Mouse Activity as an Indicator of Interestingness in Video
作者： Gloria Zen , Paloma de Juan , Yale Song , Alejandro Jaimes
关键词:
摘要: Automatic detection of interesting moments in video has many real-world applications such as summarization and efficient online browsing. In this paper, we present a lightweight scalable solution to problem based on user mouse activity while watching video. Unlike previous approaches that analyze content infer the interestingness, leverage implicit feedback obtained from thousands sessions. This makes our method computationally billions videos. Most importantly, approach can handle variety genres because make no assumption what constitutes interestingness: let crowd tell us through their activity. By analyzing 106,212 sessions collected popular website, show is highly indicative competitive performance several state-of-the-art methods.
acm.org
lens.org 参考文章(70)
Robert T. Knight, Anantha Pradeep, Ramachandran Gurumoorthy, Multi-market program and commercial response monitoring system using neuro-response measurements ,(2008)
Yuichi Ito, Kris M. Kitani, James A. Bagnell, Martial Hebert, Detecting interesting events using unsupervised density ratio estimation international conference on computer vision. pp. 151- 161 ,(2012) , 10.1007/978-3-642-33885-4_16
Min Sun, Ali Farhadi, Steve Seitz, Ranking Domain-Specific Highlights by Analyzing Edited Videos european conference on computer vision. pp. 787- 802 ,(2014) , 10.1007/978-3-319-10590-1_51
Florian Pfleiderer, Alireza Sahami Shirazi, Hendrik Glück, Markus Funk, Albrecht Schmidt, MediaBrain: Annotating Videos based on Brain-Computer Interaction Mensch & Computer. pp. 263- 272 ,(2012)
Tal Zubalsky, Yuval Hofshy, Jonathan Bloch, Barak Feldman, Methods and systems for in-video library ,(2013)
Reto Wettach, Kairi Sai, Digital video reproduction method, digital video reproducing apparatus and digital video recording and reproducing apparatus ,(2001)
Michel Hersen, Gerald Goldstein, Handbook of psychological assessment Pergamon Press. ,(1990)
Christophe Chênes, Guillaume Chanel, Mohammad Soleymani, Thierry Pun, Highlight Detection in Movie Scenes Through Inter-users, Physiological Linkage Social Media Retrieval. pp. 217- 237 ,(2013) , 10.1007/978-1-4471-4555-4_10
Oleg Skrypnyuk, Maik Steffen Maurer, Francis Abbott Waldman, Tracking content through serial presentation ,(2013)
David A. Shamma, Peter Shafton, Method and system for media landmark identification ,(2007)