World-wide scale geotagged image dataset for automatic image annotation and reverse geotagging

Sergieh, Hatem Mousselly; Watzinger, Daniel; Huber, Bastian; Döller, Mario; Egyed-Zsigmond, Elöd; Kosch, Harald

doi:10.1145/2557642.2563673

Cited by 20 publications

(12 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this section, we introduced the dataset that collected from SNS [12] and used in our work and shows implementation steps to rank locations based on tags of them and its results.…”

Section: Results and Experimental Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Locations Ranking using Page Rank Algorithm

Al-Sultany¹,

Al-Ameer²

2018

IJET

View full text Add to dashboard Cite

Nowadays, large amount of user-generated data can obtained from social media (e.g., Instagram and Flicker) .People sharing their travel experiences with geo-tagged photo through these media, and the photo itself has important information like title, tags and location.Thesetypes of data provide a new perspective for us to understand the contexts of users. In this paper we focused on tourism service by collecting and analyzing geo-tagged photo from the social media to identify the most popular tourist places and rank them based on user location. We used PageRank algorithm that rank locations based on the relation between the locations and a set of tags that discovered by weighting scheme. Thus, an intelligent location-based tourist services can be provide to people. The work experiments have shown encouraging results in terms of ranking the given locations.

show abstract

“…In this section, we introduced the dataset that collected from SNS [12] and used in our work and shows implementation steps to rank locations based on tags of them and its results.…”

Section: Results and Experimental Discussionmentioning

confidence: 99%

“…Our system used dataset taken from [12]. This dataset crawled from Flickr and it consists of a sample of geo-tagged photos with the corresponding file metadatathat consist of image metadata in CSV format that contain information's fieldsabout all images.Each field define a specific information on the image.…”

Section: Data Representationmentioning

confidence: 99%

Locations Ranking using Page Rank Algorithm

Al-Sultany¹,

Al-Ameer²

2018

IJET

View full text Add to dashboard Cite

show abstract

“…types of produced cheese. The second data set is filtered from a Flickr data set with geo-tagged photos [10]. We filtered the data set keeping only Great Britain and Ireland, selected the most frequent tags and removed those that are about the camera or mode in which the photo was taken.…”

Section: Methodsmentioning

confidence: 99%

Geo word clouds

Buchin

Creemers

Lazzarotto

et al. 2016

2016 IEEE Pacific Visualization Symposium (PacificVis)

View full text Add to dashboard Cite

“…In our evaluation, to ensure the comparability and fairness of empirical results, we adopted a publicly accessible dataset [Mousselly-Sergieh et al 2014]. The dataset contains 14.1 million geotagged photos crawled from Flickr, which is currently the largest geotagged image dataset.…”

Section: Data Collectionsmentioning

confidence: 99%

Augmented Collaborative Filtering for Sparseness Reduction in Personalized POI Recommendation

Cui

Shen

Nie

et al. 2017

ACM Trans. Intell. Syst. Technol.

View full text Add to dashboard Cite

As mobile device penetration increases, it has become pervasive for images to be associated with locations in the form of geotags. Geotags bridge the gap between the physical world and the cyberspace, giving rise to new opportunities to extract further insights into user preferences and behaviors. In this article, we aim to exploit geotagged photos from online photo-sharing sites for the purpose of personalized Point-of-Interest (POI) recommendation. Owing to the fact that most users have only very limited travel experiences, data sparseness poses a formidable challenge to personalized POI recommendation. To alleviate data sparseness, we propose to augment current collaborative filtering algorithms along from multiple perspectives. Specifically, hybrid preference cues comprising user-uploaded and user-favored photos are harvested to study users' tastes. Moreover, heterogeneous high-order relationship information is jointly captured from user social networks and POI multimodal contents with hypergraph models. We also build upon the matrix factorization algorithm to integrate the disparate sources of preference and relationship information, and apply our approach to directly optimize user preference rankings. Extensive experiments on a large and publicly accessible dataset well verified the potential of our approach for addressing data sparseness and offering quality recommendations to users, especially for those who have only limited travel experiences.

show abstract

World-wide scale geotagged image dataset for automatic image annotation and reverse geotagging

Cited by 20 publications

References 19 publications

Locations Ranking using Page Rank Algorithm

Locations Ranking using Page Rank Algorithm

Geo word clouds

Augmented Collaborative Filtering for Sparseness Reduction in Personalized POI Recommendation

Contact Info

Product

Resources

About