Visual tag authoring: Picture extraction via localized, collaborative tagging

Andrea Bellucci; Stefano Levialdi Ghiron; Ignacio Aedo; Alessio Malizia

doi:10.1145/1385569.1385630

Visual tag authoring: Picture extraction via localized, collaborative tagging

Andrea Bellucci, Stefano Levialdi Ghiron, Ignacio Aedo, Alessio Malizia

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

5 Citations (Scopus)

Abstract

In this work we present a system to encode location based information extracted from a media collection (the Flickr tagging system) into a single 2D physical label. This information is clustered by using locations metadata (geotags) and key-words (tags) associated to pictures. Our system helps two types of users: the user authoring the physical label and the final user who retrieves up-to-date information scanning the label with his/her camera phone. Preliminary results for a given seed word (the tag Napoli) on 3000 photographs are presented, together with some ad-hoc weighting factors that help in finding significant pictures (representing places) that can be associated to a specific area.

Original language	English
Title of host publication	Proceedings of the Working Conference on Advanced Visual Interfaces, AVI 08
Pages	351-354
Number of pages	4
DOIs	https://doi.org/10.1145/1385569.1385630
Publication status	Published - 2008
Event	Working Conference on Advanced Visual Interfaces, AVI 08 - Naples, Italy Duration: 28 May 2008 → 30 May 2008

Conference

Conference	Working Conference on Advanced Visual Interfaces, AVI 08
Country/Territory	Italy
City	Naples
Period	28/05/08 → 30/05/08

Keywords

Clustering
Collaborative tagging
Geo-referenced photographs

Access to Document

10.1145/1385569.1385630

Cite this

@inproceedings{853788fcfd75413d945d6d4c7b25c0ba,

title = "Visual tag authoring: Picture extraction via localized, collaborative tagging",

abstract = "In this work we present a system to encode location based information extracted from a media collection (the Flickr tagging system) into a single 2D physical label. This information is clustered by using locations metadata (geotags) and key-words (tags) associated to pictures. Our system helps two types of users: the user authoring the physical label and the final user who retrieves up-to-date information scanning the label with his/her camera phone. Preliminary results for a given seed word (the tag Napoli) on 3000 photographs are presented, together with some ad-hoc weighting factors that help in finding significant pictures (representing places) that can be associated to a specific area.",

keywords = "Clustering, Collaborative tagging, Geo-referenced photographs",

author = "Andrea Bellucci and {Levialdi Ghiron}, Stefano and Ignacio Aedo and Alessio Malizia",

year = "2008",

doi = "10.1145/1385569.1385630",

language = "English",

pages = "351--354",

booktitle = "Proceedings of the Working Conference on Advanced Visual Interfaces, AVI 08",

note = "Working Conference on Advanced Visual Interfaces, AVI 08 ; Conference date: 28-05-2008 Through 30-05-2008",

}

TY - GEN

T1 - Visual tag authoring

T2 - Working Conference on Advanced Visual Interfaces, AVI 08

AU - Bellucci, Andrea

AU - Levialdi Ghiron, Stefano

AU - Aedo, Ignacio

AU - Malizia, Alessio

PY - 2008

Y1 - 2008

N2 - In this work we present a system to encode location based information extracted from a media collection (the Flickr tagging system) into a single 2D physical label. This information is clustered by using locations metadata (geotags) and key-words (tags) associated to pictures. Our system helps two types of users: the user authoring the physical label and the final user who retrieves up-to-date information scanning the label with his/her camera phone. Preliminary results for a given seed word (the tag Napoli) on 3000 photographs are presented, together with some ad-hoc weighting factors that help in finding significant pictures (representing places) that can be associated to a specific area.

AB - In this work we present a system to encode location based information extracted from a media collection (the Flickr tagging system) into a single 2D physical label. This information is clustered by using locations metadata (geotags) and key-words (tags) associated to pictures. Our system helps two types of users: the user authoring the physical label and the final user who retrieves up-to-date information scanning the label with his/her camera phone. Preliminary results for a given seed word (the tag Napoli) on 3000 photographs are presented, together with some ad-hoc weighting factors that help in finding significant pictures (representing places) that can be associated to a specific area.

KW - Clustering

KW - Collaborative tagging

KW - Geo-referenced photographs

UR - http://www.scopus.com/inward/record.url?scp=57549117108&partnerID=8YFLogxK

U2 - 10.1145/1385569.1385630

DO - 10.1145/1385569.1385630

M3 - Conference contribution

AN - SCOPUS:57549117108

SP - 351

EP - 354

BT - Proceedings of the Working Conference on Advanced Visual Interfaces, AVI 08

Y2 - 28 May 2008 through 30 May 2008

ER -

Visual tag authoring: Picture extraction via localized, collaborative tagging

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this