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 1391108 images similar to your query in 1033 ms (Index access Time: 97 ms, Temporary result managemet time: 625 ms, Database access time: 311 ms)

Query:

Best guessed tags:
Relevance: 15.50, Guessed tags: view
Relevance: 12.98, Guessed tags: top
Relevance: 11.22, Guessed tags: build
Relevance: 10.33, Guessed tags: empire state
Relevance: 9.52, Guessed tags: central park
Relevance: 9.50, Guessed tags: new york
Relevance: 8.70, Guessed tags: rock
Relevance: 6.03, Guessed tags: skyline
Relevance: 4.32, Guessed tags: manhattan
Search using images similar to your query or see more random images:


(Weight 0) Flickr->

(Weight 335) Flickr->

(Weight 402) Flickr->

(Weight 410) Flickr->

(Weight 413) Flickr->

(Weight 415) Flickr->

(Weight 417) Flickr->

(Weight 431) Flickr->

(Weight 433) Flickr->

(Weight 433) Flickr->

(Weight 434) Flickr->

(Weight 436) Flickr->

(Weight 436) Flickr->

(Weight 437) Flickr->

(Weight 438) Flickr->

(Weight 438) Flickr->

(Weight 439) Flickr->

(Weight 441) Flickr->

(Weight 442) Flickr->

(Weight 442) 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).