Domain Adaptation for Sequential Detection

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F13%3A00211713" target="_blank" >RIV/68407700:21230/13:00211713 - isvavai.cz</a>
Result on the web
<a href="http://cmp.felk.cvut.cz/pub/cmp/articles/fojtusim/Fojtu-POSTER-2013.pdf" target="_blank" >http://cmp.felk.cvut.cz/pub/cmp/articles/fojtusim/Fojtu-POSTER-2013.pdf</a>
DOI - Digital Object Identifier
—

Result language
angličtina
Original language name
Domain Adaptation for Sequential Detection
Original language description
We propose a domain adaptation method for sequential decision-making process, which is suitable for real-time processing. The work is motivated by applications in surveillance, where detectors must be adapted to new observation conditions. We address thesituation, where the new observation is related to the previous observation by a parametric transformation. We propose a learning procedure, which reveals the hidden transformation between the old and new data. The transformation essentially allows to transfer the knowledge from the old data to the new one. We show that our method can achieve a 60% speedup in the training w.r.t. the baseline WaldBoost algorithm while outperforming it in precision.
Czech name
—
Czech description
—

Publication year
2013
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection
POSTER 2013 - 17th International Student Conference on Electrical Engineering
ISBN
978-80-01-05242-6
ISSN
—
e-ISSN
—
Number of pages
5
Pages from-to
1-5
Publisher name
Czech Technical University
Place of publication
Prague
Event location
Prague
Event date
May 16, 2013
Type of event by nationality
EUR - Evropská akce
UT code for WoS article
—

Similar results(10)