Filters








61 Hits in 8.9 sec

Georeferencing Flickr Photos Using Language Models at Different Levels of Granularity: An Evidence Based Approach

Olivier Van Laere, Steven Schockaert, Barth Dhoedt
2012 Social Science Research Network  
To this end, we consider the idea of training language models at different levels of granularity, and combining the evidence provided by these language models using Dempster and Shafer's theory of evidence  ...  Thus there is a need for adaptive techniques that assign locations to photos at the right level of granularity, or, in some cases, even refrain from making any estimations regarding location at all.  ...  Conclusions We have proposed an approach to georeferencing Flickr photos which combines the evidence provided by different language models using Dempster-Shafer evidence theory.  ... 
doi:10.2139/ssrn.3198976 fatcat:jsprxuvngzdmliyzh6oiml2sum

Georeferencing Flickr photos using language models at different levels of granularity: An evidence based approach

Olivier Van Laere, Steven Schockaert, Bart Dhoedt
2012 Journal of Web Semantics  
To this end, we consider the idea of training language models at different levels of granularity, and combining the evidence provided by these language models using Dempster and Shafer's theory of evidence  ...  Thus there is a need for adaptive techniques that assign locations to photos at the right level of granularity, or, in some cases, even refrain from making any estimations regarding location at all.  ...  Conclusions We have proposed an approach to georeferencing Flickr photos which combines the evidence provided by different language models using Dempster-Shafer evidence theory.  ... 
doi:10.1016/j.websem.2012.05.005 fatcat:qgxqclbgqveifidu5wj7xpdiuu

Georeferencing Flickr resources based on textual meta-data

Olivier Van Laere, Steven Schockaert, Bart Dhoedt
2013 Information Sciences  
Much attention has been focused on Flickr photos and videos, for which it was found that language modeling approaches are particularly suitable.  ...  In particular, state-of-the art systems for georeferencing Flickr photos tend to cluster the locations on Earth in a relatively small set of disjoint regions, apply feature selection to identify location-relevant  ...  We would also like to thank the organizers of the MediaEval workshop and the Placing Task organizers in particular for providing us with the Flickr dataset.  ... 
doi:10.1016/j.ins.2013.02.045 fatcat:conaztnl3bfabisnco55givhya

Towards automated georeferencing of Flickr photos

Olivier Van Laere, Steven Schockaert, Bart Dhoedt
2010 Proceedings of the 6th Workshop on Geographic Information Retrieval - GIR '10  
Based on this observation, we stress the importance of adaptive approaches that estimate locations at different granularities for different photos.  ...  Using an approach based on k-medoids clustering and Naive Bayes classification, we demonstrate that the task is feasible, although high accuracy can only be expected for a portion of all photos.  ...  RELATED WORK By far the most similar work to ours is [13] , where a language modeling approach is used to predict the location of Flickr images based on their tags.  ... 
doi:10.1145/1722080.1722087 dblp:conf/gir/LaereSD10 fatcat:uvzfjepiofho5nji5w5dzeob3m

Exploring place through user-generated content: Using Flickr to describe city cores

Ross Purves, Livia Hollenstein
2010 Journal of Spatial Information Science  
Using Flickr metadata, it is possible not only to describe the use of the term Downtown across the USA, but also to explore the borders of city center neighborhoods at the level of individual cities, whilst  ...  at the granularity of city names being by far the most common.  ...  Jo Wood, David Mark, Clair Davies, and Alistair Edwardes are thanked for useful suggestions with respect to this research.  ... 
doi:10.5311/josis.2010.1.3 fatcat:ihhwavldpbeydejchaja4ye4la

Combining Multi-resolution Evidence for Georeferencing Flickr Images [chapter]

Olivier Van Laere, Steven Schockaert, Bart Dhoedt
2010 Lecture Notes in Computer Science  
In particular, we estimate the location of Flickr photos, based on their tags, at four different scales, ranging from a city-level granularity to fine-grained intra-city areas.  ...  We explore the task of determining the geographic location of photos on Flickr, using combined evidence from Naive Bayes classifiers that are trained at different spatial resolutions.  ...  Acknowledgments Steven Schockaert was funded as a postdoctoral fellow of the Research Foundation -Flanders (FWO).  ... 
doi:10.1007/978-3-642-15951-0_32 fatcat:zosbgcsddradfbfil6u3njcsce

GIS-Based Emotional Computing: A Review of Quantitative Approaches to Measure the Emotion Layer of Human–Environment Relationships

Yingjing Huang, Teng Fei, Mei-Po Kwan, Yuhao Kang, Jun Li, Yizhuo Li, Xiang Li, Meng Bian
2020 ISPRS International Journal of Geo-Information  
emotions using AI-based emotional computing technics such as natural language processing (NLP) and computer vision (CV), and (3) visualizing and analyzing the spatiotemporal patterns with GIS tools.  ...  In recent years, with the growing accessibility of abundant contextual emotion information, which is benefited by the numerous georeferenced user-generated content and the maturity of artificial intelligence  ...  Additionally, Flickr photos with geotags are traced and analyzed to extract the trend in the changes of human emotions between 2004 and 2014 [75] at the international level.  ... 
doi:10.3390/ijgi9090551 fatcat:dpbqacn6zvbzze42i2y4itfdeu

Placing images on the world map

Claudia Hauff, Geert-Jan Houben
2012 Proceedings of the 35th international ACM SIGIR conference on Research and development in information retrieval - SIGIR '12  
Large numbers of images uploaded to platforms such as Flickr do not contain GPS-based latitude/longitude coordinates.  ...  Moreover, we also find another type of additional information useful: population density data.  ...  In contrast to [21] , the location estimation is performed on different levels of granularity (city granularity, street level granularity, etc.) and the evidence obtained over the different granularities  ... 
doi:10.1145/2348283.2348376 dblp:conf/sigir/HauffH12 fatcat:3pqy2otn5bdtdar2falolslffa

E2mC: Improving Emergency Management Service Practice through Social Media and Crowdsourcing Analysis in Near Real Time

Clemens Havas, Bernd Resch, Chiara Francalanci, Barbara Pernici, Gabriele Scalia, Jose Fernandez-Marquez, Tim Van Achte, Gunter Zeug, Maria Mondardini, Domenico Grandoni, Birgit Kirsch, Milan Kalas (+2 others)
2017 Sensors  
In the next sections the main components of the architecture are described to give an insight of the methods integrated into the components.  ...  The advantage of these new kinds of data is that they are continuously produced in a timely fashion because users actively participate throughout an event and share related information.  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/s17122766 pmid:29186080 pmcid:PMC5751655 fatcat:2trtqzcvxjcnrafhzamvi7k4fa

Geographic Information Retrieval

Ross Purves, Christopher Jones
2011 SIGSPATIAL Special  
The SIGSPATIAL Special is the newsletter of the Association for Computing Machinery (ACM) Special Interest Group on Spatial Information (SIGSPATIAL).  ...  ACM SIGSPATIAL addresses issues related to the acquisition, management, and processing of spatially-related information with a focus on algorithmic, geometric, and visual considerations.  ...  early draft of this work.  ... 
doi:10.1145/2047296.2047297 fatcat:npmfk7kdhrailfrgyyaszkj6wi

Towards A Crowdsourced Supervision Of The Analysis Of User-Generated Geographic Content: Engaging Citizens In Discovering Urban Places

Frank O. Ostermann, Gustavo Garcia-Chapeton, Menno-Jan Kraak, Raul Zurita-Milla
2018 Zenodo  
For the pilot study, we adapt an approach to find semantically distinct places in UGGC.  ...  This paper presents a conceptual model and a proof-of-concept implementation of a novel approach to engage citizens in supervising the analysis of user-generated geographic content (UGGC).  ...  Collect Flickr photo meta-data The initial step is to collect georeference Flickr image meta-data about the study area using the public API, and store the retrieved information in a PostGIS database.  ... 
doi:10.5281/zenodo.1215682 fatcat:pnlhijoocjcjrekjehat5wmzdq

On the Accuracy of Hyper-local Geotagging of Social Media Content [article]

David Flatow, Mor Naaman, Ke Eddie Xie, Yana Volkovich, Yaron Kanza
2015 arXiv   pre-print
Our findings show the potential and the bounds of a data-driven approach to geotag short social media texts, and offer implications for all applications that use data-driven approaches to locate content  ...  We present a data- driven approach for identifying non-geotagged content items that can be associated with a hyper-local geographic area by modeling the location distributions of hyper-local n-grams that  ...  Our goal is identifying content items that were posted from specific geographic areas, with finer granularity than city-level. Some studies applied traditional language models to geotagging, e.g.  ... 
arXiv:1409.1461v2 fatcat:hsepshuanrcwbdkvdtllruspha

On the Accuracy of Hyper-local Geotagging of Social Media Content

David Flatow, Mor Naaman, Ke Eddie Xie, Yana Volkovich, Yaron Kanza
2015 Proceedings of the Eighth ACM International Conference on Web Search and Data Mining - WSDM '15  
Our findings show the potential and the bounds of a data-driven approach to assigning location data to short social media texts, and offer implications for all applications that use data-driven approaches  ...  We present a datadriven approach for identifying non-geotagged content items that can be associated with a hyper-local geographic area by modeling the location distributions of n-grams that appear in the  ...  Our goal is identifying content items that were posted from specific geographic areas, with finer granularity than city-level. Some studies applied traditional language models to geotagging, e.g.  ... 
doi:10.1145/2684822.2685296 dblp:conf/wsdm/FlatowNXVK15 fatcat:bwfmead62jdibog6qmthyrrlwe

Social media data for conservation science: A methodological overview

Tuuli Toivonen, Vuokko Heikinheimo, Christoph Fink, Anna Hausmann, Tuomo Hiippala, Olle Järv, Henrikki Tenkanen, Enrico Di Minin
2019 Biological Conservation  
However, the use of advanced methods for analysing social media is still limited, and social media data are not used to their full potential.  ...  Recently, social media have become an increasingly important source of information on human-nature interactions.  ...  Supplementary material Supplementary material (more results and further method descriptions) to this article can be found online at https://doi.org/10.1016/j. biocon.2019.01.023.  ... 
doi:10.1016/j.biocon.2019.01.023 fatcat:nxs2oh6cfbaeln2jiyg4zg5uby

From image descriptions to perceived sounds and sources in landscape: Analyzing aural experience through text

Olga Chesnokova, Ross S. Purves
2018 Applied Geography  
Our results show that sentiment classification gives an additional level of understanding of descriptions classified into different types of sound emitters.  ...  Our results show that sentiment classification gives an additional level of understanding of descriptions classified into different types of sound emitters.  ...  OC is also grateful to Lone Kristensen and Veerle Van Eetvelde for feedback on early versions of this work. Finally, we thank the reviewers for their useful suggestions.  ... 
doi:10.1016/j.apgeog.2018.02.014 fatcat:nlfdh6vhbrdlvoauwi6bgtujbi
« Previous Showing results 1 — 15 out of 61 results