Fraunhofer-Gesellschaft

Publica

Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

The AXES submissions at TrecVid 2013

TRECVid 2013, 20-22 Nov 2013, Gaithersburg, Maryland, USA
 
: Aly, Robin; Arandjelovic, Relja; Chatfield, Ken; Douze, Matthijs; Fernando, Basura; Harchaoui, Zaid; McGuinness, Kevin; O'Connor, Noel E.; Oneata, Dan; Parkhi, Omkar M.; Potapov, Danila; Revaud, Jerome; Schmid, Cordelia; Schwenninger, Jochen; Scott, David; Tuytelaars, Tinne; Verbeek, Jakob; Wang, Heng; Zisserman, Andrew

:
Volltext ()

Washington, DC: NIST, 2013, 12 S.
Englisch
Bericht, Elektronische Publikation
Fraunhofer IAIS ()

Abstract
The AXES project participated in the interactive instance search task (INS), the semantic indexing task (SIN) the multimedia event recounting task (MER), and the multimedia event detection task (MED) for TRECVid 2013. Our interactive INS focused this year on using classifiers trained at query time with positive examples collected from external search engines. Participants in our INS experiments were carried out by students and researchers at Dublin City University. Our best INS runs performed on par with the top ranked INS runs in terms of P@10 and P@30, and around the median in terms of mAP.For SIN, MED and MER, we use systems based on stateof-the-art local low-level descriptors for motion, image, and sound, as well as high-level features to capture speech and text and the visual and audio stream respectively. The low-level descriptors were aggregated by means of Fisher vectors into highdimensional video-level signatures, the high-level features areaggregated into bag-of-word histograms. Using thes

: http://publica.fraunhofer.de/dokumente/N-415209.html