The AXES submissions at TrecVid 2013

Conference item

The AXES project participated in the interactive instance search task (INS), the semantic indexing task (SIN), the multimedia event detection task (MED) and the multimedia event recounting task (MER) 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 state-of-the-art low-level descriptors for motion, image and sound as well as high-level features for speech and text. The low-level descriptors are aggregated with Fisher vectors into high-dimensional video-level signatures and the high-level features are aggregated into bag-of-word histograms. Given 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, SIN, MED and MER systems and the results and findings of our experiments.

Authors: Aly, R; Arandjelović, R; Chatfield, K; Douze, M; Fernando, B

• Publication status: Published
• Peer review status: Reviewed (other)
• Publisher: National Institute of Standards and Technology
• Host title: 2013 TREC Video Retrieval Evaluation Notebook Papers and Slides
• Publication date: 2013-01-01
• Event title: TRECVID 2013 Workshop
• Event series: TRECVID
• Event location: Gaithersburg, Maryland, USA
• Event website: https://www-nlpir.nist.gov/projects/tv2013/index.html
• Event start date: 2013-11-20
• Event end date: 2013-11-22
• Language: English