Mining Discriminative Co-occurrence Patterns for Visual Recognition
MiningDiscriminativeCo-occurrencePatternsforVisualRecognition
JunsongYuanSchoolofEEE
NanyangTechnologicalUniversity
Singapore639798
jsyuan@ntu.edu.sg
MingYang
Dept.ofMediaAnalyticsNECLaboratoriesAmericaCupertino,CA,95014USA
myang@sv.nec-labs.com
YingWuEECSDept.
NorthwesternUniversityEvanston,IL,60208USA
yingwu@eecs.northwestern.edu
Abstract
Theco-occurrencepattern,acombinationofbinaryorlocalfeatures,ismorediscriminativethanindividualfea-turesandhasshownitsadvantagesinobject,scene,andactionrecognition.Wediscusstwotypesofco-occurrencepatternsthatarecomplementarytoeachother,thecon-junction(AND)anddisjunction(OR)ofbinaryfeatures.Thenecessaryconditionofidentifyingdiscriminativeco-occurrencepatternsis rstlyprovided.Thenweproposeanoveldataminingmethodtoef cientlydiscovertheop-timalco-occurrencepatternwithminimumempiricalerror,despitethenoisytrainingdataset.ThisminingprocedureofANDandORpatternsisreadilyintegratedtoboosting,whichimprovesthegeneralizationabilityovertheconven-tionalboostingdecisiontreesandboostingdecisionstumps.Ourversatileexperimentsonobject,scene,andactioncat-egorizationvalidatetheadvantagesofthediscovereddis-criminativeco-occurrencepatterns.
Figure1.Byinferringbinaryvisualattributesfromrawimagefea-tures,suchaswheels,furry[6][4],wecandistinguishbikesfrompeoplebyaco-occurrenceofcertainattributes,forexampleabikehasmetalandwheels,butdoesnothavehead.Giventwoclassesofobjects,describedby(possiblyquitenoisy)attributes,canweef cientlydiscovertheco-occurrenceofattributesthatcanbestdiscriminatethem?
1.Introduction
Duetothecompositionalpropertyofvisualobjects,scenes,andactions,thediscoveryofdiscriminativeco-occurrencepatternisoffundamentalimportanceinrec-ognizingthem.Althoughtheextractedfeatures,suchascolor,texture,shape,ormotionfeatures,canbequiteweakindividually,anappropriatecombinationofthemwillbringastrongfeaturewhichismuchmorediscrimina-tive[31][29][3][16][2][9].Therehasbeenarecenttrendinminingco-occurrencepatternsforvisualrecogni-tion.Forexample,everyreal-worldobjectisassociatedwithnumerousvisualattributesintermsofitsmaterial,structure,shape,etc,[11][4][10],althoughitisdif culttodifferentiatethemusingasinglevisualattribute,theycanbewelldistinguishedbytheco-occurrenceofspeci cat-tributes,asillustratedinFig.1.
Inabinaryclassi cationproblem,givenacollectionofNbinaryfeatures,theproblemofco-occurrencepat-ternminingistoselectasubsetfromtheseNfea-tures,suchthattheco-occurrenceofthemcanbestdis-2777
criminatethetwoclasses.Inspiteofmanyprevi-ousworksinminingandintegratingco-occurrencepat-terns[22][20][3][29][33][16][24][9][27],noneofthesemethodsistargetedat ndingthemostdiscrimina-tiveco-occurrencepatternwiththesmallestclassi cationerror.GivenNbinaryfeatures,becausetheco-occurrencepatterncancontainanarbitrarynumberoffeatures(uptoN),thetotalnumberofcandidatesofco-occurrencepat-ternsisexponentiallylarge(e.g.3Nifconsideringtheneg-ativevalueor2Nifonlyconsideringthepositivevalue.)Asaresult,itiscomputationallyintractabletoperformanexhaustivesearch.Evenworse,unlikeconventionalfeatureselectiontask,themonotonicpropertyoffeaturesubsetdoesnotholdinsearchingco-occurrencepatterns.Namely,a(K+1)-orderbinaryfeatureisnotnecessarilybetterthanaK-orderone.Therefore,thebranch-and-boundsearchcannotbeapplieddirectly[18].Existingapproachesforco-occurrencepatternsearch,suchassequentialfor-wardselection[16][24],orrecentdatamining-drivenap-proaches[22][20][3][29][33],donotguaranteetheop-timalityoftheselectedco-occurrencepatterns.Ingeneral,whenthetrainingdataisnoisy,itisstillanopenproblemto ndtheco-occurrencepatternofthebestperformance,e.g.,minimumclassi cationerror[17].
DISCRIMINATIVE TRAINING FOR SPEECH RECOGNITION A DISSERTATION SUBMITTED TO THE...President of ATR Auditory and Visual Perception Research Laboratories, and Dr...
Fine-scale species co-occurrence patterns in an old-growth temperate forest_自然科学_专业资料。Forest Ecology and Management 257 (2009) 2115–2120 ...
Latent-Dynamic Discriminative Models for Continuous Gesture Recognition Louis-...visual gestures and can distinguish subtle motion patterns such as natural ...
Extraction of Patterns Displaying Hyponym-Hypernym Co-Occurrence from Co... verb subcategorization frame recognition, collocation acquisition and, ...
Junsong Yuan, Ming Yang, and Ying Wu, Mining Discriminative Co-occurrence Patterns for Visual Recognition, Proc. IEEE Conference on Computer Vision and ...
recognition of spatio-temporal visual patterns from... try to capture the semantic co-occurrence ...Mori. Discriminative latent models for recognizing ...
Warning for Hospitalized Patients via Data Mining...? ? ? ? ? Temporal bucketing Discriminative ... related to co-occurrence of patterns – First ...
visual co-occurrence patterns, motivating novel ...scene representation, discriminative for accurate ...recognition, wide baseline matching, and image ...
visual co-occurrence patterns, motivating novel ...scene representation, discriminative for accurate ...recognition, wide baseline matching, and image ...
热门文档