2023 Fiscal Year Final Research Report
Graph clustering based on multimodal data fusion and its application to retrieval
| Project/Area Number |
21K17861
|
|---|
| Research Category |
Grant-in-Aid for Early-Career Scientists
|
| Allocation Type | Multi-year Fund |
|---|
| Review Section |
Basic Section 62020:Web informatics and service informatics-related
|
|---|
| Research Institution | Nagaoka University of Technology |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2021-04-01 – 2024-03-31
|
| Keywords | マルチモーダル解析 / クラスタリング / グラフ理論 / 複雑ネットワーク / 情報検索 |
|---|
| Outline of Final Research Achievements |
This research aimed to develop multimodal data integration methods that can deal with missing modalities and improve the accuracy of graph clustering to enable users to search for desired information. We conducted researches about “construction of a simultaneous optimization method for latent feature extraction and graph clustering with missing modality interpolation,”' “construction of a graph clustering method that introduces confidence estimation,” and “application of graph clustering to information retrieval.” We succeeded in developing these methods and achieved the original purpose.
|
| Free Research Field |
マルチメディアデータ解析
|
| Academic Significance and Societal Importance of the Research Achievements |
ソーシャルネットワーキングサービス上の映像やタグ付き画像等のマルチモーダルデータが増加し続けている．蓄積されたビッグデータは，ウェブ情報学や計算社会科学などの様々な領域において活用されている．しかしながら，情報検索を行うユーザに視点に立つと，自らが望む情報を検索することが困難な情報洪水と呼ばれる問題を引き起こしている．本研究では，情報洪水問題の解決に資する基盤技術の構築に成功した．
|
