Flickr API: What are the "vision" tags?

Question

When querying the Flickr API and checking for the returned tags, I noticed that I receive additional tags which are not shown on the web interface. For example for this image:

http://www.flickr.com/photos/77060598@N08/12078886973

Beside the tags shown on the webpage (Nikon F2AS, Nikon, Black and White, B&W, Mountains, Germany, Snow, Landscape, Sky, Clouds), the JSON response contains the tags vision:outdoor=0949 and vision:sky=051.

I assume, that some computer vision processing is applied by Flickr to automatically assign those tags. Am I right with this assumption? I cannot find any documentation about those tags. Is there any description about the algorithms they employ and/or the kind of tags and the meaning of the numbers they assign?

Answer 1

Yes, your assumption is right. These tags are image classification tags. They are part of an ongoing research in the area of classification and computational learning. The research goal is to reach a precise category based image classification with a minimal learning effort.

• yahoo large scale flickr tag image classification challenge
• Everingham, M., Van Gool, L., Williams, C. K. I., Winn, J. and Zisserman, A. The PASCAL Visual Object Classes (VOC) Challenge International Journal of Computer Vision, 88(2), 303-338, 2010 - PDF
• http://pascallin.ecs.soton.ac.uk/challenges/VOC/
• Training and Test Data
• Results & Leaderboard