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 597330 images similar to your query in 641 ms (Index access Time: 31 ms, Temporary result managemet time: 391 ms, Database access time: 219 ms)

Query:

Best guessed tags:
Relevance: 22.41, Guessed tags: coffee
Relevance: 7.17, Guessed tags: latte
Relevance: 6.42, Guessed tags: cup
Relevance: 4.80, Guessed tags: hot
Relevance: 4.00, Guessed tags: cafe
Relevance: 3.97, Guessed tags: tea

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


(Weight 0) Flickr->

(Weight 631) Flickr->

(Weight 633) Flickr->

(Weight 648) Flickr->

(Weight 664) Flickr->

(Weight 666) Flickr->

(Weight 676) Flickr->

(Weight 677) Flickr->

(Weight 682) Flickr->

(Weight 682) Flickr->

(Weight 686) Flickr->

(Weight 687) Flickr->

(Weight 690) Flickr->

(Weight 691) Flickr->

(Weight 691) Flickr->

(Weight 691) Flickr->

(Weight 696) Flickr->

(Weight 698) Flickr->

(Weight 701) Flickr->

(Weight 703) 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).