Code for superframe extraction from video frames based on paper- Semantic Text Summarization of Long Videos at 2017 IEEE Winter Conference on Applications of Computer Vision (http://www.cis.rit.edu/~sxs4337/publication/Sah_2017_WACV.pdf)
This code shows how to use superframes as a temporal segmentation. The code is a modified version of the one used in the initial publication: Gygli et al. - Creating Summaries from User Videos, ECCV 2014 https://people.ee.ethz.ch/~gyglim/vsum/#sf_code
The modifications include the addition of: Contrast Saturation Sharpness FaceImpact and is the basis for Sah et al., WACV 2017
Ray Ptucha and Shagan Sah, Rochester Institute of Technology, 2017
superframes_v01/demo.m
If you use this code, please cite the following three references:
Gygli, Michael, Helmut Grabner, Hayko Riemenschneider, and Luc Van Gool. "Creating summaries from user videos." In European conference on computer vision, pp. 505-520. Springer, Cham, 2014.
Xuehan Xiong, Fernando de la Torre, Supervised Descent Method and Its Application to Face Alignment. CVPR, 2013.
Sah, Shagan, Sourabh Kulhare, Allison Gray, Subhashini Venugopalan, Emily Prud'Hommeaux, and Raymond Ptucha. "Semantic Text Summarization of Long Videos." In Applications of Computer Vision (WACV), 2017 IEEE Winter Conference on, pp. 989-997. IEEE, 2017.