of the content. The bottom-up approach-that is, video retrieval-is useful when one knows exactly what is needed from the content. In video summarization, the "essence" a summary should capture depends on whether or not the content is scripted. Because scripted content, such as news, drama, and movies, is carefully structured as a sequence of semantic units, one can get its essence by enabling a traversal through representative items from these semantic units. Hence, ToC-based video browsing caters to summarization of scripted content.
AB - This chapter presents techniques for constructing the video "table of contents" (ToC), video highlights, and video index as well as the ways to integrate them into a unified framework. It reviews video analysis, representation, summarization, and retrieval. Further, a unified framework for video summarization and retrieval is described, followed by algorithms and experimental results on real-world video clips. Video content can be accessed by using either a top-down approach or a bottom-up approach. The top-down approach-that is, video browsing-is useful when one needs to get an "essence" of the content. The bottom-up approach-that is, video retrieval-is useful when one knows exactly what is needed from the content. In video summarization, the "essence" a summary should capture depends on whether or not the content is scripted. Because scripted content, such as news, drama, and movies, is carefully structured as a sequence of semantic units, one can get its essence by enabling a traversal through representative items from these semantic units. Hence, ToC-based video browsing caters to summarization of scripted content.
UR - http://www.scopus.com/inward/record.url?scp=33645750769&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=33645750769&partnerID=8YFLogxK
U2 - 10.1016/B978-012119792-6/50122-4
DO - 10.1016/B978-012119792-6/50122-4
M3 - Chapter
AN - SCOPUS:33645750769
SN - 9780121197926
SP - 1013
EP - 1029
BT - Handbook of Image and Video Processing
PB - Elsevier Inc.
ER -