Automatic mash up music video generation system by remixing existing video content

Hayato Ohya, Shigeo Morishima

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    1 Citation (Scopus)

    Abstract

    Music video is a short film which presents a visual representation of recent music. In these days, there is a trend that amateur users create music video in the video sharing website. Especially, the music video which is created by cutting and pasting existing video is called mashup music video. In this paper, we proposed the system that users can easily create mushup music video by using existing music videos. In addition, we conducted assessment evaluation experiment for our system. The system firstly extracts music features and video features from existing music videos. Then, the each feature is clustered and the relationship between each feature is learned by Hidden Markov Model. At last, the system cuts learned video scene which is the closest feature among learned videos and pastes it synchronizing with input song. Experiment shows that our method can generate more synchronized video than a previous method.

    Original languageEnglish
    Title of host publicationProceedings - 2013 International Conference on Culture and Computing, Culture and Computing 2013
    PublisherIEEE Computer Society
    Pages157-158
    Number of pages2
    ISBN (Print)9780769550473
    DOIs
    Publication statusPublished - 2013
    Event2013 International Conference on Culture and Computing, Culture and Computing 2013 - Kyoto
    Duration: 2013 Sep 162013 Sep 18

    Other

    Other2013 International Conference on Culture and Computing, Culture and Computing 2013
    CityKyoto
    Period13/9/1613/9/18

    Fingerprint

    Hidden Markov models
    Websites
    Experiments

    Keywords

    • Machine learning
    • Music analysis
    • Music video
    • Video content analysis

    ASJC Scopus subject areas

    • Software

    Cite this

    Ohya, H., & Morishima, S. (2013). Automatic mash up music video generation system by remixing existing video content. In Proceedings - 2013 International Conference on Culture and Computing, Culture and Computing 2013 (pp. 157-158). [6680357] IEEE Computer Society. https://doi.org/10.1109/CultureComputing.2013.44

    Automatic mash up music video generation system by remixing existing video content. / Ohya, Hayato; Morishima, Shigeo.

    Proceedings - 2013 International Conference on Culture and Computing, Culture and Computing 2013. IEEE Computer Society, 2013. p. 157-158 6680357.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Ohya, H & Morishima, S 2013, Automatic mash up music video generation system by remixing existing video content. in Proceedings - 2013 International Conference on Culture and Computing, Culture and Computing 2013., 6680357, IEEE Computer Society, pp. 157-158, 2013 International Conference on Culture and Computing, Culture and Computing 2013, Kyoto, 13/9/16. https://doi.org/10.1109/CultureComputing.2013.44
    Ohya H, Morishima S. Automatic mash up music video generation system by remixing existing video content. In Proceedings - 2013 International Conference on Culture and Computing, Culture and Computing 2013. IEEE Computer Society. 2013. p. 157-158. 6680357 https://doi.org/10.1109/CultureComputing.2013.44
    Ohya, Hayato ; Morishima, Shigeo. / Automatic mash up music video generation system by remixing existing video content. Proceedings - 2013 International Conference on Culture and Computing, Culture and Computing 2013. IEEE Computer Society, 2013. pp. 157-158
    @inproceedings{4d178c9135494a23a1423dfbba2222aa,
    title = "Automatic mash up music video generation system by remixing existing video content",
    abstract = "Music video is a short film which presents a visual representation of recent music. In these days, there is a trend that amateur users create music video in the video sharing website. Especially, the music video which is created by cutting and pasting existing video is called mashup music video. In this paper, we proposed the system that users can easily create mushup music video by using existing music videos. In addition, we conducted assessment evaluation experiment for our system. The system firstly extracts music features and video features from existing music videos. Then, the each feature is clustered and the relationship between each feature is learned by Hidden Markov Model. At last, the system cuts learned video scene which is the closest feature among learned videos and pastes it synchronizing with input song. Experiment shows that our method can generate more synchronized video than a previous method.",
    keywords = "Machine learning, Music analysis, Music video, Video content analysis",
    author = "Hayato Ohya and Shigeo Morishima",
    year = "2013",
    doi = "10.1109/CultureComputing.2013.44",
    language = "English",
    isbn = "9780769550473",
    pages = "157--158",
    booktitle = "Proceedings - 2013 International Conference on Culture and Computing, Culture and Computing 2013",
    publisher = "IEEE Computer Society",

    }

    TY - GEN

    T1 - Automatic mash up music video generation system by remixing existing video content

    AU - Ohya, Hayato

    AU - Morishima, Shigeo

    PY - 2013

    Y1 - 2013

    N2 - Music video is a short film which presents a visual representation of recent music. In these days, there is a trend that amateur users create music video in the video sharing website. Especially, the music video which is created by cutting and pasting existing video is called mashup music video. In this paper, we proposed the system that users can easily create mushup music video by using existing music videos. In addition, we conducted assessment evaluation experiment for our system. The system firstly extracts music features and video features from existing music videos. Then, the each feature is clustered and the relationship between each feature is learned by Hidden Markov Model. At last, the system cuts learned video scene which is the closest feature among learned videos and pastes it synchronizing with input song. Experiment shows that our method can generate more synchronized video than a previous method.

    AB - Music video is a short film which presents a visual representation of recent music. In these days, there is a trend that amateur users create music video in the video sharing website. Especially, the music video which is created by cutting and pasting existing video is called mashup music video. In this paper, we proposed the system that users can easily create mushup music video by using existing music videos. In addition, we conducted assessment evaluation experiment for our system. The system firstly extracts music features and video features from existing music videos. Then, the each feature is clustered and the relationship between each feature is learned by Hidden Markov Model. At last, the system cuts learned video scene which is the closest feature among learned videos and pastes it synchronizing with input song. Experiment shows that our method can generate more synchronized video than a previous method.

    KW - Machine learning

    KW - Music analysis

    KW - Music video

    KW - Video content analysis

    UR - http://www.scopus.com/inward/record.url?scp=84893271788&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84893271788&partnerID=8YFLogxK

    U2 - 10.1109/CultureComputing.2013.44

    DO - 10.1109/CultureComputing.2013.44

    M3 - Conference contribution

    SN - 9780769550473

    SP - 157

    EP - 158

    BT - Proceedings - 2013 International Conference on Culture and Computing, Culture and Computing 2013

    PB - IEEE Computer Society

    ER -