next up previous contents
Next: TRECVid 2012 Semantic Video Up: Summary of References Related Previous: ImageNet Classification with Deep   Contents

Subsections

The Stanford / Technicolor / Fraunhofer HHI Video [3]

Original 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 aggregat- ing 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.


Miquel Perello Nieto 2014-11-28