2015 Fiscal Year Final Research Report
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
|
| 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 |
|---|
| 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.
|
| Free Research Field |
メディア情報学
|
