Video Search by Impression Extracted from Social Annotation

Authors:
Satoshi Nakamura;Katsumi Tanaka
Affiliations:
Graduate School of Kyoto University, Yoshida-Honmachi, Sakyo, Kyoto, Japan;Graduate School of Kyoto University, Yoshida-Honmachi, Sakyo, Kyoto, Japan
Venue:
WISE '09 Proceedings of the 10th International Conference on Web Information Systems Engineering
Year:
2009

Citing 10
Cited 0

Semantic analysis for video contents extraction—spotting by association in news video

MULTIMEDIA '97 Proceedings of the fifth ACM international conference on Multimedia
Closed-world tracking

ICCV '95 Proceedings of the Fifth International Conference on Computer Vision
Annotating TV Drama based on Viewer Dialogue - Analysis of Viewers' Attention Generated on an Internet Bulletin Board -

SAINT '05 Proceedings of the The 2005 Symposium on Applications and the Internet
Generation of views of TV content using TV viewers' perspectives expressed in live chats on the web

Proceedings of the 13th annual ACM international conference on Multimedia
From social bookmarking to social summarization: an experiment in community-based summary generation

Proceedings of the 12th international conference on Intelligent user interfaces
Can social bookmarking enhance search in the web?

Proceedings of the 7th ACM/IEEE-CS joint conference on Digital libraries
Can social bookmarking improve web search?

WSDM '08 Proceedings of the 2008 International Conference on Web Search and Data Mining
Can social annotation support users in evaluating the trustworthiness of video clips?

Proceedings of the 2nd ACM workshop on Information credibility on the web
Automatic annotation of tennis action for content-based retrieval by integrated audio and visual information

CIVR'03 Proceedings of the 2nd international conference on Image and video retrieval
Person spotting: video shot retrieval for face sets

CIVR'05 Proceedings of the 4th international conference on Image and Video Retrieval

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper proposes a novel indexing and ranking method for video clips on video sharing Web sites that overcomes some of the problems with conventional systems. These problems include the difficulty of finding target video clips by the emotional impression they make, such as level of happiness, level of sadness, and so on because text summaries of video clips on video sharing Web sites usually do not contain such information. Our system extracts this type of information from comments on the video clips and generates an impression index for searching and ranking. In this work, we present analytical studies of video sharing Web site. Then, we propose an impression ranking method and show the usefulness of this method on the experimental test. In addition, we describe the future direction of this work.