Options
2012
Conference Paper
Titel
The stanford/technicolor/fraunhofer HHI video semantic indexing system
Abstract
Video search has become a very important tool, with the ever-growing size of multimedia collections. This work introduces our Video Semantic Indexing system. Our experiments show that Residual Vectors provide an efficient way of aggregating local descriptors, with complementary gain with respect to BoVW. Also, we show that systems using a limited number of descriptors and machine learning techniques can still be quite effective. Our first participation at the TRECVID evaluation has been very fruitful: our team was ranked 6th in the light version of the Semantic Indexing task.