A proxy mechanism to capture a present situation of the society
Project/Area Number |
24300074
|
Research Category |
Grant-in-Aid for Scientific Research (B)
|
Allocation Type | Partial Multi-year Fund |
Section | 一般 |
Research Field |
Perception information processing/Intelligent robotics
|
Research Institution | Kyushu University |
Principal Investigator |
|
Co-Investigator(Kenkyū-buntansha) |
NAGAHARA Hajime 九州大学, 大学院システム情報科学研究院, 准教授 (80362648)
SHIMADA Atsushi 九州大学, 基幹教育院, 准教授 (80452811)
UCHIYAMA Hideaki 九州大学, 大学院システム情報科学研究院, 助教 (90735804)
|
Research Collaborator |
XU Xing 九州大学, 大学院システム情報科学府, 博士課程
|
Project Period (FY) |
2012-04-01 – 2016-03-31
|
Project Status |
Completed (Fiscal Year 2015)
|
Budget Amount *help |
¥17,940,000 (Direct Cost: ¥13,800,000、Indirect Cost: ¥4,140,000)
Fiscal Year 2014: ¥5,200,000 (Direct Cost: ¥4,000,000、Indirect Cost: ¥1,200,000)
Fiscal Year 2013: ¥5,720,000 (Direct Cost: ¥4,400,000、Indirect Cost: ¥1,320,000)
Fiscal Year 2012: ¥7,020,000 (Direct Cost: ¥5,400,000、Indirect Cost: ¥1,620,000)
|
Keywords | クロスモーダル検索 / 画像アノテーション / 画像検索 / 画像認識 / 情報検索 / 整合性評価 |
Outline of Final Research Achievements |
In this research, a new communication mechanism between people who require some information and people who can provide the information. We have focused on how to utilize image media which can be easily acquired by smartphones, We suppose transformation of modality can be applied to achieve an efficient and effective information transfer. Especially, image annotation techniques can be used as modality transformation mechanism, and we have researched mainly to develop new algorithms related to image annotation, We have constructed correlated topic model to improve image annotation performance, image annotation model from incomplete training data set, cross-modal retrieval framework realizing mutual retrieval of multi-modal data, and summarization of users' captured images based on a model of human's image capturing process. These research results have presented in several top-level international conferences and journals.
|
Report
(5 results)
Research Products
(14 results)