Zobrazeno 1 - 10
of 116
pro vyhledávání: '"Perina, Alessandro"'
Autor:
Zhang, Baochang, Luan, Shangzhen, Chen, Chen, Han, Jungong, Wang, Wei, Perina, Alessandro, Shao, Ling
Correlation filters are special classifiers designed for shift-invariant object recognition, which are robust to pattern distortions. The recent literature shows that combining a set of sub-filters trained based on a single or a small group of images
Externí odkaz:
http://arxiv.org/abs/1711.04192
Autor:
Zhang, Baochang, Li, Zhigang, Cao, Xianbin, Ye, Qixiang, Chen, Chen, Shen, Linlin, Perina, Alessandro, Ji, Rongrong
Kernelized Correlation Filter (KCF) is one of the state-of-the-art object trackers. However, it does not reasonably model the distribution of correlation response during tracking process, which might cause the drifting problem, especially when target
Externí odkaz:
http://arxiv.org/abs/1612.05365
Autor:
Luan, Shangzhen, Zhang, Baochang, Han, Jungong, Chen, Chen, Shao, Ling, Perina, Alessandro, Shen, Linlin
There is a neglected fact in the traditional machine learning methods that the data sampling can actually lead to the solution sampling. We consider this observation to be important because having the solution sampling available makes the variable di
Externí odkaz:
http://arxiv.org/abs/1606.02170
The counting grid is a grid of microtopics, sparse word/feature distributions. The generative model associated with the grid does not use these microtopics individually. Rather, it groups them in overlapping rectangular windows and uses these grouped
Externí odkaz:
http://arxiv.org/abs/1503.03701
We present a novel method to infer, in closed-form, a general 3D spatial occupancy and orientation of a collection of rigid objects given 2D image detections from a sequence of images. In particular, starting from 2D ellipses fitted to bounding boxes
Externí odkaz:
http://arxiv.org/abs/1502.04754
Autor:
Perina, Alessandro, Jojic, Nebojsa
In recent scene recognition research images or large image regions are often represented as disorganized "bags" of features which can then be analyzed using models originally developed to capture co-variation of word counts in text. However, image fe
Externí odkaz:
http://arxiv.org/abs/1410.6264
Autor:
Perina, Alessandro, Jojic, Nebojsa
We introduce and we analyze a new dataset which resembles the input to biological vision systems much more than most previously published ones. Our analysis leaded to several important conclusions. First, it is possible to disambiguate over dozens of
Externí odkaz:
http://arxiv.org/abs/1304.7236
Autor:
Jojic, Nebojsa, Perina, Alessandro
Models of bags of words typically assume topic mixing so that the words in a single bag come from a limited number of topics. We show here that many sets of bag of words exhibit a very different pattern of variation than the patterns that are efficie
Externí odkaz:
http://arxiv.org/abs/1202.3752
Publikováno v:
In Pattern Recognition May 2018 77:87-98
Autor:
Lovato, Pietro, Bicego, Manuele, Kesa, Maria, Jojic, Nebojsa, Murino, Vittorio, Perina, Alessandro
Publikováno v:
In Artificial Intelligence In Medicine June 2016 70:1-11