By Topic

Low complexity customized video playlist generation

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$33 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

2 Author(s)
Masoud Alghoniemy ; Department of Electronics and Computer Engineering, Egypt-Japan University of Science and Technology, Egypt ; Ahmed H. Tewfik

We consider the problem of customizing video playlist where a system for constructing a playlist composed of a sequence of videos that attain a specific user profile is proposed. Each video item is represented as a collection of weighted attributes that represent the accompanying features. The proposed solution allows users to construct a sequence of video items by imposing global and transitional constraints. Transitional constraints deal with the similarity between successive video objects while global constraints ensure that the retrieved video attributes attain the proposed user profile. The retrieved sequence of videos is constructed by considering it as a solution to a constrained sequence retrieval problem where constraints represent user preferences. The constrained retrieval problem is then modeled as a network flow model which leads to integer program. Relaxation techniques are then used for complexity reduction. Experiments demonstrate the flexibility of the proposed model in constructing the playlist according to user needs.

Published in:

Emerging Signal Processing Applications (ESPA), 2012 IEEE International Conference on

Date of Conference:

12-14 Jan. 2012