EURECOM at TrecVid 2013: The Semantic Indexing Task

Abstract

This year EURECOM participated in the TRECVID 2013 Semantic INdexing (SIN) Task [11] for the submission of four different runs for 60 concepts. Our submission builds on the runs submitted last year at the 2012 SIN task, the details of which can be found in [8]. In 2013, two runs are combinations of basic descriptors. One run adds uploaders bias to the pool of visual features while another run was prepared in collaboration with Aalto University. All runs are trained on annotations provided by the IRIM collaborative effort [4]. When compared with last year system, our runs use a larger set of visual features, and larger visual dictionaries to provide a finer representation of the visual/clustering space and increase the precision of the retrieval system. Like in last year’s submission we add a global descriptor to visual features capturing salient details or gist of a keyframe. We further benefit from metadata information by including an uploader bias to increase the scores of videos uploaded by same users. A major difference this year is that we have used a new training algorithm based on a combination of PEGASOS [14] mixed with Homogeneous Kernel Maps [16], while our previous system was based on the libsvm library [5]. Our four runs are organized as follows:

3 Figures and Tables

Cite this paper

@inproceedings{Niaz2014EURECOMAT, title={EURECOM at TrecVid 2013: The Semantic Indexing Task}, author={Usman Farrokh Niaz and Miriam Redi and Claudiu Tanase and Bernard M{\'e}rialdo}, year={2014} }