GeoWINE: Geolocation based Wiki, Image, News and Event Retrieval

  title={GeoWINE: Geolocation based Wiki, Image, News and Event Retrieval},
  author={Golsa Tahmasebzadeh and Endri Kacupaj and Eric Muller-Budack and Sherzod Hakimov and Jens Lehmann and Ralph Ewerth},
  journal={Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval},
  • Golsa Tahmasebzadeh, Endri Kacupaj, R. Ewerth
  • Published 30 April 2021
  • Computer Science
  • Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval
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… 

Figures and Tables from this paper


Wikidata: a free collaborative knowledgebase
This collaboratively edited knowledgebase provides a common source of data for Wikipedia, and everyone else, to help improve the quality of the encyclopedia.
OEKG: The Open Event Knowledge Graph
This paper presents the Open Event Knowledge Graph (OEKG), a multilingual, event-centric, temporal knowledge graph composed of seven different data sets from multiple application domains, including question answering, entity recommendation and named entity recognition.
Multimodal news analytics using measures of cross-modal entity and context consistency
A multimodal approach to quantify the entity coherence between image and text in real-world news and an approach that quantifies contextual image-text relations is introduced.
Awjedni: A Reverse-Image-Search Application
Awjedni is a reverse-image search application compatible with iOS and Android smartphones built to provide an efficient way to search millions of products on the internet using images only.
MLM: A Benchmark Dataset for Multitask Learning with Multiple Languages and Modalities
The value of the resource in developing novel applications in the digital humanities with a motivating use case is demonstrated and a benchmark set of tasks to retrieve modalities and locate entities in the dataset is specified.
Google Landmarks Dataset v2 – A Large-Scale Benchmark for Instance-Level Recognition and Retrieval
This work introduces the Google Landmarks Dataset v2 (GLDv2), a new benchmark for large-scale, fine-grained instance recognition and image retrieval in the domain of human-made and natural landmarks, and demonstrates the suitability of the dataset for transfer learning by showing that image embeddings trained on it achieve competitive retrieval performance on independent datasets.
Multimodal Analytics for Real-world News using Measures of Cross-modal Entity Consistency
This paper presents a multimodal approach to quantify the entity coherence between image and text in real-world news, and suggests several measures to calculate the cross-modal similarity of these entities with the news photo, using state of theart computer vision approaches.
QATM: Quality-Aware Template Matching for Deep Learning
This paper proposes a novel quality-aware template matching method, which is not only used as a standalone template matching algorithm, but also a trainable layer that can be easily plugged in any deep neural network.
EventKG - the Hub of Event Knowledge on the Web - and Biographical Timeline Generation
An application of EventKG to biographical timeline generation, where it is demonstrated to adopt a distant supervision method to identify relations most relevant for an entity biography and the effectiveness of the proposed biographical Timeline generation method is demonstrated.
Geolocation Estimation of Photos Using a Hierarchical Model and Scene Classification
This paper proposes to exploit hierarchical knowledge of multiple partitionings and additionally extract and take the photo’s scene content into account and incorporate contextual information at different spatial resolutions as well as more specific features for various environmental settings are incorporated in the learning process of the convolutional neural network.