简介:Researchersoftensummarizetheirworkintheformofscientificposters.Postersprovideacoherentandefficientwaytoconveycoreideasexpressedinscientificpapers.Generatingagoodscientificposter,however,isacomplexandtime-consumingcognitivetask,sincesuchpostersneedtobereadable,informative,andvisuallyaesthetic.Inthispaper,forthefirsttime,westudythechallengingproblemoflearningtogeneratepostersfromscientificpapers.Tothisend,adata-drivenframework,whichutilizesgraphicalmodels,isproposed.Specifically,givencontenttodisplay,thekeyelementsofagoodposter,includingattributesofeachpanelandarrangementsofgraphicalelements,arelearnedandinferredfromdata.Duringtheinferencestage,themaximumaposterior(MAP)estimationframeworkisemployedtoincorporatesomedesignprinciples.Inordertobridgethegapbetweenpanelattributesandthecompositionwithineachpanel,wealsoproposearecursivepagesplittingalgorithmtogeneratethepanellayoutforaposter.Tolearnandvalidateourmodel,wecollectandreleaseanewbenchmarkdataset,calledNJU-FudanPaper-Posterdataset,whichconsistsofscientificpapersandcorrespondingposterswithexhaustivelylabelledpanelsandattributes.Qualitativeandquantitativeresultsindicatetheeffectivenessofourapproach.
简介:Thepresentingworkdealswithimplementationofsamplegraphicpatternsderivedfrompublishedscientific/technologicdocumentationfiguresonnumericsimulationofmultiphaseflowandFEManalysisofthinwalledmechanicalstructures.First,geometricplanepatternsinrectangular/circularformweredemonstratedincontrasttogradualchangestyleincolorandgraphicconfiguration.Next,selectedartistic/graphicsamplepatternswereimplementedinlogoconceptualdesignandvisualinnovationstorming.Thewayineditingtheaboveoriginalfiguresis2Dsymmetry,rectangulararraygeometrically,andconvertingthemininversecolorinsoftwarelikePS.Theobjectiveofthisworkistocultivate,exploreanddisciplinetrainees'visualabilityinartistic/aestheticappreciation,graphiccommunicationandindustrialdesignandapplication,thuslayingtiescloselyamongcomprehensiveuniversitystudentsfromdifferentmajorsonscience,engineering,artsandhumanity.