Event driven semantics based ad selection

The growth of digital television over satellite, cable, and terrestrial networks has driven advertisers to "better target" users by customized and personalized advertisements. Advertisements, whose content and theme are relevant and related to ongoing programs, content and theme, are known to have better impact on viewers. We propose a system for the selection, filtering, and presentation of advertisements based on detected program events and profiles contained in the home information system. A comprehensive event prediction and event analysis is performed based on which relevant ads are either selected for transport stream insertion or for caching purposes. The system also describes the notion of ActiveAd to achieve self-evaluation and self-transformation of an ad to increase its relevance with respect to an event.

[1]  B. Li,et al.  Event detection and summarization in sports video , 2001, Proceedings IEEE Workshop on Content-Based Access of Image and Video Libraries (CBAIVL 2001).

[2]  A. Thawani,et al.  iTV Application for Intent Tracking , 2004 .

[3]  Willem Jonker,et al.  Content-based video retrieval by integrating spatio-temporal and stochastic recognition of events , 2001, Proceedings IEEE Workshop on Detection and Recognition of Events in Video.

[4]  Milind R. Naphade,et al.  Detecting semantic concepts using context and audiovisual features , 2001, Proceedings IEEE Workshop on Detection and Recognition of Events in Video.

[5]  S. Gopalan,et al.  Viewing characteristics based personalized ad streaming in an interactive TV environment , 2004, First IEEE Consumer Communications and Networking Conference, 2004. CCNC 2004..

[6]  A. Murat Tekalp,et al.  Automatic Soccer Video Analysis and Summarization , 2003, IS&T/SPIE Electronic Imaging.

[7]  Xinghua Sun,et al.  Bayesian-network-based soccer video event detection and retrieval , 2003, International Symposium on Multispectral Image Processing and Pattern Recognition.