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 1599136 images similar to your query in 1368 ms (Index access Time: 131 ms, Temporary result managemet time: 611 ms, Database access time: 626 ms)

Query:

Best guessed tags:
Relevance: 17.05, Guessed tags: parliament
Relevance: 9.41, Guessed tags: budapest
Relevance: 9.34, Guessed tags: london
Relevance: 5.96, Guessed tags: river
Relevance: 4.26, Guessed tags: danube
Relevance: 4.25, Guessed tags: build
Relevance: 4.23, Guessed tags: big ben
Search using images similar to your query or see more random images:


(Weight 0) Flickr->

(Weight 399) Flickr->

(Weight 404) Flickr->

(Weight 416) Flickr->

(Weight 418) Flickr->

(Weight 432) Flickr->

(Weight 432) Flickr->

(Weight 435) Flickr->

(Weight 440) Flickr->

(Weight 443) Flickr->

(Weight 450) Flickr->

(Weight 451) Flickr->

(Weight 452) Flickr->

(Weight 454) Flickr->

(Weight 457) Flickr->

(Weight 460) Flickr->

(Weight 460) Flickr->

(Weight 475) Flickr->

(Weight 476) Flickr->

(Weight 476) 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).