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 420000 images similar to your query in 545 ms (Index access Time: 148 ms, Temporary result managemet time: 234 ms, Database access time: 163 ms)

Query:

Best guessed tags:
Relevance: 24.85, Guessed tags: baseball
Relevance: 11.18, Guessed tags: field
Relevance: 8.56, Guessed tags: game
Relevance: 7.71, Guessed tags: met
Relevance: 6.84, Guessed tags: stadium
Relevance: 5.15, Guessed tags: yankee
Relevance: 5.14, Guessed tags: park
Relevance: 5.12, Guessed tags: nation
Relevance: 4.29, Guessed tags: dodger
Search using images similar to your query or see more random images:


(Weight 0) Flickr->

(Weight 425) Flickr->

(Weight 438) Flickr->

(Weight 446) Flickr->

(Weight 448) Flickr->

(Weight 468) Flickr->

(Weight 468) Flickr->

(Weight 483) Flickr->

(Weight 485) Flickr->

(Weight 485) Flickr->

(Weight 485) Flickr->

(Weight 486) Flickr->

(Weight 487) Flickr->

(Weight 487) Flickr->

(Weight 488) Flickr->

(Weight 488) Flickr->

(Weight 488) Flickr->

(Weight 489) Flickr->

(Weight 490) Flickr->

(Weight 492) 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).