Effective Comic-Like Representations with Embedded Regions of Interest
Comic-like summaries exploit the narrative structure of comics to create intuitive and easily readable abstracts. However, real comics use complex composition techniques which are difficult to mimic in an unsupervised way as they involve high level semantic understanding. This paper explores the use of visual attention analysis and face detection to embed regions of interest in adjacent images, obtaining more compact yet informative representations. This paper also addresses the generation of the layout, which involves combinatorial optimization problems. In practice, using exhaustive search to solve the problem is not feasible due to the large number of images. A split and merge approach is proposed to effectively address the layout problem, thus the limitations of finding solutions in a wide range of row widths can be avoided. A user study conducted on several episodes of TV series confirmed the utility of the proposed approach.
KeywordsComics layout visual attention video summarizations regions of interest
Unable to display preview. Download preview PDF.
- 1.Calic, J., Campbell, N.W.: Compact visualisation of video summaries. EURASIP Journal on Advances in Signal Processing 2007(2), 14 pages (2007)Google Scholar
- 4.Girgensohn, A.: A fast layout algorithm for visual video summaries. In: Proc. of International Conference on Multimedia and Expo, vol. 2, pp. 77–80 (2003)Google Scholar
- 5.Hong, R., Yuan, X.-T., Xu, M., Wang, M., Yan, S., Chua, T.-S.: Movie2comics: a feast of multimedia artwork. In: Proceedings of the ACM International Conference on Multimedia, pp. 611–614 (2010)Google Scholar
- 6.Likert, R.: A technique for the measurement of attitudes. Archives of Psychology 22(140), 1–55 (1932)Google Scholar
- 7.Liu, H., Jiang, S., Huang, Q., Xu, C.: A generic virtual content insertion system based on visual attention analysis. In: Proc. of the ACM International Conference on Multimedia, pp. 379–388 (2008)Google Scholar
- 8.McCloud, S.: Understanding Comics: The Invisible Art. HarperCollins (May 1994)Google Scholar
- 10.Uchihashi, S., Foote, J., Girgensohn, A., Boreczky, J.: Video manga: generating semantically meaningful video summaries. In: Proc. of the ACM International Conference on Multimedia, pp. 383–392 (1999)Google Scholar