AUTHORS: Chonthorn Ariyapitipan and Kingkarn Sookhanaphibarn
ABSTRACT: This paper presents a systematic approach for video-audience-watching content analysis. Our analysis technique is based on audience preference that they will click Like while watching a video clip. The principal component analysis is applied to extract the content structure of a video clip. The hierarchical clustering technique also is used to segment a video content as time slots. The analysis and clustering are based on the audience opinion. In our experiment, the approach is set to teaching video content for 22 4-year students in Bachelor degree. The analysis results show the three principal structures that can represent three principal video-audience-watching preference styles.
Keywords: Routine-structure analysis, Singular Value De-composition (SVD), Principal Component Analysis (PCA)
LINK: http://mit.itu.bu.ac.th/publications/Structural Analysis of Video-Audience-Watching.pdf
REFERENCES:
| [1] | K. Darabi and G. Ghinea, “Video summarization by group scoring,” in 2014 International Conference on Multimedia Computing and Systems (ICMCS). IEEE, 2014, pp. 112–116. | |
| [2] | N. Eagle and A. S. Pentland, “Eigenbehaviors: Identifying structure in routine,” Behavioral Ecology and Sociobiology, vol. 63, no. 7, pp. 1057–1066, 2009. | |
| [3] | K. Sookhanaphibarn, R. Thawonmas, F. Rinaldo, and K.-T. Chen, “Spa-tiotemporal analysis in virtual environments using eigenbehaviors,” in Proceedings of the 7th International Conference on Advances in Com-puter Entertainment Technology. ACM, 2010, pp. 62–65. | |
| [4] | F. Calabrese, J. Reades, and C. Ratti, “Eigenplaces: segmenting space through digital signatures,” IEEE Pervasive Computing, vol. 9, no. 1, pp. 78–84, 2009. | |