AXES at TRECVid 2013

Robin Aly, Relja Arandjelovic, Ken Chatfield, Matthijs Douze, Basura Fernando, Zaid Harchaoui, Kevin McGuinness, Noel E. O' Connor, Dan Oneata, Omar M. Parkhi, Danila Potapov, Jerome Revaud, Cordelia Schmid, Jochen Schwenninger, David Scott, Tinne Tuytelaars, Jakob Verbeek, Heng Wang, Heng Wang, Andrew Zisserman

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademic

16 Downloads (Pure)

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 state- of-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 high- dimensional video-level signatures, the high-level features are aggregated into bag-of-word histograms. Using these features we train linear classifiers, and use early and late-fusion to combine the different features. Our MED system achieved the best score of all submitted runs in the main track, as well as in the ad-hoc track. This paper describes in detail our INS, MER, and MED systems and the results and findings of our experiments.
Original languageEnglish
Title of host publicationTREC Video Retrieval Evaluation Online Proceedings (TRECVid 2013)
Place of PublicationGaithersburg, MD, USA
PublisherNIST
Pages-
Number of pages12
Publication statusPublished - Dec 2013
EventTREC Video Retrieval Evaluation, TRECVID 2013 - Gaithersburg, United States
Duration: 19 Nov 201322 Nov 2013

Publication series

NameTREC Video Retrieval Evaluation: TRECVID
PublisherNIST
Volume2013

Conference

ConferenceTREC Video Retrieval Evaluation, TRECVID 2013
Abbreviated titleTRECVID
CountryUnited States
CityGaithersburg
Period19/11/1322/11/13

Fingerprint Dive into the research topics of 'AXES at TRECVid 2013'. Together they form a unique fingerprint.

Cite this