2019 Fiscal Year Annual Research Report
Participatory Sensing and Felicitous Recommending of Venues
| Project/Area Number |
16K16058
|
|---|
| Research Institution | National Institute of Informatics |
|---|
Principal Investigator |
ュ イ 国立情報学研究所, コンテンツ科学研究系, 特任助教 (00754681)
|
|---|
| Project Period (FY) |
2016-04-01 – 2020-03-31
|
| Keywords | venue discovery / cross-modal retrieval |
|---|
| Outline of Annual Research Achievements |
Fine-grained venue discovery from a photo was almost impossible years ago because we lack reliable venue data sources. Fostered by multimedia technology innovation and mobile user engagements, business-related social multimedia data and information have been expanding with large volumes over the Internet. In this research, we have taken Wikipedia featured articles and photos for venues as basic knowledge to learn a deep correlation model for fine-grained venue discovery from Foursquare photos. This year, We have and developed a demonstration system based on proposed method deep C-DCCA. we also tried to work on some potential methods to improve the reliability of real-world venue discovery such as taking the low-resolution venue photo as the input where the relevant multimodal contents are retrieved.
|
Research Products
(1 results)
