Spatial and Temporal Clustering of MPEG-7 Based Dozen Dimensional Digital Content
-
- KUO Pei-Jeng
- Yasuda-Aoki Laboratory, The University of Tokyo
-
- AOKI Terumasa
- Yasuda-Aoki Laboratory, The University of Tokyo
-
- YASUDA Hiroshi
- Yasuda-Aoki Laboratory, The University of Tokyo
抄録
In this Paper, we discuss the spatial and temporal relationship among clusters of images grouped by pre-annotated folder names in a consumer digital photograph collection of more than 80,000 images. In previous paper, we have proposed a MPEG-7 based multimedia content description tool which annotates multimedia data with twelve main attributes regarding its semantic representation. The twelve attributes include answers of who, what, when, where, why and how (5W1H) the digital content was produced as well as the respective direction, distance and duration (3D) information. And we define digital multimedia contents including image, video and music embedded with the proposed semantic attributes as Dozen Dimensional Digital Content (DDDC). This discussion indicates how spatial and temporal information closely relate to the clustering of consumer photograph collections and can be used in building future DDDC Library.
収録刊行物
-
- 画像電子学会研究会講演予稿
-
画像電子学会研究会講演予稿 03-05 (0), 57-61, 2003
一般社団法人 画像電子学会
- Tweet
詳細情報 詳細情報について
-
- CRID
- 1390001205598632064
-
- NII論文ID
- 130005441535
-
- 本文言語コード
- en
-
- データソース種別
-
- JaLC
- CiNii Articles
-
- 抄録ライセンスフラグ
- 使用不可