In the context of the Multimedia Commons initiative, we extracted and indexed deep features of about 100M images uploaded on Flickr between 2004 and 2014 and published under a Creative Commons commercial or noncommercial license. The extracted features and an online demo built using the MI-File approximated data structure are both publicly available. The online CBIR system demonstrates the effectiveness of the deep features and the efficiency of the indexing approach.
Indexing 100M images with deep features and MI-File
Amato G;Falchi F;Gennaro C;Rabitti F
2016
Abstract
In the context of the Multimedia Commons initiative, we extracted and indexed deep features of about 100M images uploaded on Flickr between 2004 and 2014 and published under a Creative Commons commercial or noncommercial license. The extracted features and an online demo built using the MI-File approximated data structure are both publicly available. The online CBIR system demonstrates the effectiveness of the deep features and the efficiency of the indexing approach.File in questo prodotto:
| File | Dimensione | Formato | |
|---|---|---|---|
|
prod_378910-doc_128258.pdf
accesso aperto
Descrizione: Indexing 100M images with deep features and MI-File
Tipologia:
Versione Editoriale (PDF)
Dimensione
685.6 kB
Formato
Adobe PDF
|
685.6 kB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
