Analysis and Re-Use of Videos in Educational Digital Libraries with Automatic Scene Detection
The advent of modern approaches to education, like Massive Open Online Courses (MOOC), made video the basic media for educating and transmitting knowledge. However, IT tools are still not adequate to allow video content re-use, tagging, annotation and personalization. In this paper we analyze the problem of identifying coherent sequences, called scenes, in order to provide the users with a more manageable editing unit. A simple spectral clustering technique is proposed and compared with state-of-the-art results. We also discuss correct ways to evaluate the performance of automatic scene detection algorithms.
KeywordsScene detection Performance evaluation Spectral clustering
This work was carried out within the project “Città educante” (ctn01_00034_393801) of the National Technological Cluster on Smart Communities cofunded by the Italian Ministry of Education, University and Research - MIUR.
- 1.Apostolidis, E., Mezaris, V.: Fast shot segmentation combining global and local visual descriptors. In: IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 6583–6587 (2014)Google Scholar
- 2.Baraldi, L., Paci, F., Serra, G., Benini, L., Cucchiara, R.: Gesture recognition in ego-centric videos using dense trajectories and hand segmentation. In: Proceedings of 10th IEEE Embedded Vision Workshop (EVW). Columbus, Ohio, June 2014Google Scholar
- 3.Battenberg, J.K., Merbler, J.B.: Touch screen versus keyboard: a comparison of task performance of young children. J. Spec. Educ. Technol. 10(2), 24–28 (1989)Google Scholar
- 8.Mascolo, M.F.: Beyond student-centered and teacher-centered pedagogy: teaching and learning as guided participation. Pedagogy Hum. Sci. 1(1), 3–27 (2009)Google Scholar
- 10.Serra, G., Camurri, M., Baraldi, L., Benedetti, M., Cucchiara, R.: Hand segmentation for gesture recognition in ego-vision. In: Proceedings of ACM Multimedia International Workshop on Interactive Multimedia on Mobile and Portable Devices (IMMPD), Barcelona, Spain, October 2013Google Scholar
- 13.Yeung, M.M., Yeo, B.L., Wolf, W.H., Liu, B.: Video browsing using clustering and scene transitions on compressed sequences. In: IS&T/SPIE’s Symposium on Electronic Imaging: Science & Technology, pp. 399–413 (1995)Google Scholar