Fine-grained Video Retrieval using Query Phrases - Waseda-Meisei TRECVID 2017 AVS System - Waseda-Meisei T

Kazuya Ueki, Koji Hirakawa, Kotaro Kikuchi, Tetsunori Kobayashi

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

    Abstract

    In this paper, a joint team from Waseda University and Meisei University (team name: Waseda-Meisei) report their efforts on the ad-hoc video search (AVS) task for the TRECVID benchmark, which is conducted annually by the National Institute of Standards and Technology (NIST). For the AVS task, a system is required to perform a fine-grained search of target videos from a large-scale video database using a query phrase including multiple keywords, such as objects, persons, scenes, and actions. The system we submitted has the following two characteristics. First, to improve the coverage rate of classes corresponding to keywords in query phrases, we prepared a large number of classifiers that can detect objects, persons, scenes, and actions, which were trained using various image and video datasets. Second, when choosing a concept classifier corresponding to a keyword, we introduced a mechanism that allows us to select additional concept classifiers by incorporating natural language processing techniques. We submitted multiple systems with these characteristics to the TRECVID 2017 AVS task and one of our systems ranked the highest among all the submitted systems from 22 teams.

    Original languageEnglish
    Title of host publication2018 24th International Conference on Pattern Recognition, ICPR 2018
    PublisherInstitute of Electrical and Electronics Engineers Inc.
    Pages3322-3327
    Number of pages6
    Volume2018-August
    ISBN (Electronic)9781538637883
    DOIs
    Publication statusPublished - 2018 Nov 26
    Event24th International Conference on Pattern Recognition, ICPR 2018 - Beijing, China
    Duration: 2018 Aug 202018 Aug 24

    Other

    Other24th International Conference on Pattern Recognition, ICPR 2018
    CountryChina
    CityBeijing
    Period18/8/2018/8/24

    Fingerprint

    Classifiers
    Processing

    ASJC Scopus subject areas

    • Computer Vision and Pattern Recognition

    Cite this

    Ueki, K., Hirakawa, K., Kikuchi, K., & Kobayashi, T. (2018). Fine-grained Video Retrieval using Query Phrases - Waseda-Meisei TRECVID 2017 AVS System - Waseda-Meisei T. In 2018 24th International Conference on Pattern Recognition, ICPR 2018 (Vol. 2018-August, pp. 3322-3327). [8546122] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICPR.2018.8546122

    Fine-grained Video Retrieval using Query Phrases - Waseda-Meisei TRECVID 2017 AVS System - Waseda-Meisei T. / Ueki, Kazuya; Hirakawa, Koji; Kikuchi, Kotaro; Kobayashi, Tetsunori.

    2018 24th International Conference on Pattern Recognition, ICPR 2018. Vol. 2018-August Institute of Electrical and Electronics Engineers Inc., 2018. p. 3322-3327 8546122.

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

    Ueki, K, Hirakawa, K, Kikuchi, K & Kobayashi, T 2018, Fine-grained Video Retrieval using Query Phrases - Waseda-Meisei TRECVID 2017 AVS System - Waseda-Meisei T. in 2018 24th International Conference on Pattern Recognition, ICPR 2018. vol. 2018-August, 8546122, Institute of Electrical and Electronics Engineers Inc., pp. 3322-3327, 24th International Conference on Pattern Recognition, ICPR 2018, Beijing, China, 18/8/20. https://doi.org/10.1109/ICPR.2018.8546122
    Ueki K, Hirakawa K, Kikuchi K, Kobayashi T. Fine-grained Video Retrieval using Query Phrases - Waseda-Meisei TRECVID 2017 AVS System - Waseda-Meisei T. In 2018 24th International Conference on Pattern Recognition, ICPR 2018. Vol. 2018-August. Institute of Electrical and Electronics Engineers Inc. 2018. p. 3322-3327. 8546122 https://doi.org/10.1109/ICPR.2018.8546122
    Ueki, Kazuya ; Hirakawa, Koji ; Kikuchi, Kotaro ; Kobayashi, Tetsunori. / Fine-grained Video Retrieval using Query Phrases - Waseda-Meisei TRECVID 2017 AVS System - Waseda-Meisei T. 2018 24th International Conference on Pattern Recognition, ICPR 2018. Vol. 2018-August Institute of Electrical and Electronics Engineers Inc., 2018. pp. 3322-3327
    @inproceedings{f6f68e5e97ef43bb8fe473daf28540c5,
    title = "Fine-grained Video Retrieval using Query Phrases - Waseda-Meisei TRECVID 2017 AVS System - Waseda-Meisei T",
    abstract = "In this paper, a joint team from Waseda University and Meisei University (team name: Waseda-Meisei) report their efforts on the ad-hoc video search (AVS) task for the TRECVID benchmark, which is conducted annually by the National Institute of Standards and Technology (NIST). For the AVS task, a system is required to perform a fine-grained search of target videos from a large-scale video database using a query phrase including multiple keywords, such as objects, persons, scenes, and actions. The system we submitted has the following two characteristics. First, to improve the coverage rate of classes corresponding to keywords in query phrases, we prepared a large number of classifiers that can detect objects, persons, scenes, and actions, which were trained using various image and video datasets. Second, when choosing a concept classifier corresponding to a keyword, we introduced a mechanism that allows us to select additional concept classifiers by incorporating natural language processing techniques. We submitted multiple systems with these characteristics to the TRECVID 2017 AVS task and one of our systems ranked the highest among all the submitted systems from 22 teams.",
    author = "Kazuya Ueki and Koji Hirakawa and Kotaro Kikuchi and Tetsunori Kobayashi",
    year = "2018",
    month = "11",
    day = "26",
    doi = "10.1109/ICPR.2018.8546122",
    language = "English",
    volume = "2018-August",
    pages = "3322--3327",
    booktitle = "2018 24th International Conference on Pattern Recognition, ICPR 2018",
    publisher = "Institute of Electrical and Electronics Engineers Inc.",

    }

    TY - GEN

    T1 - Fine-grained Video Retrieval using Query Phrases - Waseda-Meisei TRECVID 2017 AVS System - Waseda-Meisei T

    AU - Ueki, Kazuya

    AU - Hirakawa, Koji

    AU - Kikuchi, Kotaro

    AU - Kobayashi, Tetsunori

    PY - 2018/11/26

    Y1 - 2018/11/26

    N2 - In this paper, a joint team from Waseda University and Meisei University (team name: Waseda-Meisei) report their efforts on the ad-hoc video search (AVS) task for the TRECVID benchmark, which is conducted annually by the National Institute of Standards and Technology (NIST). For the AVS task, a system is required to perform a fine-grained search of target videos from a large-scale video database using a query phrase including multiple keywords, such as objects, persons, scenes, and actions. The system we submitted has the following two characteristics. First, to improve the coverage rate of classes corresponding to keywords in query phrases, we prepared a large number of classifiers that can detect objects, persons, scenes, and actions, which were trained using various image and video datasets. Second, when choosing a concept classifier corresponding to a keyword, we introduced a mechanism that allows us to select additional concept classifiers by incorporating natural language processing techniques. We submitted multiple systems with these characteristics to the TRECVID 2017 AVS task and one of our systems ranked the highest among all the submitted systems from 22 teams.

    AB - In this paper, a joint team from Waseda University and Meisei University (team name: Waseda-Meisei) report their efforts on the ad-hoc video search (AVS) task for the TRECVID benchmark, which is conducted annually by the National Institute of Standards and Technology (NIST). For the AVS task, a system is required to perform a fine-grained search of target videos from a large-scale video database using a query phrase including multiple keywords, such as objects, persons, scenes, and actions. The system we submitted has the following two characteristics. First, to improve the coverage rate of classes corresponding to keywords in query phrases, we prepared a large number of classifiers that can detect objects, persons, scenes, and actions, which were trained using various image and video datasets. Second, when choosing a concept classifier corresponding to a keyword, we introduced a mechanism that allows us to select additional concept classifiers by incorporating natural language processing techniques. We submitted multiple systems with these characteristics to the TRECVID 2017 AVS task and one of our systems ranked the highest among all the submitted systems from 22 teams.

    UR - http://www.scopus.com/inward/record.url?scp=85059742311&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=85059742311&partnerID=8YFLogxK

    U2 - 10.1109/ICPR.2018.8546122

    DO - 10.1109/ICPR.2018.8546122

    M3 - Conference contribution

    AN - SCOPUS:85059742311

    VL - 2018-August

    SP - 3322

    EP - 3327

    BT - 2018 24th International Conference on Pattern Recognition, ICPR 2018

    PB - Institute of Electrical and Electronics Engineers Inc.

    ER -