Efficient Video Indexing on the Web : A System that Crowdsources User Interactions with a Video Player
I. Leftheriotis, C. Gkonela, and K. Chorianopoulos. 2nd International ICST Conference on User Centric Media (UCMEDIA 2010), volume 60 of Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, Springer Berlin Heidelberg, Berlin, Heidelberg, (January 2012)
DOI: 10.1007/978-3-642-35145-7\_16
Abstract
In this paper, we propose a user-based video-indexing method, that automatically generates thumbnails of the most important scenes of an online video stream, by analyzing users’ interactions with a web video player. As a test bench to verify our idea we have extended the YouTube video player into the VideoSkip system. In addition, VideoSkip uses a web-database (Google Application Engine) to keep a record of some important parameters, such as the timing of basic user actions (play, pause, skip). Moreover, we implemented an algorithm that selects representative thumbnails. Finally, we populated the system with data from an experiment with nine users. We found that the VideoSkip system indexes video content by leveraging implicit users interactions, such as pause and thirty seconds skip. Our early findings point toward improvements of the web video player and its thumbnail generation technique. The VideSkip system could compliment content-based algorithms, in order to achieve efficient video-indexing in difficult videos, such as lectures or sports.
%0 Book Section
%1 Leftheriotis2012
%A Leftheriotis, Ioannis
%A Gkonela, Chrysoula
%A Chorianopoulos, Konstantinos
%B 2nd International ICST Conference on User Centric Media (UCMEDIA 2010)
%C Berlin, Heidelberg
%D 2012
%E Alvarez, Federico
%E Costa, Cristina
%I Springer Berlin Heidelberg
%K app crowdsourcing,google engine,human-computer interaction,indexing,interactive lectures,youtube technology,thumbnails,time-series,video,video tv,multimedia,pragmatics,semantics,software
%P 123--131
%R 10.1007/978-3-642-35145-7\_16
%T Efficient Video Indexing on the Web : A System that Crowdsources User Interactions with a Video Player
%U http://dx.doi.org/10.1007/978-3-642-35145-7\_16
%V 60
%X In this paper, we propose a user-based video-indexing method, that automatically generates thumbnails of the most important scenes of an online video stream, by analyzing users’ interactions with a web video player. As a test bench to verify our idea we have extended the YouTube video player into the VideoSkip system. In addition, VideoSkip uses a web-database (Google Application Engine) to keep a record of some important parameters, such as the timing of basic user actions (play, pause, skip). Moreover, we implemented an algorithm that selects representative thumbnails. Finally, we populated the system with data from an experiment with nine users. We found that the VideoSkip system indexes video content by leveraging implicit users interactions, such as pause and thirty seconds skip. Our early findings point toward improvements of the web video player and its thumbnail generation technique. The VideSkip system could compliment content-based algorithms, in order to achieve efficient video-indexing in difficult videos, such as lectures or sports.
%@ 978-3-642-35144-0
@incollection{Leftheriotis2012,
abstract = {In this paper, we propose a user-based video-indexing method, that automatically generates thumbnails of the most important scenes of an online video stream, by analyzing users’ interactions with a web video player. As a test bench to verify our idea we have extended the YouTube video player into the VideoSkip system. In addition, VideoSkip uses a web-database (Google Application Engine) to keep a record of some important parameters, such as the timing of basic user actions (play, pause, skip). Moreover, we implemented an algorithm that selects representative thumbnails. Finally, we populated the system with data from an experiment with nine users. We found that the VideoSkip system indexes video content by leveraging implicit users interactions, such as pause and thirty seconds skip. Our early findings point toward improvements of the web video player and its thumbnail generation technique. The VideSkip system could compliment content-based algorithms, in order to achieve efficient video-indexing in difficult videos, such as lectures or sports.},
added-at = {2013-12-30T18:09:17.000+0100},
address = {Berlin, Heidelberg},
author = {Leftheriotis, Ioannis and Gkonela, Chrysoula and Chorianopoulos, Konstantinos},
biburl = {https://www.bibsonomy.org/bibtex/2c12d4f61c4e2595fad76311791faa549/choko},
booktitle = {2nd International ICST Conference on User Centric Media (UCMEDIA 2010)},
doi = {10.1007/978-3-642-35145-7\_16},
editor = {Alvarez, Federico and Costa, Cristina},
file = {:Users/choko/Documents/Mendeley Desktop//Efficient Video Indexing on the Web A System that Crowdsources User Interactions with a Video Player.pdf:pdf},
interhash = {254c67c2d54358b2572e5c9b0db4f0d2},
intrahash = {c12d4f61c4e2595fad76311791faa549},
isbn = {978-3-642-35144-0},
keywords = {app crowdsourcing,google engine,human-computer interaction,indexing,interactive lectures,youtube technology,thumbnails,time-series,video,video tv,multimedia,pragmatics,semantics,software},
mendeley-tags = {human-computer interaction,multimedia,software technology,time-series,video lectures},
month = jan,
pages = {123--131},
publisher = {Springer Berlin Heidelberg},
series = {Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering},
timestamp = {2013-12-30T18:09:17.000+0100},
title = {{Efficient Video Indexing on the Web : A System that Crowdsources User Interactions with a Video Player}},
url = {http://dx.doi.org/10.1007/978-3-642-35145-7\_16},
volume = 60,
year = 2012
}