MuseSync: standing on the shoulders of Hollywood

TitleMuseSync: standing on the shoulders of Hollywood
Publication TypeConference Paper
Year of Publication2012
AuthorsLiem, CCS, Bazzica, A, Hanjalic, A
Tertiary AuthorsBabaguchi, N, Aizawa, K, Smith, JR, Satoh, S', Plagemann, T, Hua, X-S, Yan, R
Conference NameThe 20th ACM international conference on Multimedia - MM '12
PublisherACM Press
Conference LocationNara, Japan
ISBN Number9781450310895
Keywordsaudiovisual synchronization, cross-modal connotation, folksonomy, multimodal techniques, popular media, web video

In this extended abstract, we present a novel story-driven approach to soundtrack retrieval for user-generated videos. Cinematic knowledge on cross-modal associations is exploited through folksonomic story text retrieval from collaborative online metadata resources. Subsequently, audiovisual synchronization is applied based on high-level features described by users. The approach is demonstrated in the MuseSync prototype system.