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

Visual Concept Modeling of Verbs Based on a Large Scale Set of Tagged Videos Provided by Folksonomy

Research Project

Project/Area Number 26730090
Research Category

Grant-in-Aid for Young Scientists (B)

Allocation TypeMulti-year Fund
Research Field Perceptual information processing
Research InstitutionOsaka University

Principal Investigator

Kazuaki Nakamura  大阪大学, 工学研究科, 助教 (10584047)

Project Period (FY) 2014-04-01 – 2017-03-31
Project Status Completed (Fiscal Year 2016)
Budget Amount *help
¥3,770,000 (Direct Cost: ¥2,900,000、Indirect Cost: ¥870,000)
Fiscal Year 2016: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000)
Fiscal Year 2015: ¥1,820,000 (Direct Cost: ¥1,400,000、Indirect Cost: ¥420,000)
Fiscal Year 2014: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Keywords視覚メディア処理 / 視覚概念学習 / 動作認識 / 映像処理 / 画像処理
Outline of Final Research Achievements

This research project investigates a technology for constructing visual models of concepts represented by verbs using tagged videos which are stored in web-based video sharing services such as YouTube. In general, a video consists of several segments, and each of them has a different semantic content. Therefore, we cannot obtain the complete correspondence between tags and segments. To cope with this problem, this project proposes a method to extract a set of segments whose semantic content commonly appears in videos that have the same tag (called “common segments” in this report), and construct a visual model of the tag using the extracted segments. In the process of common segment extraction, it is quite important to measure the similarity between two segments. This project also proposes a method for calculating the similarity based on a large scale set of tagged images.

Report

(4 results)
  • 2016 Annual Research Report   Final Research Report ( PDF )
  • 2015 Research-status Report
  • 2014 Research-status Report
  • Research Products

    (10 results)

All 2017 2016 2015

All Journal Article (1 results) (of which Peer Reviewed: 1 results,  Acknowledgement Compliant: 1 results) Presentation (9 results)

  • [Journal Article] Effect of Junk Images on Inter-concept Distance Measurement: Positive or Negative?2017

    • Author(s)
      Yusuke Nagasawa, Kazuaki Nakamura, Naoko Nitta, and Noboru Babaguchi
    • Journal Title

      MultiMedia Modeling, MMM 2017, Lecture Notes in Computer Science

      Volume: 10133 Pages: 173-184

    • Related Report
      2016 Annual Research Report
    • Peer Reviewed / Acknowledgement Compliant
  • [Presentation] 隣接領域間での整合性を考慮した静止画からの運動フロー場推定2017

    • Author(s)
      櫻井皓介,中村和晃,新田直子,馬場口登
    • Organizer
      電子情報通信学会2017年総合大会
    • Place of Presentation
      名城大学(愛知県名古屋市)
    • Year and Date
      2017-03-22
    • Related Report
      2016 Annual Research Report
  • [Presentation] 前景の運動と背景の外観を併用した複数映像からの共通動作区間の検出2017

    • Author(s)
      河村圭将,中村和晃,新田直子,馬場口登
    • Organizer
      電子情報通信学会 パターン認識・メディア理解研究会
    • Place of Presentation
      名城大学(愛知県名古屋市)
    • Year and Date
      2017-03-20
    • Related Report
      2016 Annual Research Report
  • [Presentation] ジャンク画像を考慮したマルチモーダルトピックモデルによる概念間距離の算出2017

    • Author(s)
      長澤優佑,中村和晃,新田直子,馬場口登
    • Organizer
      電子情報通信学会 パターン認識・メディア理解研究会
    • Place of Presentation
      名城大学(愛知県名古屋市)
    • Year and Date
      2017-03-20
    • Related Report
      2016 Annual Research Report
  • [Presentation] Motion Prediction from Still Images Considering the Ambiguity of the Relationship Between Appearance and Motion Features2016

    • Author(s)
      Christian Bender-Saebelkampf, Kazuaki Nakamura, Naoko Nitta, and Noboru Babaguchi
    • Organizer
      19th Meeting on Image Recognition and Understanding (MIRU2016)
    • Place of Presentation
      アクトシティ浜松(静岡県浜松市)
    • Year and Date
      2016-08-01
    • Related Report
      2016 Annual Research Report
  • [Presentation] 動作の階層構造を考慮して投票法に基づく人間動作の時間的スポッティング2016

    • Author(s)
      原啓太,中村和晃,馬場口登
    • Organizer
      電子情報通信学会パターン認識・メディア理解研究会
    • Place of Presentation
      産業技術総合研究所(臨海副都心センター),東京都
    • Year and Date
      2016-03-24
    • Related Report
      2015 Research-status Report
  • [Presentation] 類似性評価の観点の多様性を考慮した概念間類似度の算出2016

    • Author(s)
      三輪智宏,中村和晃,馬場口登
    • Organizer
      電子情報通信学会2016年総合大会
    • Place of Presentation
      九州大学,福岡県
    • Year and Date
      2016-03-15
    • Related Report
      2015 Research-status Report
  • [Presentation] 画像信頼度の反復推定に基づく概念間類似度の算出2015

    • Author(s)
      長澤優佑,中村和晃,馬場口登
    • Organizer
      電子情報通信学会パターン認識・メディア理解研究会
    • Place of Presentation
      信州大学,長野県
    • Year and Date
      2015-12-21
    • Related Report
      2015 Research-status Report
  • [Presentation] Similarity Measurement of Human Action Videos Using Image-Based Models of Diverse Concepts2015

    • Author(s)
      Keisuke Kawamura, Kazuaki Nakamura, and Noboru Babaguchi
    • Organizer
      The 18th Meeting on Imagge Recognition and Understanding (MIRU2015)
    • Place of Presentation
      Osaka, Japan
    • Year and Date
      2015-07-27 – 2015-07-30
    • Related Report
      2014 Research-status Report
  • [Presentation] Temporal Spotting of Human Actions from Videos Containing Actor's Unintentional Motions2015

    • Author(s)
      Keita Hara, Kazuaki Nakamura, and Noboru Babaguchi
    • Organizer
      IEEE International Conference on Multimedia and Expo 2015 (ICME2015)
    • Place of Presentation
      Torino, Italy
    • Year and Date
      2015-06-29 – 2015-07-03
    • Related Report
      2014 Research-status Report

URL: 

Published: 2014-04-04   Modified: 2018-03-22  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi