Zobrazeno 1 - 10
of 16
pro vyhledávání: '"Bartoli, Federico"'
We present a novel online unsupervised method for face identity learning from video streams. The method exploits deep face descriptors together with a memory based learning mechanism that takes advantage of the temporal coherence of visual data. Spec
Externí odkaz:
http://arxiv.org/abs/1711.07368
Human motion and behaviour in crowded spaces is influenced by several factors, such as the dynamics of other moving agents in the scene, as well as the static elements that might be perceived as points of attraction or obstacles. In this work, we pre
Externí odkaz:
http://arxiv.org/abs/1705.02503
Publikováno v:
In Pattern Recognition March 2019 87:170-178
Publikováno v:
In IFAC PapersOnLine 2018 51(9):446-451
Autor:
Bartoli, Federico, Lisanti, Giuseppe, Seidenari, Lorenzo, Karaman, Svebor, Del Bimbo, Alberto
Publikováno v:
2015 IEEE International Symposium on Antennas & Propagation & USNC/URSI National Radio Science Meeting; 2015, p19-27, 9p
Autor:
Bartoli, Federico, Lisanti, Giuseppe, Karaman, Svebor, Bagdanov, Andrew D., Bimbo, Alberto Del
Publikováno v:
2014 22nd International Conference on Pattern Recognition; 2014, p3534-3539, 6p
Publikováno v:
Pattern Recognition. 87:170-178
In this paper, we present a new method that provides a substantial speed-up of person detection while showing high classification accuracy. Our method learns a Gaussian Mixture Model of locations and scales of the persons in the scene under observati
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4c46e906ca566fe977f3b05b98329e64
https://doi.org/10.1016/j.patcog.2018.10.008
https://doi.org/10.1016/j.patcog.2018.10.008
Publikováno v:
ICPR
Human motion and behaviour in crowded spaces is influenced by several factors, such as the dynamics of other moving agents in the scene, as well as the static elements that might be perceived as points of attraction or obstacles. In this work, we pre
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::add57cae6fb76f4031bc360d2b580fea
http://hdl.handle.net/11585/656093
http://hdl.handle.net/11585/656093
Publikováno v:
ICMR
We present a new tool we have developed to ease the annotation of crowded environments, typical of visual surveillance datasets. Our tool is developed using HTML5 and Javascript and has two back-ends. A PHP based back-end implement the persistence us
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1610fca56fa5259c0397980f87f57ad6
http://hdl.handle.net/11585/654620
http://hdl.handle.net/11585/654620