Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Gajic, Bojana"'
Training a Siamese architecture for re-identification with a large number of identities is a challenging task due to the difficulty of finding relevant negative samples efficiently. In this work we present Bag of Negatives (BoN), a method for acceler
Externí odkaz:
http://arxiv.org/abs/1908.02391
Training a deep architecture using a ranking loss has become standard for the person re-identification task. Increasingly, these deep architectures include additional components that leverage part detections, attribute predictions, pose estimators an
Externí odkaz:
http://arxiv.org/abs/1801.05339
Publikováno v:
In Pattern Recognition April 2021 112
Autor:
Gajic, Bojana
This thesis presents a study of alternative speech feature extraction methods aimed at increasing robustness of automatic speech recognition (ASR) against additive background noise. Spectral peak positions of speech signals remain practically unchang
Externí odkaz:
http://urn.kb.se/resolve?urn=urn:nbn:no:ntnu:diva-441
Publikováno v:
Nordic Studies in Science Education
Although creativity constitutes part of 21st century skills, realizing a curriculum that emphasizes creativity in science and mathematics appears to be a challenge. In this study, we investigate how lower secondary science and mathematics teachers un
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::65bca5429689ce044726a90833b8556b
https://doi.org/10.5617/nordina.8620
https://doi.org/10.5617/nordina.8620
Autor:
Becks, Stefan, Gajic, Bojana
Vor dem Hintergrund der PISA-Ergebnisse von 2000 und 2009 in Bezug auf die Lesekompetenz österreichischer SchülerInnen wird in dieser Diplomarbeit der Versuch unternommen, einen empirischen Vergleich der Lesekompetenz von SchülerInnen, die nach de
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::76fa678089ab131f201d9948325607d3
Autor:
Gajic, Bojana
This thesis presents a study of alternative speech feature extraction methods aimed at increasing robustness of automatic speech recognition (ASR) against additive background noise. Spectral peak positions of speech signals remain practically unchang
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::39125d990edbfa2d1272b89916a5994a
https://hdl.handle.net/11250/249782
https://hdl.handle.net/11250/249782
Publikováno v:
The Journal of the Acoustical Society of America; November 2000, Vol. 108 Issue: 5 p2575-2575, 1p