Browse DORAS
Browse Theses
Search
Latest Additions
Creative Commons License
Except where otherwise noted, content on this site is licensed for use under a:

AXES at TRECVID 2012: KIS, INS, and MED

Aly, Robin and McGuinness, Kevin and Chen, Shu and O'Connor, Noel E. and Chatfield, Ken and Parkhi, Omkar M. and Arandjelovic, Relja and Zisserman, Andrew and Fernando, Basura and Tuytelaars, Tinne and Oneata, Dan and Douze, Matthijs and Revaud, Jérôme and Schwenninger, Jochen and Potapov, Danila and Wang, Heng and Harchaoui, Zaid and Verbeek, Jakob and Schmid, Cordelia (2012) AXES at TRECVID 2012: KIS, INS, and MED. In: TRECVid 2012, 26-28 Nov 2012, Gaithersburg, Maryland, USA.

Full text available as:

[img]PDF (Workshop Paper) - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
8Mb

Abstract

The AXES project participated in the interactive instance search task (INS), the known-item search task (KIS), and the multimedia event detection task (MED) for TRECVid 2012. As in our TRECVid 2011 system, we used nearly identical search systems and user interfaces for both INS and KIS. Our interactive INS and KIS systems focused this year on using classifiers trained at query time with positive examples collected from external search engines. Participants in our KIS experiments were media professionals from the BBC; our INS experiments were carried out by students and researchers at Dublin City University. We performed comparatively well in both experiments. Our best KIS run found 13 of the 25 topics, and our best INS runs outperformed all other submitted runs in terms of P@100. For MED, the system presented was based on a minimal number of low-level descriptors, which we chose to be as large as computationally feasible. These descriptors are aggregated to produce high-dimensional video-level signatures, which are used to train a set of linear classifiers. Our MED system achieved the second-best score of all submitted runs in the main track, and best score in the ad-hoc track, suggesting that a simple system based on state-of-the-art low-level descriptors can give relatively high performance. This paper describes in detail our KIS, INS, and MED systems and the results and findings of our experiments.

Item Type:Conference or Workshop Item (Paper)
Event Type:Workshop
Refereed:No
Subjects:Computer Science > Interactive computer systems
Computer Science > Machine learning
Computer Science > Multimedia systems
Computer Science > Information retrieval
Computer Science > Digital video
Computer Science > Image processing
DCU Faculties and Centres:DCU Faculties and Schools > Faculty of Engineering and Computing > School of Electronic Engineering
DCU Faculties and Schools > Faculty of Engineering and Computing > School of Computing
Research Initiatives and Centres > CLARITY: The Centre for Sensor Web Technologies
Use License:This item is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 3.0 License. View License
Funders:EU FP7 AXES ICT-269980, QUAERO project supported by OSEO, UK EPSRC and ERC grant VisRec no. 228180
ID Code:17860
Deposited On:12 Mar 2013 10:40 by Dr. Kevin McGuinness. Last Modified 21 Oct 2016 16:43

Download statistics

Archive Staff Only: edit this record