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:
|
|
Full Contents:
|
click to dowload
|
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. |
|
|
|
|