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 1311664 images similar to your query in 1032 ms (Index access Time: 143 ms, Temporary result managemet time: 654 ms, Database access time: 235 ms)

Query:

Best guessed tags:
Relevance: 20.01, Guessed tags: top
Relevance: 13.15, Guessed tags: central park
Relevance: 12.20, Guessed tags: rock
Relevance: 11.20, Guessed tags: view
Relevance: 10.38, Guessed tags: build
Relevance: 9.55, Guessed tags: new york
Relevance: 6.93, Guessed tags: empire state
Relevance: 5.27, Guessed tags: manhattan
Relevance: 5.20, Guessed tags: skyline
Relevance: 4.34, Guessed tags: skyscraper
Search using images similar to your query or see more random images:


(Weight 0) Flickr->

(Weight 314) Flickr->

(Weight 321) Flickr->

(Weight 323) Flickr->

(Weight 325) Flickr->

(Weight 330) Flickr->

(Weight 347) Flickr->

(Weight 352) Flickr->

(Weight 355) Flickr->

(Weight 360) Flickr->

(Weight 360) Flickr->

(Weight 361) Flickr->

(Weight 362) Flickr->

(Weight 364) Flickr->

(Weight 367) Flickr->

(Weight 370) Flickr->

(Weight 371) Flickr->

(Weight 372) Flickr->

(Weight 373) Flickr->

(Weight 374) 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).