Institution
University of Trento
Education•Trento, Italy•
About: University of Trento is a education organization based out in Trento, Italy. It is known for research contribution in the topics: Population & Large Hadron Collider. The organization has 10527 authors who have published 30978 publications receiving 896614 citations. The organization is also known as: Universitá degli Studi di Trento & Universita degli Studi di Trento.
Papers published on a yearly basis
Papers
More filters
••
[...]
TL;DR: A recurrent face aging (RFA) framework based on a recurrent neural network which can identify the ages of people from 0 to 80 is introduced and demonstrates the proposed RFA provides better aging faces over other state-of-the-art age progression methods.
Abstract: Modeling the aging process of human face is important for cross-age face verification and recognition. In this paper, we introduce a recurrent face aging (RFA) framework based on a recurrent neural network which can identify the ages of people from 0 to 80. Due to the lack of labeled face data of the same person captured in a long range of ages, traditional face aging models usually split the ages into discrete groups and learn a one-step face feature transformation for each pair of adjacent age groups. However, those methods neglect the in-between evolving states between the adjacent age groups and the synthesized faces often suffer from severe ghosting artifacts. Since human face aging is a smooth progression, it is more appropriate to age the face by going through smooth transition states. In this way, the ghosting artifacts can be effectively eliminated and the intermediate aged faces between two discrete age groups can also be obtained. Towards this target, we employ a twolayer gated recurrent unit as the basic recurrent module whose bottom layer encodes a young face to a latent representation and the top layer decodes the representation to a corresponding older face. The experimental results demonstrate our proposed RFA provides better aging faces over other state-of-the-art age progression methods.
202 citations
••
TL;DR: In this paper, a comparison of the relative yields of upsilon resonances in the mu(+) mu(-) decay channel in PbPb and pp collisions at a centre-of-mass energy per nucleon pair of 2.76 TeV, is performed with data collected with the CMS detector at the LHC.
Abstract: A comparison of the relative yields of Upsilon resonances in the mu(+) mu(-) decay channel in PbPb and pp collisions at a centre-of-mass energy per nucleon pair of 2.76 TeV, is performed with data collected with the CMS detector at the LHC. Using muons of transverse momentum above 4 GeV/c and pseudorapidity below 2.4, the double ratio of the Upsilon(2S) and Upsilon(3S) excited states to the Upsilon(1S) ground state in PbPb and pp collisions,(Upsilon(2S+3S)/Upsilon(1S)[PbPb])/(Upsilon(2S+3S)/Upsilon(1S)[pp]), is found to be 0.31 - 0.15 + 0.19 (stat.) +/- 0.03 (syst.). The probability to obtain the measured value, or lower, if the true double ratio is unity, has been calculated to be less than 1%.
202 citations
••
TL;DR: The proposed approach is quite general and can be used for any given crystallite shape and different distribution functions; moreover, the Fourier transform formalism allows the introduction in the line-profile expression of other contributions to line broadening in a relatively easy and straightforward way.
Abstract: Diffraction patterns for polydisperse systems of crystalline grains of cubic materials were calculated considering some common grain shapes: sphere, cube, tetrahedron and octahedron Analytical expressions for the Fourier transforms and corresponding column-length distributions were calculated for the various crystal shapes considering two representative examples of size-distribution functions: lognormal and Poisson Results are illustrated by means of pattern simulations for a fcc material Line-broadening anisotropy owing to the different crystal shapes is discussed The proposed approach is quite general and can be used for any given crystallite shape and different distribution functions; moreover, the Fourier transform formalism allows the introduction in the line-profile expression of other contributions to line broadening in a relatively easy and straightforward way
202 citations
••
TL;DR: A new multi-task feature selection algorithm is proposed and applied to multimedia (e.g., video and image) analysis, which enables the common knowledge of multiple tasks as supplementary information to facilitate decision making.
Abstract: While much progress has been made to multi-task classification and subspace learning, multi-task feature selection has long been largely unaddressed. In this paper, we propose a new multi-task feature selection algorithm and apply it to multimedia (e.g., video and image) analysis. Instead of evaluating the importance of each feature individually, our algorithm selects features in a batch mode, by which the feature correlation is considered. While feature selection has received much research attention, less effort has been made on improving the performance of feature selection by leveraging the shared knowledge from multiple related tasks. Our algorithm builds upon the assumption that different related tasks have common structures. Multiple feature selection functions of different tasks are simultaneously learned in a joint framework, which enables our algorithm to utilize the common knowledge of multiple tasks as supplementary information to facilitate decision making. An efficient iterative algorithm is proposed to optimize it, whose convergence is guaranteed. Experiments on different databases have demonstrated the effectiveness of the proposed algorithm.
202 citations
••
TL;DR: A digital architecture for support vector machine (SVM) learning is proposed and its implementation on a field programmable gate array (FPGA) is discussed and a new algorithm for SVM learning which is less sensitive to quantization errors respect to the solution is used.
Abstract: In this paper, we propose a digital architecture for support vector machine (SVM) learning and discuss its implementation on a field programmable gate array (FPGA). We analyze briefly the quantization effects on the performance of the SVM in classification problems to show its robustness, in the feedforward phase, respect to fixed-point math implementations; then, we address the problem of SVM learning. The architecture described here makes use of a new algorithm for SVM learning which is less sensitive to quantization errors respect to the solution appeared so far in the literature. The algorithm is composed of two parts: the first one exploits a recurrent network for finding the parameters of the SVM; the second one uses a bisection process for computing the threshold. The architecture implementing the algorithm is described in detail and mapped on a real current-generation FPGA (Xilinx Virtex II). Its effectiveness is then tested on a channel equalization problem, where real-time performances are of paramount importance.
201 citations
Authors
Showing all 10758 results
Name | H-index | Papers | Citations |
---|---|---|---|
Yi Chen | 217 | 4342 | 293080 |
Jie Zhang | 178 | 4857 | 221720 |
Richard B. Lipton | 176 | 2110 | 140776 |
Jasvinder A. Singh | 176 | 2382 | 223370 |
J. N. Butler | 172 | 2525 | 175561 |
Andrea Bocci | 172 | 2402 | 176461 |
P. Chang | 170 | 2154 | 151783 |
Bradley Cox | 169 | 2150 | 156200 |
Marc Weber | 167 | 2716 | 153502 |
Guenakh Mitselmakher | 165 | 1951 | 164435 |
Brian L Winer | 162 | 1832 | 128850 |
J. S. Lange | 160 | 2083 | 145919 |
Ralph A. DeFronzo | 160 | 759 | 132993 |
Darien Wood | 160 | 2174 | 136596 |
Robert Stone | 160 | 1756 | 167901 |