%0 Conference Proceedings %F ChangVideoSearch:2007 %A Chang, Shih-Fu %A Kennedy, Lyndon %A Zavesky, Eric %T {Columbia University's Semantic Video Search Engine} %B {ACM International Conference on Image and Video Retrieval} %C Amsterdam, Netherlands %X We briefly describe ¡°CuVid,¡± Columbia University¡¯s video search engine, a system that enables semantic multimodal search over video broadcast news collections. The system was developed and first evaluated for the NIST TRECVID 2005 benchmark and later expanded to include a large number (374) of visual concept detectors. Our focus is on comparative studies of pros and cons of search methods built on various individual modalities (keyword, image, near-duplicate, and semantic concept) and combinations, without requiring advanced tools and interfaces for interactive search. %U http://www.ee.columbia.edu/dvmm/publications/07/civr2007-videolympics.pdf %8 July %D 2007