Digital Library

cab1

 
Title:      SEMANTIC CONCEPTS FOR CONTENT FILTERING ON VIDEO SHARING SOCIAL NETWORKS
Author(s):      Antonio da Luz, Eduardo Valle, Arnaldo de A. Araújo
ISBN:      978-989-8533-01-2
Editors:      Bebo White, Pedro Isaías and Flávia Maria Santoro
Year:      2011
Edition:      Single
Keywords:      Semantic Video Classification, Latent Semantic Analysis, Bag-of-Features, STIP
Type:      Full Paper
First Page:      293
Last Page:      300
Language:      English
Cover:      cover          
Full Contents:      click to dowload Download
Paper Abstract:      In this work we are concerned in use semantic concepts to filter spam videos on video sharing social networks. Specifically, we investigate how much semantic-based information analysis, based on content-based visual information retrieval (CBVIR), can aid in detecting spam videos. This is a very challenging task, because of the high-level semantic concepts involved; of the assorted nature of social networks, preventing the use of constrained a priori information. In addition, a spam video is by nature context-dependent, forcing us to take into account the context of the videos within their threads in the classification. Web services for the sharing of clips of video are extremely popular; and the recent boom of intelligent mobile devices such as smartphones and tablets equipped with fast network access and good-quality cameras and displays has reduced the interval between content creation and broadcasting. That proliferation of new content, and the immediacy of its availability, is not without problems, creating a demand for mechanisms to control abuses and terms-of-use violations. We propose an approach based on bags-of-topic-differences, which improves considerably over the use of the baseline bags-of-words model, by allowing us to incorporate the context of the video in the representation. Our model is evaluated in challenging video dataset, showing very encouraging results.
   

Social Media Links

Search

Login