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

2013 Fiscal Year Final Research Report

Video Retrieval System based on Machine Learning

Research Project

  • PDF
Project/Area Number 23300038
Research Category

Grant-in-Aid for Scientific Research (B)

Allocation TypeSingle-year Grants
Section一般
Research Field Media informatics/Database
Research InstitutionKobe University

Principal Investigator

UEHARA Kuniaki  神戸大学, システム情報学研究科, 教授 (60160206)

Co-Investigator(Kenkyū-buntansha) SHIRAHAMA Kimiaki  日本学術振興会, 海外特別研究員 (30467675)
Project Period (FY) 2011-04-01 – 2014-03-31
Keywordsマルチメディア / 機械学習 / 映像データ / 映像検索
Research Abstract

Query-By-Example (QBE) can be considered as a machine learning problem. Here, given videos for a query, a classifier is built to discriminate between relevant and irrelevant videos based on features like color, edge and motion. This research has explored QBE from the perspectives of machine learning, such as training examples, features, learning algorithms and data size. As a result, we have developed a fast and accurate method which can retrieve videos relevant to a query from a large amount video data. Furthermore, by applying the developed method to object recognition, we have achieved the highest performance at TRECVID 2012 that is a NIST-sponsored annual worldwide competition on video analysis.

  • Research Products

    (17 results)

All 2013 2012 2011 Other

All Journal Article (5 results) (of which Peer Reviewed: 5 results) Presentation (8 results) Remarks (4 results)

  • [Journal Article] 行列演算に基づく高速かつ厳密な大規模映像データ処理2013

    • Author(s)
      白浜公章, 上原邦昭
    • Journal Title

      映像情報メディア学会誌

      Volume: Vol. 67, No. 7 Pages: J241-J251

    • DOI

      10.3169/itej.67.J241

    • Peer Reviewed
  • [Journal Article] ラフ集合理論を用いたクエリの帰納的定義に基づく例示映像検索2012

    • Author(s)
      白浜公章, 松岡悠太, 上原邦昭
    • Journal Title

      映像情報メディア学会誌

      Volume: Vol. 66, No. 5 Pages: J124-J135

    • DOI

      10.3169/itej.66.J124

    • Peer Reviewed
  • [Journal Article] Constructing and Utilizing Video Ontology for Accurate and Fast Retrieval2011

    • Author(s)
      Kimiaki Shirahama and Kuniaki Uehara
    • Journal Title

      International Journal of Multimedia Data Engineering and Management (IJMDEM)

      Volume: Vol. 2, No. 4 Pages: 59-75

    • DOI

      10.4018/jmdem.2011100104

    • Peer Reviewed
  • [Journal Article] Event Retrieval in Video Archives Using Rough Set Theory and Partially Supervised Learning2011

    • Author(s)
      Kimiaki Shirahama, Yuta Matsuoka and Kuniaki Uehara
    • Journal Title

      Multimedia Tools and Applications

      Volume: Vol. 57, No. 1 Pages: 145-173

    • DOI

      10.1007/s11042-011-0727-z

    • Peer Reviewed
  • [Journal Article] Hybrid Negative Example Selection Using Visual and Conceptual Features

    • Author(s)
      Kimiaki Shirahama, Yuta Matsuoka and Kuniaki Uehara
    • Journal Title

      Multimedia Tools and Applications

    • DOI

      10.1007/s11042-011-0886-y

    • Peer Reviewed
  • [Presentation] University of Siegen, Kobe University, and Muroran Institute of Technology at TRECVID 2013 Multimedia Event Detection2013

    • Author(s)
      Kimiaki Shirahama, Chen Li, Marcin Grzegorzek, Kuniaki Uehara
    • Organizer
      TREC Video Retrieval Evaluation (TRECVID) 2013 Workshop
    • Place of Presentation
      Maryland, US
    • Year and Date
      2013-11-21
  • [Presentation] Video Retrieval by Learning Uncertainties in Concept Detection from Imbalanced Annotation Data2013

    • Author(s)
      Kimiaki Shirahama, Kenji Kumabuchi and Kuniaki Uehara
    • Organizer
      The Fifth International Conferences on Advances in Multimedia(MMEDIA 2013)
    • Place of Presentation
      Venice, Italy
    • Year and Date
      2013-04-22
  • [Presentation] Kobe University and Muroran Institute of Technology at TRECVID 2012 Semantic Indexing Task2012

    • Author(s)
      Kimiaki Shirahama and Kuniaki Uehara
    • Organizer
      TREC Video Retrieval Evaluation (TRECVID) 2012 Workshop
    • Place of Presentation
      Maryland, US
    • Year and Date
      2012-11-26
  • [Presentation] Examining the Applicability of Virtual Reality Technique for Video Retrieval2012

    • Author(s)
      Kimiaki Shirahama, Kuniaki Uehara and Marcin Grzegorzek
    • Organizer
      The 10th Workshop on Content-Based Multimedia Indexing (CBMI 2012)
    • Place of Presentation
      Annecy France
    • Year and Date
      2012-06-29
  • [Presentation] Kobe University at TRECVID 2011 Semantic Indexing and Multimedia Event Detection2011

    • Author(s)
      Kimiaki Shirahama, Lin Yanpeng and Kuniaki Uehara
    • Organizer
      TREC Video Retrieval Evaluation (TRECVID) 2011 Workshop
    • Place of Presentation
      Maryland, US
    • Year and Date
      2011-12-06
  • [Presentation] Utilizing Video Ontology for Fast and Accurate Query-by-Example Retrieval2011

    • Author(s)
      Kimiaki Shirahama and Kuniaki Uehara
    • Organizer
      The IEEE International Workshop on Semantic Multimedia in conjunction with the Fifth IEEE International Conference on Semantic Computing
    • Place of Presentation
      California, US
    • Year and Date
      2011-09-21
  • [Presentation] Effectiveness of Video Ontology in Query by Example Approach2011

    • Author(s)
      Kimiaki Shirahama and Kuniaki Uehara
    • Organizer
      The Seventh International Conference on Active Media Technology (AMT 2011)
    • Place of Presentation
      Lanzhou, China
    • Year and Date
      2011-09-07
  • [Presentation] Video Retrieval by Managing Uncertainty in Concept Detection using Dempster-Shafer Theory2011

    • Author(s)
      Kimiaki Shirahama, Kenji Kumabuchi and Kuniaki Uehara
    • Organizer
      The Fourth International Conferences on Advances in Multimedia (MMEDIA 2012)
    • Place of Presentation
      Chamonix/Mont Blanc, France
    • Year and Date
      2011-05-01
  • [Remarks] TRECVID2012で開発した物体認識手法の詳細は, 以下のNISTサイトで公開されている.

  • [Remarks] 意味イ ンデキシング部門の概要, 及び各研究機関で開発さ れた手法の順位

    • URL

      http://www-nlpir.nist.gov/projects/tvpubs/tv12.slides/tv12.sin.slides.pdf

  • [Remarks] 開発した物体認識手法に関する論文

    • URL

      http://www-nlpir.nist.gov/projects/tvpubs/tv12.papers/kobe-muroran.pdf

  • [Remarks] 開発した物体認識手法に関する講演資料

    • URL

      http://www-nlpir.nist.gov/projects/tvpubs/tv12.slides/tv12.kobe-muroran.sin.slides.pdf

URL: 

Published: 2015-06-25  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi