Dynamic object scanning: Object-based elastic timeline for quickly browsing first-person videos

Seita Kayukawa, Keita Higuchi, Ryo Yonetani, Masanori Nakamura, Yoichi Sato, Shigeo Morishima

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

    1 Citation (Scopus)

    Abstract

    This work presents the Dynamic Object Scanning (DO-Scanning), a novel interface that helps users browse long and untrimmed first-person videos quickly. The proposed interface offers users a small set of object cues generated automatically tailored to the context of a given video. Users choose which cue to highlight, and the interface in turn fast-forwards the video adaptively while keeping scenes with highlighted cues played at original speed. Our experimental results have revealed that the DO-Scanning arranged an efficient and compact set of cues, and this set of cues is useful for browsing a diverse set of first-person videos.

    Original languageEnglish
    Title of host publicationCHI 2018 - Extended Abstracts of the 2018 CHI Conference on Human Factors in Computing Systems
    Subtitle of host publicationEngage with CHI
    PublisherAssociation for Computing Machinery
    Volume2018-April
    ISBN (Electronic)9781450356206, 9781450356213
    DOIs
    Publication statusPublished - 2018 Apr 20
    Event2018 CHI Conference on Human Factors in Computing Systems, CHI EA 2018 - Montreal, Canada
    Duration: 2018 Apr 212018 Apr 26

    Other

    Other2018 CHI Conference on Human Factors in Computing Systems, CHI EA 2018
    CountryCanada
    CityMontreal
    Period18/4/2118/4/26

    Fingerprint

    Scanning
    User interfaces

    Keywords

    • Content-aware video fast-forwarding
    • First-person videos

    ASJC Scopus subject areas

    • Human-Computer Interaction
    • Computer Graphics and Computer-Aided Design
    • Software

    Cite this

    Kayukawa, S., Higuchi, K., Yonetani, R., Nakamura, M., Sato, Y., & Morishima, S. (2018). Dynamic object scanning: Object-based elastic timeline for quickly browsing first-person videos. In CHI 2018 - Extended Abstracts of the 2018 CHI Conference on Human Factors in Computing Systems: Engage with CHI (Vol. 2018-April). [LBW611] Association for Computing Machinery. https://doi.org/10.1145/3170427.3189085

    Dynamic object scanning : Object-based elastic timeline for quickly browsing first-person videos. / Kayukawa, Seita; Higuchi, Keita; Yonetani, Ryo; Nakamura, Masanori; Sato, Yoichi; Morishima, Shigeo.

    CHI 2018 - Extended Abstracts of the 2018 CHI Conference on Human Factors in Computing Systems: Engage with CHI. Vol. 2018-April Association for Computing Machinery, 2018. LBW611.

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

    Kayukawa, S, Higuchi, K, Yonetani, R, Nakamura, M, Sato, Y & Morishima, S 2018, Dynamic object scanning: Object-based elastic timeline for quickly browsing first-person videos. in CHI 2018 - Extended Abstracts of the 2018 CHI Conference on Human Factors in Computing Systems: Engage with CHI. vol. 2018-April, LBW611, Association for Computing Machinery, 2018 CHI Conference on Human Factors in Computing Systems, CHI EA 2018, Montreal, Canada, 18/4/21. https://doi.org/10.1145/3170427.3189085
    Kayukawa S, Higuchi K, Yonetani R, Nakamura M, Sato Y, Morishima S. Dynamic object scanning: Object-based elastic timeline for quickly browsing first-person videos. In CHI 2018 - Extended Abstracts of the 2018 CHI Conference on Human Factors in Computing Systems: Engage with CHI. Vol. 2018-April. Association for Computing Machinery. 2018. LBW611 https://doi.org/10.1145/3170427.3189085
    Kayukawa, Seita ; Higuchi, Keita ; Yonetani, Ryo ; Nakamura, Masanori ; Sato, Yoichi ; Morishima, Shigeo. / Dynamic object scanning : Object-based elastic timeline for quickly browsing first-person videos. CHI 2018 - Extended Abstracts of the 2018 CHI Conference on Human Factors in Computing Systems: Engage with CHI. Vol. 2018-April Association for Computing Machinery, 2018.
    @inproceedings{7cc7434454f142b38327cbc7b984c970,
    title = "Dynamic object scanning: Object-based elastic timeline for quickly browsing first-person videos",
    abstract = "This work presents the Dynamic Object Scanning (DO-Scanning), a novel interface that helps users browse long and untrimmed first-person videos quickly. The proposed interface offers users a small set of object cues generated automatically tailored to the context of a given video. Users choose which cue to highlight, and the interface in turn fast-forwards the video adaptively while keeping scenes with highlighted cues played at original speed. Our experimental results have revealed that the DO-Scanning arranged an efficient and compact set of cues, and this set of cues is useful for browsing a diverse set of first-person videos.",
    keywords = "Content-aware video fast-forwarding, First-person videos",
    author = "Seita Kayukawa and Keita Higuchi and Ryo Yonetani and Masanori Nakamura and Yoichi Sato and Shigeo Morishima",
    year = "2018",
    month = "4",
    day = "20",
    doi = "10.1145/3170427.3189085",
    language = "English",
    volume = "2018-April",
    booktitle = "CHI 2018 - Extended Abstracts of the 2018 CHI Conference on Human Factors in Computing Systems",
    publisher = "Association for Computing Machinery",

    }

    TY - GEN

    T1 - Dynamic object scanning

    T2 - Object-based elastic timeline for quickly browsing first-person videos

    AU - Kayukawa, Seita

    AU - Higuchi, Keita

    AU - Yonetani, Ryo

    AU - Nakamura, Masanori

    AU - Sato, Yoichi

    AU - Morishima, Shigeo

    PY - 2018/4/20

    Y1 - 2018/4/20

    N2 - This work presents the Dynamic Object Scanning (DO-Scanning), a novel interface that helps users browse long and untrimmed first-person videos quickly. The proposed interface offers users a small set of object cues generated automatically tailored to the context of a given video. Users choose which cue to highlight, and the interface in turn fast-forwards the video adaptively while keeping scenes with highlighted cues played at original speed. Our experimental results have revealed that the DO-Scanning arranged an efficient and compact set of cues, and this set of cues is useful for browsing a diverse set of first-person videos.

    AB - This work presents the Dynamic Object Scanning (DO-Scanning), a novel interface that helps users browse long and untrimmed first-person videos quickly. The proposed interface offers users a small set of object cues generated automatically tailored to the context of a given video. Users choose which cue to highlight, and the interface in turn fast-forwards the video adaptively while keeping scenes with highlighted cues played at original speed. Our experimental results have revealed that the DO-Scanning arranged an efficient and compact set of cues, and this set of cues is useful for browsing a diverse set of first-person videos.

    KW - Content-aware video fast-forwarding

    KW - First-person videos

    UR - http://www.scopus.com/inward/record.url?scp=85052022461&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=85052022461&partnerID=8YFLogxK

    U2 - 10.1145/3170427.3189085

    DO - 10.1145/3170427.3189085

    M3 - Conference contribution

    AN - SCOPUS:85052022461

    VL - 2018-April

    BT - CHI 2018 - Extended Abstracts of the 2018 CHI Conference on Human Factors in Computing Systems

    PB - Association for Computing Machinery

    ER -