Please use this identifier to cite or link to this item: https://doi.org/10.1145/1631144.1631154
DC FieldValue
dc.titleEvent driven summarization for web videos
dc.contributor.authorHong, R.
dc.contributor.authorTang, J.
dc.contributor.authorTan, H.-K.
dc.contributor.authorYan, S.
dc.contributor.authorNgo, C.
dc.contributor.authorChua, T.-S.
dc.date.accessioned2013-07-23T09:28:56Z
dc.date.available2013-07-23T09:28:56Z
dc.date.issued2009
dc.identifier.citationHong, R.,Tang, J.,Tan, H.-K.,Yan, S.,Ngo, C.,Chua, T.-S. (2009). Event driven summarization for web videos. 1st ACM SIGMM International Workshop on Social Media, WSM'09, Co-located with the 2009 ACM International Conference on Multimedia, MM'09 : 43-48. ScholarBank@NUS Repository. <a href="https://doi.org/10.1145/1631144.1631154" target="_blank">https://doi.org/10.1145/1631144.1631154</a>
dc.identifier.isbn9781605587592
dc.identifier.urihttp://scholarbank.nus.edu.sg/handle/10635/43247
dc.description.abstractThe explosive growth of web videos brings out the challenge of how to efficiently browse hundreds or even thousands of videos at a glance. Given an event-driven query, social media web sites can easily return a ranked list of large but diverse and somewhat noisy videos. Users often need to painstakingly explore the retrieved list for an overview of the event. This paper presents a novel solution by mining and threading "key" shots, which can provide an overview of main contents of videos at a glance, by summarizing a large set of diverse videos. The proposed framework comprises three stages for multi-video summarization. Firstly, given an event query, a ranked list of web videos together with their associated tags are retrieved. Key shots are then established by near-duplicate keyframe detection, ranked according to informativeness and threaded in a chronological order. Finally, summarization is formulated as an optimization procedure which trades off between relevance of key shots and user-defined skimming ratio. The framework provides the summary with the way of dynamic video skimming. We conduct user studies on twelve event queries for over hundred hours of videos crawled from YouTube. The evaluation demonstrates the feasibility and effectiveness of the proposed solution. Copyright 2009 ACM.
dc.description.urihttp://libproxy1.nus.edu.sg/login?url=http://dx.doi.org/10.1145/1631144.1631154
dc.sourceScopus
dc.subjectEvent evolution
dc.subjectWeb video summarization
dc.typeConference Paper
dc.contributor.departmentCOMPUTER SCIENCE
dc.contributor.departmentELECTRICAL & COMPUTER ENGINEERING
dc.description.doi10.1145/1631144.1631154
dc.description.sourcetitle1st ACM SIGMM International Workshop on Social Media, WSM'09, Co-located with the 2009 ACM International Conference on Multimedia, MM'09
dc.description.page43-48
dc.identifier.isiutNOT_IN_WOS
Appears in Collections:Staff Publications

Show simple item record
Files in This Item:
There are no files associated with this item.

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.