Date of Original Version
Proceedings of the 2008 International Conference on Content-Based Image and Video Retrieval (Niagara Falls, Canada, July 07 - 09, 2008). CIVR '08. ACM, New York, NY, 543-544
Abstract or Table of Contents
We introduce an interface for efficient video search that exploits the human ability to quickly scan visual content, after an automatic system has done its best to arrange the images in order of relevance. While extreme video retrieval is taxing to the human, it has also been shown to be very effective. The system will demonstrate several ways to rapidly scan images, change search queries, and employ different types of relevance feedback.