Details
| Original language | English |
|---|---|
| Title of host publication | SIGIR 2021 |
| Subtitle of host publication | Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval |
| Pages | 2565-2569 |
| Number of pages | 5 |
| ISBN (electronic) | 9781450380379 |
| Publication status | Published - 11 Jul 2021 |
| Event | 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2021 - Virtual, Online, Canada Duration: 11 Jul 2021 → 15 Jul 2021 |
Publication series
| Name | SIGIR 2021 - Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval |
|---|
Abstract
In the context of social media, geolocation inference on news or events has become a very important task. In this paper, we present the GeoWINE (Geolocation-based Wiki-Image-News-Event retrieval) demonstrator, an effective modular system for multimodal retrieval which expects only a single image as input. The GeoWINE system consists of five modules in order to retrieve related information from various sources. The first module is a state-of-the-art model for geolocation estimation of images. The second module performs a geospatial-based query for entity retrieval using the Wikidata knowledge graph. The third module exploits four different image embedding representations, which are used to retrieve most similar entities compared to the input image. The last two modules perform news and event retrieval from EventRegistry and the Open Event Knowledge Graph (OEKG). GeoWINE provides an intuitive interface for end-users and is insightful for experts for reconfiguration to individual setups. The GeoWINE achieves promising results in entity label prediction for images on Google Landmarks dataset. The demonstrator is publicly available at http://cleopatra.ijs.si/geowine/.
Keywords
- computer vision, geolocation estimation, knowledge graph
ASJC Scopus subject areas
- Computer Science(all)
- Software
- Computer Science(all)
- Computer Graphics and Computer-Aided Design
- Computer Science(all)
- Information Systems
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
SIGIR 2021: Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval. 2021. p. 2565-2569 3462786 (SIGIR 2021 - Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval).
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - GeoWINE
T2 - 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2021
AU - Tahmasebzadeh, Golsa
AU - Kacupaj, Endri
AU - Müller-Budack, Eric
AU - Hakimov, Sherzod
AU - Ewerth, Ralph
AU - Lehmann, Jens
N1 - This work has received funding from the European Union’s Horizon 2020 research and innovation program under the Marie Skłodowska- Curie grant agreement No. 812997 (CLEOPATRA ITN).
PY - 2021/7/11
Y1 - 2021/7/11
N2 - In the context of social media, geolocation inference on news or events has become a very important task. In this paper, we present the GeoWINE (Geolocation-based Wiki-Image-News-Event retrieval) demonstrator, an effective modular system for multimodal retrieval which expects only a single image as input. The GeoWINE system consists of five modules in order to retrieve related information from various sources. The first module is a state-of-the-art model for geolocation estimation of images. The second module performs a geospatial-based query for entity retrieval using the Wikidata knowledge graph. The third module exploits four different image embedding representations, which are used to retrieve most similar entities compared to the input image. The last two modules perform news and event retrieval from EventRegistry and the Open Event Knowledge Graph (OEKG). GeoWINE provides an intuitive interface for end-users and is insightful for experts for reconfiguration to individual setups. The GeoWINE achieves promising results in entity label prediction for images on Google Landmarks dataset. The demonstrator is publicly available at http://cleopatra.ijs.si/geowine/.
AB - In the context of social media, geolocation inference on news or events has become a very important task. In this paper, we present the GeoWINE (Geolocation-based Wiki-Image-News-Event retrieval) demonstrator, an effective modular system for multimodal retrieval which expects only a single image as input. The GeoWINE system consists of five modules in order to retrieve related information from various sources. The first module is a state-of-the-art model for geolocation estimation of images. The second module performs a geospatial-based query for entity retrieval using the Wikidata knowledge graph. The third module exploits four different image embedding representations, which are used to retrieve most similar entities compared to the input image. The last two modules perform news and event retrieval from EventRegistry and the Open Event Knowledge Graph (OEKG). GeoWINE provides an intuitive interface for end-users and is insightful for experts for reconfiguration to individual setups. The GeoWINE achieves promising results in entity label prediction for images on Google Landmarks dataset. The demonstrator is publicly available at http://cleopatra.ijs.si/geowine/.
KW - computer vision
KW - geolocation estimation
KW - knowledge graph
UR - http://www.scopus.com/inward/record.url?scp=85111642975&partnerID=8YFLogxK
U2 - https://doi.org/10.48550/arXiv.2104.14994
DO - https://doi.org/10.48550/arXiv.2104.14994
M3 - Conference contribution
AN - SCOPUS:85111642975
T3 - SIGIR 2021 - Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval
SP - 2565
EP - 2569
BT - SIGIR 2021
Y2 - 11 July 2021 through 15 July 2021
ER -