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 1799068 images similar to your query in 9366 ms (Index access Time: 1252 ms, Temporary result managemet time: 1061 ms, Database access time: 7053 ms)

Query:

Best guessed tags:
Relevance: 17.84, Guessed tags: paul
Relevance: 12.52, Guessed tags: cathedral
Relevance: 11.58, Guessed tags: dome
Relevance: 7.92, Guessed tags: capitol
Relevance: 7.08, Guessed tags: london
Relevance: 4.41, Guessed tags: build
Relevance: 4.41, Guessed tags: oxford
Search using images similar to your query or see more random images:


(Weight 0) Flickr->

(Weight 269) Flickr->

(Weight 293) Flickr->

(Weight 296) Flickr->

(Weight 299) Flickr->

(Weight 300) Flickr->

(Weight 301) Flickr->

(Weight 302) Flickr->

(Weight 304) Flickr->

(Weight 307) Flickr->

(Weight 310) Flickr->

(Weight 314) Flickr->

(Weight 317) Flickr->

(Weight 319) Flickr->

(Weight 323) Flickr->

(Weight 323) Flickr->

(Weight 324) Flickr->

(Weight 326) Flickr->

(Weight 327) Flickr->

(Weight 331) 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).