Image Search and Annotation on a Very Large Scale
Using Deep Features and MI-File to search and annotate YFCC100M
(Yahoo Flickr Creative Commons 100M) dataset.

VEMIR
Research group


(97 millions images currently indexed)

Upload an image as query:
Chose an url as query:
Choose a random query.

Found 1406367 images similar to your query in 1858 ms (Index access Time: 66 ms, Temporary result managemet time: 719 ms, Database access time: 1073 ms)

Query:

Best guessed tags:
Relevance: 8.60, Guessed tags: london
Relevance: 7.74, Guessed tags: westminster
Relevance: 5.99, Guessed tags: parliament
Relevance: 5.15, Guessed tags: big ben
Relevance: 5.12, Guessed tags: cathedral
Relevance: 4.30, Guessed tags: palace
Relevance: 4.27, Guessed tags: church

Search using images similar to your query or see more random images:


(Weight 0) Flickr->

(Weight 439) Flickr->

(Weight 440) Flickr->

(Weight 444) Flickr->

(Weight 453) Flickr->

(Weight 455) Flickr->

(Weight 467) Flickr->

(Weight 483) Flickr->

(Weight 485) Flickr->

(Weight 491) Flickr->

(Weight 500) Flickr->

(Weight 502) Flickr->

(Weight 503) Flickr->

(Weight 511) Flickr->

(Weight 511) Flickr->

(Weight 513) Flickr->

(Weight 514) Flickr->

(Weight 520) Flickr->

(Weight 524) Flickr->

(Weight 527) Flickr->

The above images are miniature versions of the original ones that come from the site www.flickr.com.
All rights are reserved to the author of the original image, which is directly available on the Flickr site through a hypertext link (surface linking).