Blind assessment for stereo images considering binocular characteristics and deep perception map based on deep belief network [PDF]
, 2018 © 2018 Elsevier Inc. In recent years, blind image quality assessment in the field of 2D image/video has gained the popularity, but its applications in 3D image/video are to be generalized.
Huifang Xu (111603) +5 more
core +1 more source
Dissipation and dilatation rates in premixed turbulent flames [PDF]
, 2020 Velocity dilatation and total, solenoidal, and dilatational dissipation rates of the total flow kinetic energy are extracted from three different direct numerical simulation databases obtained by three independent research groups using different ...
Dave, Himanshu +6 more
core +3 more sources
Simulation study on light ions identification methods for carbon beams from 95 to 400 MeV/A
, 2013 Monte Carlo simulations have been performed in order to evaluate the efficiencies of several light ions identification techniques. The detection system was composed with layers of scintillating material to measure either the deposited energy or the time ...
Colin, J. +5 more
core +1 more source
CMML: Contextual Modulation Meta Learning for Cold-Start Recommendation [PDF]
, 2021 Practical recommender systems experience a cold-start problem when observed user-item interactions in the history are insufficient. Meta learning, especially gradient based one, can be adopted to tackle this problem by learning initial parameters of the ...
Chen, C +5 more
core +1 more source
Real analytic vector fields with first integral and separatrices [PDF]
, 2019 We prove that a germ of analytic vector field at (R3, 0) that possesses a non-constant analytic first integral has a real formal separatrix. We provide an example which shows that such a vector field does not necessarily have a real analytic separatrix ...
Mol, Rogério, Sánchez, Fernando Sanz
core +1 more source
Finding Influential Examples in Deep Learning Models [PDF]
, 2021 Machine learning models are powerful, but not without errors and the complexity of large models makes it hard for a human to intuitively understand the cause of the error. This thesis approaches the task of explaining predictions made by deep learning
Brinkman, Adam, Larsson Hörkén, Johan
core +1 more source
Wild and backyard food use during COVID-19 in upstate New York, United States. [PDF]
Front Nutr, 2023 Coffin-Schmitt JL +9 more
europepmc +1 more source
A decision cognizant Kullback-Leibler divergence [PDF]
, 2017 In decision making systems involving multiple classifiers there is the need to assess classifier (in)congruence, that is to gauge the degree of agreement between their outputs.
de Campos, T +4 more
core +1 more source
Common and rare variant analysis in early-onset bipolar disorder vulnerability [PDF]
, 2014 Bipolar disorder is one of the most common and devastating psychiatric disorders whose mechanisms remain largely unknown. Despite a strong genetic contribution demonstrated by twin and adoption studies, a polygenic background influences this ...
Albus, Margot +32 more
core +8 more sources
An Exploration of Broader Influence Maximization in Timeliness Networks with Opportunistic Selection [PDF]
, 2015 The goal of classic influence maximization in Online Social Networks (OSNs) is to maximize the spread of influence with a fix budget constraint, e.g. the size of seed nodes is pre-determined.
yan, mingyuan
core +1 more source