Geotagging text content with language models and feature mining

G Kordopatis-Zilos, S Papadopoulos… - Proceedings of the …, 2017 - ieeexplore.ieee.org
The large-scale availability of user-generated content in social media platforms has recently
opened up new possibilities for studying and understanding the geospatial aspects of real …

Geo-distinctive visual element matching for location estimation of images

X Li, M Larson, A Hanjalic - IEEE Transactions on Multimedia, 2017 - ieeexplore.ieee.org
We propose an image representation and matching approach that substantially improves
visual-based location estimation for images. The main novelty of the approach, called …

[PDF][PDF] Knowledge-based and data-driven approaches for geographical information access.

DF Domènech - 2017 - core.ac.uk
Abstract Geographical Information Access (GeoIA) can be defined as a way of retrieving
information from textual collections that includes the automatic analysis and interpretation of …

Knowledge-based and data-driven approaches for geographical information access

D Ferrés Domènech - 2017 - upcommons.upc.edu
Geographical Information Access (GeoIA) can be defined as a way of retrieving information
from textual collections that includes the automatic analysis and interpretation of the …

Feature-centric ranking algorithms for georeferenced video search

H Fritze, A Degbelo, T Brüggentisch… - Proceedings of the 25th …, 2017 - dl.acm.org
While it is commonplace to retrieve photos showing a particular feature (eg through tools
such as Google Pictures or Bing Images), spatial approaches for retrieving videos showing a …

[PDF][PDF] Geo-Locating Images: Where in the world was this picture taken?

A Sy, C Day - 2016 - vision.stanford.edu
Our project focuses on geo-location for a subset of the 2015 MediaEval Placing dataset and
produces comparable performance to existing submissions on the classification task and …

[PDF][PDF] Version Changes

SS CEA, FA CEA, T Michalareas, A Kousaridas… - usemp.eu
This deliverable provides a description of the USEMP multimodal1 annotation, retrieval and
location detection modules implemented during the second iteration of the project. The …