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 662418 images similar to your query in 643 ms (Index access Time: 110 ms, Temporary result managemet time: 233 ms, Database access time: 300 ms)

Query:

Best guessed tags:
Relevance: 16.04, Guessed tags: coffee
Relevance: 8.04, Guessed tags: latte
Relevance: 4.83, Guessed tags: drink
Relevance: 4.00, Guessed tags: morn
Search using images similar to your query or see more random images:


(Weight 0) Flickr->

(Weight 620) Flickr->

(Weight 656) Flickr->

(Weight 667) Flickr->

(Weight 680) Flickr->

(Weight 690) Flickr->

(Weight 700) Flickr->

(Weight 703) Flickr->

(Weight 704) Flickr->

(Weight 704) Flickr->

(Weight 705) Flickr->

(Weight 705) Flickr->

(Weight 707) Flickr->

(Weight 707) Flickr->

(Weight 708) Flickr->

(Weight 709) Flickr->

(Weight 710) Flickr->

(Weight 712) Flickr->

(Weight 712) Flickr->

(Weight 714) 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).