An Analysis on Locality of Relations Between Images and Visual Conceps by Mining of Large-Scale Geo-tagged Images
Project/Area Number |
24300036
|
Research Category |
Grant-in-Aid for Scientific Research (B)
|
Allocation Type | Partial Multi-year Fund |
Section | 一般 |
Research Field |
Media informatics/Database
|
Research Institution | The University of Electro-Communications |
Principal Investigator |
YANAI KEIJI 電気通信大学, 情報理工学(系)研究科, 教授 (20301179)
|
Project Period (FY) |
2012-04-01 – 2016-03-31
|
Project Status |
Completed (Fiscal Year 2015)
|
Budget Amount *help |
¥17,290,000 (Direct Cost: ¥13,300,000、Indirect Cost: ¥3,990,000)
Fiscal Year 2015: ¥4,030,000 (Direct Cost: ¥3,100,000、Indirect Cost: ¥930,000)
Fiscal Year 2014: ¥4,420,000 (Direct Cost: ¥3,400,000、Indirect Cost: ¥1,020,000)
Fiscal Year 2013: ¥3,900,000 (Direct Cost: ¥3,000,000、Indirect Cost: ¥900,000)
Fiscal Year 2012: ¥4,940,000 (Direct Cost: ¥3,800,000、Indirect Cost: ¥1,140,000)
|
Keywords | 画像マイニング / 視覚概念分析 / 画像認識 / 位置情報 / 物体認識 / Web画像マイニング / 位置情報画像 / ジオタグ / Twitter画像 / ソーシャルメディア / 大規模データ処理 |
Outline of Final Research Achievements |
In this project, we studied geotagged image mining which explored location dependency of visual concepts. We obtained the following results: (1) We developed method on location-dependency analysis of geotagged image data collected from social media such as Flickr and Twitter. (2) We proposed a method for location-dependent image ranking method, GeoVisualRank. (3) We made large-scale experiments with Flickr geotagged images data. (4) We collected a great many of geotagged photos from the Twitter stream for about five years, and made large-scale experiments with that data.
|
Report
(5 results)
Research Products
(25 results)