Abstract
This paper proposes an method of automatically generating video digest that can dynamically change the scene component ratio in relation to context semantics and to individual distinctive events. We implemented a system of generating tennis digest, where three parameters given by the user, i.e. player being focused on, digest composition, and total duration, were reflected in the content. We asked several people with TV production experience to create correct digest data for reference, which should be generated when the same parameters are given. The reference data and the output of the system were compared to evaluate the effectiveness of the proposed method. The results revealed that the generated digests could convey the semantics of the original video reasonably well, and they demonstrated the performance and the validity of our approach.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Zhang, H., et al.: Automatic Parsing and Indexing of News Video. Multimedia Systems 2(6), 256–266 (1995)
Ariki, Y., et al.: Indexing and Classification of News Video Articles by Speech, Character and Image Recognition. IEICE, PRMU96-97, pp. 31-38 (1996)
Smith, M., Kanade, T.: Video Skimming and Characterizati on through the Combination of Image and Language Understanding Techniques. IEEE Computer Vision and Pattern Recognition (CVPR) (1997)
Nakamura, Y., Kanade, T.: Semantic analysis for video contents extraction - spotting by association in news video. ACM Multimedia, pp. 393-401 (1997)
Ueda, K., et al.: A Design of Summary Composition System with Template Scenario. IPSJ, DBS-119-24, pp. 139-144 (1999)
Hashimoto, T., et al.: Prototype of Digest Viewing System for Television., IPSJ, Vol.41, No.SIG3(TOD6), pp. 71-84 (2000)
Watanabe, Y., et al.: Image Analysis Using Natural Language Information Extracted from Explanation Text. JSAI 13(1), 66–74 (1998)
Gong, Y., Sin, L.T., Chuan, C.H., Zhang, H., Sakauchi, M.: Automatic parsing of TV soccer programs. In: Proc. Int’l Conf. on Multimedia Computing and Systems, pp. 167–174 (1995)
Babaguchi, N., et al.: Generation of Personalized Abstract of Sports Video. In: International Conference on Multimedia and Expo (ICME), FP4.4 (2001)
Miyamori, H.: Automatic Annotation of Tennis Action for Content-based Retrieval by Integrated Audio and Visual Information. In: International Conference on Image and Video Retrieval (CIVR) (2003)
Miyamori, H.: Automatic Video Annotation using Action Indices and its Application to Flexible Content-Based Retrieval. IPSJ, DBS127-2, FI67-2, pp. 9-16 (2002)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Miyamori, H. (2004). Automatic Generation of Personalized Digest Based on Context Flow and Distinctive Events. In: Enser, P., Kompatsiaris, Y., O’Connor, N.E., Smeaton, A.F., Smeulders, A.W.M. (eds) Image and Video Retrieval. CIVR 2004. Lecture Notes in Computer Science, vol 3115. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-27814-6_24
Download citation
DOI: https://doi.org/10.1007/978-3-540-27814-6_24
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-22539-3
Online ISBN: 978-3-540-27814-6
eBook Packages: Springer Book Archive