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 1725112 images similar to your query in 1214 ms (Index access Time: 86 ms, Temporary result managemet time: 545 ms, Database access time: 583 ms)

Query:

Best guessed tags:
Relevance: 14.96, Guessed tags: paul
Relevance: 9.57, Guessed tags: capitol
Relevance: 8.78, Guessed tags: cathedral
Relevance: 7.04, Guessed tags: london
Relevance: 4.42, Guessed tags: england
Relevance: 4.34, Guessed tags: washington
Relevance: 4.34, Guessed tags: build
Search using images similar to your query or see more random images:


(Weight 0) Flickr->

(Weight 306) Flickr->

(Weight 350) Flickr->

(Weight 355) Flickr->

(Weight 359) Flickr->

(Weight 363) Flickr->

(Weight 372) Flickr->

(Weight 375) Flickr->

(Weight 379) Flickr->

(Weight 381) Flickr->

(Weight 383) Flickr->

(Weight 385) Flickr->

(Weight 385) Flickr->

(Weight 387) Flickr->

(Weight 387) Flickr->

(Weight 387) Flickr->

(Weight 397) Flickr->

(Weight 397) Flickr->

(Weight 397) Flickr->

(Weight 398) 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).