Proceedings of the 19th International Conference on World Wide Web 2010
DOI: 10.1145/1772690.1772904
|View full text |Cite
|
Sign up to set email alerts
|

Diversifying landmark image search results by learning interested views from community photos

Abstract: In this paper, we demonstrate a novel landmark photo search and browsing system, Agate, which ranks landmark image search results considering their relevance, diversity and quality. Agate learns from community photos the most interested aspects and related activities of a landmark, and generates adaptively a Table of Content (TOC) as a summary of the attractions to facilitate user browsing. Image search results are thus re-ranked with the TOC so as to ensure a quick overview of the attractions of the landmarks… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1

Citation Types

0
2
0
1

Year Published

2010
2010
2017
2017

Publication Types

Select...
3
3
2

Relationship

0
8

Authors

Journals

citations
Cited by 15 publications
(3 citation statements)
references
References 7 publications
0
2
0
1
Order By: Relevance
“…In particular, the method uses the statistics of temporal metadata in geo-referenced images, trying to estimate the duration of the visit of a user in a specific location. In [11], in addition to geo-referenced information, the authors exploit a different type of metadata: the user interests. The system search for images on both a generic search engine and Flickr, and Flickr images are sorted according to the users preferences.…”
Section: A State Of the Artmentioning
confidence: 99%
“…In particular, the method uses the statistics of temporal metadata in geo-referenced images, trying to estimate the duration of the visit of a user in a specific location. In [11], in addition to geo-referenced information, the authors exploit a different type of metadata: the user interests. The system search for images on both a generic search engine and Flickr, and Flickr images are sorted according to the users preferences.…”
Section: A State Of the Artmentioning
confidence: 99%
“…Recent years, as the rapid development of Internet technology and tourism, the relevant pictures and their information become more and more valuable and indispensable. How to mine and obtain the information from those pictures is always a hot pot in data mining, image processing and also related academic fields [1][2][3].…”
Section: Introductionmentioning
confidence: 99%
“…΄Εχει αποδειχτεί ότι οι εικόνες δηµοφιλών σηµείων ενδιαφέροντος σε διάφορες περιοχές του κόσµου µπορούν επιτυχώς να ανακτηθούν από µεγάλα σύνολα επισηµασµένων εικόνων. Επιπρόσθετα, για κάθε εντοπισµένο σηµείο µπορούν να ταυτοποιηθούν διαφορετικές αντιπροσωπευτικές εικόνες-στιγµιότυπα (Kennedy & Naaman, 2008) (Ren, Yu, Wang, Zhang, & Ma, 2010), οδηγώντας σε µεγαλύτερης ποικιλίας εικονογραφικές περιγραφές. Παρά το τεράστιο ενδιαφέρον σε αυτό το πρόβληµα, οι περισσότερες από τις υπάρχουσες ερευνητικές εργασίες περιορίζονται στην ανακάλυψη εξέχοντων σηµείων ενδιαφέροντος τα οποία αντιπροσωπεύονται επαρκώς στις συλλογές εικόνων.…”
Section: εισαγωγήunclassified