Contextual In-Video Advertising Using Situation Information

With the rapid growth of video data service, demand to provide advertisements or additional information with regard to a particular video scene is increasing. However, the direct use of automated visual analysis or speech recognition on videos virtually has limitations with current level of technology; the metadata of video such as title, category information, or summary does not reflect the content of continuously changing scenes. This work presents a new video contextual advertising system that serves relevant advertisements on a given scene by leveraging the scene`s situation information inferred from video scripts. Experimental results show that the use of situation information extracted from scripts leads to better performance and display of more relevant advertisements to the user.