Generalization between canonical and non-canonical views in object recognition
Identifieur interne : 001B76 ( Main/Merge ); précédent : 001B75; suivant : 001B77Generalization between canonical and non-canonical views in object recognition
Auteurs : Tandra Ghose [Allemagne] ; Zili LiuSource :
- Journal of Vision [ 1534-7362 ] ; 2013.
Abstract
Viewpoint generalization in object recognition is the process that allows recognition of a given 3D object from many different viewpoints despite variations in its 2D projections. We used the canonical view effects as a foundation to empirically test the validity of a major theory in object recognition, the view-approximation model (Poggio & Edelman,
Url:
DOI: 10.1167/13.1.1
PubMed: 23283692
PubMed Central: 3586995
Links toward previous steps (curation, corpus...)
- to stream Pmc, to step Corpus: 001486
- to stream Pmc, to step Curation: 001486
- to stream Pmc, to step Checkpoint: 001238
- to stream Ncbi, to step Merge: 002416
- to stream Ncbi, to step Curation: 002416
- to stream Ncbi, to step Checkpoint: 002416
Links to Exploration step
PMC:3586995Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en">Generalization between canonical and non-canonical views in object recognition</title>
<author><name sortKey="Ghose, Tandra" sort="Ghose, Tandra" uniqKey="Ghose T" first="Tandra" last="Ghose">Tandra Ghose</name>
<affiliation wicri:level="4"><nlm:aff id="aff1">Department of Psychology, Technical University of Kaiserslautern, Germany</nlm:aff>
<country xml:lang="fr">Allemagne</country>
<wicri:regionArea>Department of Psychology, Technical University of Kaiserslautern</wicri:regionArea>
<placeName><settlement type="city">Kaiserslautern</settlement>
<region type="land" nuts="2">Rhénanie-Palatinat</region>
</placeName>
<orgName type="university">Université de technologie de Kaiserslautern</orgName>
</affiliation>
</author>
<author><name sortKey="Liu, Zili" sort="Liu, Zili" uniqKey="Liu Z" first="Zili" last="Liu">Zili Liu</name>
<affiliation><nlm:aff>NONE</nlm:aff>
</affiliation>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">PMC</idno>
<idno type="pmid">23283692</idno>
<idno type="pmc">3586995</idno>
<idno type="url">http://www.ncbi.nlm.nih.gov/pmc/articles/PMC3586995</idno>
<idno type="RBID">PMC:3586995</idno>
<idno type="doi">10.1167/13.1.1</idno>
<date when="2013">2013</date>
<idno type="wicri:Area/Pmc/Corpus">001486</idno>
<idno type="wicri:Area/Pmc/Curation">001486</idno>
<idno type="wicri:Area/Pmc/Checkpoint">001238</idno>
<idno type="wicri:Area/Ncbi/Merge">002416</idno>
<idno type="wicri:Area/Ncbi/Curation">002416</idno>
<idno type="wicri:Area/Ncbi/Checkpoint">002416</idno>
<idno type="wicri:Area/Main/Merge">001B76</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en" level="a" type="main">Generalization between canonical and non-canonical views in object recognition</title>
<author><name sortKey="Ghose, Tandra" sort="Ghose, Tandra" uniqKey="Ghose T" first="Tandra" last="Ghose">Tandra Ghose</name>
<affiliation wicri:level="4"><nlm:aff id="aff1">Department of Psychology, Technical University of Kaiserslautern, Germany</nlm:aff>
<country xml:lang="fr">Allemagne</country>
<wicri:regionArea>Department of Psychology, Technical University of Kaiserslautern</wicri:regionArea>
<placeName><settlement type="city">Kaiserslautern</settlement>
<region type="land" nuts="2">Rhénanie-Palatinat</region>
</placeName>
<orgName type="university">Université de technologie de Kaiserslautern</orgName>
</affiliation>
</author>
<author><name sortKey="Liu, Zili" sort="Liu, Zili" uniqKey="Liu Z" first="Zili" last="Liu">Zili Liu</name>
<affiliation><nlm:aff>NONE</nlm:aff>
</affiliation>
</author>
</analytic>
<series><title level="j">Journal of Vision</title>
<idno type="eISSN">1534-7362</idno>
<imprint><date when="2013">2013</date>
</imprint>
</series>
</biblStruct>
</sourceDesc>
</fileDesc>
<profileDesc><textClass></textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en"><p>Viewpoint generalization in object recognition is the process that allows recognition of a given 3D object from many different viewpoints despite variations in its 2D projections. We used the canonical view effects as a foundation to empirically test the validity of a major theory in object recognition, the view-approximation model (Poggio & Edelman, <xref ref-type="bibr" rid="i1534-7362-13-1-1-Poggio2">1990</xref>
). This model predicts that generalization should be better when an object is first seen from a non-canonical view and <italic>then</italic>
a canonical view than when seen in the reversed order. We also manipulated object similarity to study the degree to which this view generalization was constrained by shape details and task instructions (object vs. image recognition). Old-new recognition performance for basic and subordinate level objects was measured in separate blocks. We found that for object recognition, view generalization between canonical and non-canonical views was comparable for basic level objects. For subordinate level objects, recognition performance was more accurate from non-canonical to canonical views than the other way around. When the task was changed from object recognition to image recognition, the pattern of the results reversed. Interestingly, participants responded “old” to “new” images of “old” objects with a substantially higher rate than to “new” objects, despite instructions to the contrary, thereby indicating involuntary view generalization. Our empirical findings are incompatible with the prediction of the view-approximation theory, and argue against the hypothesis that views are stored independently.</p>
</div>
</front>
</TEI>
</record>
Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Ticri/CIDE/explor/HapticV1/Data/Main/Merge
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 001B76 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Merge/biblio.hfd -nk 001B76 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien |wiki= Ticri/CIDE |area= HapticV1 |flux= Main |étape= Merge |type= RBID |clé= PMC:3586995 |texte= Generalization between canonical and non-canonical views in object recognition }}
Pour générer des pages wiki
HfdIndexSelect -h $EXPLOR_AREA/Data/Main/Merge/RBID.i -Sk "pubmed:23283692" \ | HfdSelect -Kh $EXPLOR_AREA/Data/Main/Merge/biblio.hfd \ | NlmPubMed2Wicri -a HapticV1
This area was generated with Dilib version V0.6.23. |