Index Generation of BGM Video Based on Distinctive Comments

フクダ, ヒロキミ, 松本, 和幸, 吉田, 稔, 北, 研二

説明

The purpose of this study is to generate indexes for background music (BGM) based on distinctive comments annotated to BGM videos posted on Nico Nico Videos. Our proposed method detects the end/start positions of the BGM considering the increase/decrease in the number of comments, comments distinctive to the songs, and exclamatory expressions annotated to the videos. The evaluation result indicated that the proposed method could generate correct indexes within a 10 s error for BGM videos less than 40 min long and with annotations of over 30,000 comments.

収録刊行物

International Journal of Advanced Intelligence

International Journal of Advanced Intelligence 10 (1), 113-119, 2018-03

AIA International Advanced Information Institute

キーワード

詳細情報詳細情報について

CRID: 1050020697876372224

NII論文ID: 120006627854

ISSN: 18833918

Web Site: https://tokushima-u.repo.nii.ac.jp/records/2006360

資料種別: journal article

データソース種別

IRDB
CiNii Articles
KAKEN

書き出し

問題の指摘