부산대학교 도서관

A critical component of today's commercial search engines is an advertisement platform. The current state-of-the-art of such platforms is primarily based on advanced keyword matching to determine the relevance of advertisements for users' queries. However, such keyword matching techniques suffer from missing user intent when the query domain is visual as opposed to textual. To handle such a domain, we propose a new advertisement platform which allows search engine advertisers to bid on images instead of just plain text. The main components of this platform include an advertisement editorial tool, ROI detection, image content understanding, and image matching modules. This platform is suitable for application scenarios where images are the main input or consumed content, for example, in Multimedia Messaging Service (MMS) or content based image retrieval. We demonstrated the effectiveness of our proposed advertisement platform solution when used in a mobile visual search scenario involving querying for real world billboards.