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 815340 images similar to your query in 7089 ms (Index access Time: 154 ms, Temporary result managemet time: 440 ms, Database access time: 6495 ms)

Query:

Best guessed tags:
Relevance: 15.59, Guessed tags: capitol
Relevance: 6.03, Guessed tags: build
Relevance: 5.16, Guessed tags: berlin
Relevance: 4.34, Guessed tags: cathedral
Relevance: 4.33, Guessed tags: victoria
Relevance: 4.32, Guessed tags: parliament
Search using images similar to your query or see more random images:


(Weight 0) Flickr->

(Weight 393) Flickr->

(Weight 406) Flickr->

(Weight 432) Flickr->

(Weight 438) Flickr->

(Weight 438) Flickr->

(Weight 440) Flickr->

(Weight 445) Flickr->

(Weight 450) Flickr->

(Weight 451) Flickr->

(Weight 454) Flickr->

(Weight 458) Flickr->

(Weight 460) Flickr->

(Weight 464) Flickr->

(Weight 467) Flickr->

(Weight 470) Flickr->

(Weight 472) Flickr->

(Weight 474) Flickr->

(Weight 474) Flickr->

(Weight 478) 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).