• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to previous page

Fine-grained video retrieval from large-scale video using query sentences containing unknown concepts

Research Project

Project/Area Number 18K11362
Research Category

Grant-in-Aid for Scientific Research (C)

Allocation TypeMulti-year Fund
Section一般
Review Section Basic Section 61010:Perceptual information processing-related
Research InstitutionMeisei University

Principal Investigator

Ueki Kazuya  明星大学, 情報学部, 准教授 (80580638)

Project Period (FY) 2018-04-01 – 2022-03-31
Project Status Completed (Fiscal Year 2021)
Budget Amount *help
¥4,290,000 (Direct Cost: ¥3,300,000、Indirect Cost: ¥990,000)
Fiscal Year 2020: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2019: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2018: ¥1,950,000 (Direct Cost: ¥1,500,000、Indirect Cost: ¥450,000)
Keywords映像検索 / クエリ文 / TRECVID / 未知の概念 / 画像/言語の同時埋め込み
Outline of Final Research Achievements

We worked on a technique for retrieving videos that match unknown query sentences containing new concepts, such as newly emerging trends and new methods of crime, from the wide variety of videos uploaded to the Internet every day. We investigated methods to apply the trained models to video frames by embedding images and language using a large number of images with captions. We evaluated our method on a large scale of videos in the international competitive video retrieval and evaluation benchmark (TRECVID) organized by the National Institute of Standards and Technology (NIST), and confirmed that our method could retrieve videos with high accuracy for a wide range of query sentences.

Academic Significance and Societal Importance of the Research Achievements

ラベル付きの画像・映像データの整備と,ディープラーニング技術の進展に伴い,ある特定の物体・シーン・動作等のキーワードに合致した画像や映像の検索が実現されつつある.しかしながら,ライフスタイルの変化により,複数かつ新しい概念を含んだクエリ文を用いた詳細映像検索の実現が期待されている.本研究成果により,幅広く複雑なクエリ文に対して高精度に映像を検索することが可能であることから,新しく生まれる未知の概念が含まれている場合においても,その説明文をクエリとして入力することで,必要となる映像を即座に検索できることが期待される.

Report

(5 results)
  • 2021 Annual Research Report   Final Research Report ( PDF )
  • 2020 Research-status Report
  • 2019 Research-status Report
  • 2018 Research-status Report
  • Research Products

    (19 results)

All 2021 2020 2019 2018

All Journal Article (1 results) (of which Peer Reviewed: 1 results) Presentation (18 results) (of which Int'l Joint Research: 5 results)

  • [Journal Article] 複雑のコンセプトを含むクエリ文からのゼロショット映像検索 - TRECVID AVS タスクにおける成果と課題 -2018

    • Author(s)
      植木 一也,平川 幸司,菊池 康太郎,小林 哲則
    • Journal Title

      精密工学会誌

      Volume: 84 Pages: 983-990

    • NAID

      130007534741

    • Related Report
      2018 Research-status Report
    • Peer Reviewed
  • [Presentation] ゼロショット画像検索のための画像と言語の対応付け手法 --サーベイ--2021

    • Author(s)
      植木 一也
    • Organizer
      第27回画像センシングシンポジウム(SSII2021)
    • Related Report
      2021 Annual Research Report
  • [Presentation] TRECVID映像検索ベンチマーク:AVSタスクへの6年間の挑戦と技術の進歩2021

    • Author(s)
      植木 一也
    • Organizer
      ビジョン技術の実利用ワークショップ(ViEW2021)
    • Related Report
      2021 Annual Research Report
  • [Presentation] Waseda_Meisei_SoftBank at TRECVID 2021: Ad-hoc Video Search2021

    • Author(s)
      Kazuya Ueki, Takayuki Hori, Yongbeom Kim, Yuma Suzuki
    • Organizer
      Notebook paper of the TRECVID 2021 Workshop
    • Related Report
      2021 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Survey of Visual-Semantic Embedding Methods for Zero-Shot Image Retrieval2021

    • Author(s)
      Kazuya Ueki
    • Organizer
      Proceedings of International Conference on Machine Learning and Applications (ICMLA)
    • Related Report
      2021 Annual Research Report
    • Int'l Joint Research
  • [Presentation] 服装の色を用いた人物検索に向けた学習済みモデルの活用2021

    • Author(s)
      セイエドネシャド ロスタム,武藤 良,植木 一也,堀 隆之,金 容範,鈴木 裕真
    • Organizer
      動的画像処理実用化ワークショップ (DIA2021)
    • Related Report
      2020 Research-status Report
  • [Presentation] 少数画像をもとにした顔属性データセットの拡張2021

    • Author(s)
      山本 啓斗,武藤 良,植木 一也,堀 隆之,金 容範,鈴木 裕真
    • Organizer
      動的画像処理実用化ワークショップ (DIA2021)
    • Related Report
      2020 Research-status Report
  • [Presentation] Waseda_Meisei_SoftBank at TRECVID 2020: Ad-hoc Video Search2020

    • Author(s)
      Kazuya Ueki, Ryo Mutou, Takayuki Hori, Yongbeom Kim, Yuma Suzuki
    • Organizer
      Notebook paper of the TRECVID 2020 Workshop
    • Related Report
      2020 Research-status Report
  • [Presentation] 学習済みモデルを用いた大規模映像データにおける特定の色の着衣をつけた人物の検索2020

    • Author(s)
      武藤 良,セイエドネシャド ロスタム,植木 一也,堀 隆之,金 容範,鈴木 裕真
    • Organizer
      ビジョン技術の実利用ワークショップ(ViEW2020)
    • Related Report
      2020 Research-status Report
  • [Presentation] OpenPoseを用いた特定の色の服を着た人物の検出2020

    • Author(s)
      セイエドネシャド ロスタム,武藤 良,植木 一也
    • Organizer
      第26回画像センシングシンポジウム(SSII2020)
    • Related Report
      2020 Research-status Report
  • [Presentation] Comparison and Evaluation of Video Retrieval Approaches Using Query Sentences2020

    • Author(s)
      Kazuya Ueki, Takayuki Hori
    • Organizer
      the 3rd International Conference on Machine Vision and Applications (ICMVA 2020)
    • Related Report
      2019 Research-status Report
    • Int'l Joint Research
  • [Presentation] Waseda_Meisei_Meisei at TRECVID 2019: Ad-hoc Video Search2019

    • Author(s)
      Kazuya Ueki, Takayuki Hori, and Tetsunori Kobayashi
    • Organizer
      the TRECVID 2019 Workshop
    • Related Report
      2019 Research-status Report
    • Int'l Joint Research
  • [Presentation] Zero-shot Video Retrieval using a Large-scale Video Database2019

    • Author(s)
      Kazuya Ueki and Takayuki Hori
    • Organizer
      the International Conference on Computer Vision (ICCV2019) MDALC Workshop
    • Related Report
      2019 Research-status Report
    • Int'l Joint Research
  • [Presentation] クエリ文を用いた映像検索手法の比較検証2019

    • Author(s)
      植木 一也, 堀 隆之, 小林 哲則
    • Organizer
      第22回 画像の認識・理解シンポジウム (MIRU2019)
    • Related Report
      2019 Research-status Report
  • [Presentation] クエリ文によるゼロショット映像検索 - TRECVID 2018 AVSタスクの成果報告 -2019

    • Author(s)
      植木 一也,中込 優,平川 幸司,菊池 康太郎,林 良彦,小川 哲司,小林 哲則
    • Organizer
      動的画像処理実用化ワークショップ(DIA2019)
    • Related Report
      2018 Research-status Report
  • [Presentation] ゼロショット映像検索のための潜在的なコンセプトの抽出2018

    • Author(s)
      植木 一也
    • Organizer
      画像の認識・理解シンポジウム (MIRU2018)
    • Related Report
      2018 Research-status Report
  • [Presentation] Fine-grained Video Retrieval using Query Phrases - Waseda_Meisei TRECVID 2017 AVS System -2018

    • Author(s)
      Kazuya Ueki, Koji Hirakawa, Kotaro Kikuchi, and Tetsunori Kobayash
    • Organizer
      International Conference on Pattern Recognition (ICPR2018)
    • Related Report
      2018 Research-status Report
  • [Presentation] Waseda_Meisei at TRECVID 2018: Fully-automatic Ad-hoc Video Search2018

    • Author(s)
      Kazuya Ueki, Yu Nakagome, Koji Hirakawa, Kotaro Kikuchi, Yoshihiko Hayashi, Tetsuji Ogawa, Tetsunori Kobayashi
    • Organizer
      TRECVID 2018 Workshop
    • Related Report
      2018 Research-status Report
  • [Presentation] Latent Concept Extraction for Zero-shot Video Retrieval2018

    • Author(s)
      Kazuya Ueki
    • Organizer
      Image and Vision Computing New Zealand (IVCNZ2018)
    • Related Report
      2018 Research-status Report

URL: 

Published: 2018-04-23   Modified: 2023-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi