Supporting video search and distribution based on cognitive aspects

2016 Fiscal Year Final Research Report

• Project/Area Number: 15H06887
• Research Category: Grant-in-Aid for Research Activity Start-up
• Allocation Type: Single-year Grants
• Research Field: Multimedia database
• Research Institution: National Institute of Advanced Industrial Science and Technology
• Principal Investigator: Tsukuda Kosetsu 国立研究開発法人産業技術総合研究所, 情報技術研究部門, 研究員 (40760020)
• Project Period (FY): 2015-08-28 – 2017-03-31
• Keywords: 動画検索 / 時刻同期コメント / 認知的尺度 / N次創作 / 派生コンテンツ / ユーザ生成コンテンツ

Outline of Final Research Achievements

The first research topic is video search based on cognitive keywords. We used time-synchronized comments posted to videos and enabled users to search for videos in which viewers post comments such as "cute", "gentle voice", and "great lyrics". Our paper was published in ICDMW 2016. We also released a Web service "Songrium comment alnalysis" (http://comment.songrium.jp/). The second research topic is modeling N-th order derivative creation. We proposed a model to estimate factors that trigger derivative creation. Our paper was published in CIKM 2016. We also released a Web service "Songrium factor analysis" (http://factor.songrium.jp).

Free Research Field

情報検索・知識抽出