Authors: Yuqiang Chen, Ou Jin, Gui-Rong Xue and Jia Chen (Shanghai Jiao Tong University) and Qiang Yang (Hong Kong UST)
Advertising in the case of textual Web pages has been studied extensively by many researchers. However, with the increasing amount of multimedia data such as image, audio and video on theWeb, the need for recommending advertisement for the multimedia data is becoming a reality. In this paper, we address the novel problem of visual contextual advertising, which is to directly advertise when users are viewing images which do not have any surrounding text. A key challenging issue of visual contextual advertising is that images and advertisements are usually represented in image space and word space respectively, which are quite different with each other inherently. To solve this problem, we use transfer learning methods to bridge the two spaces.
For more information, please see our AAAI 2010 article:
http://www.cse.ust.hk/~qyang/Docs/2010/vicad.pdf
Please see a media report on this system:
http://www.technologyreview.com/business/25833/
This project is supported by Hong Kong RGC/China NSFC Projects 60910123 and N_HKUST624/09.