Learning Shared, Discriminative, and Compact Representations for Visual Recognition

Simple item page
dc.contributor.authorLöbel Díaz, Hans-Albert
dc.contributor.authorVidal, R.
dc.contributor.authorSoto Arriaza, Álvaro Marcelo
dc.date.accessioned2022-05-18T14:04:50Z
dc.date.available2022-05-18T14:04:50Z
dc.date.issued2015
dc.description.abstractDictionary-based and part-based methods are among the most popular approaches to visual recognition. In both methods, a mid-level representation is built on top of low-level image descriptors and high-level classifiers are trained on top of the mid-level representation. While earlier methods built the mid-level representation without supervision, there is currently great interest in learning both representations jointly to make the mid-level representation more discriminative. In this work we propose a new approach to visual recognition that jointly learns a shared, discriminative, and compact mid-level representation and a compact high-level representation. By using a structured output learning framework, our approach directly handles the multiclass case at both levels of abstraction. Moreover, by using a group-sparse prior in the structured output learning framework, our approach encourages sharing of visual words and thus reduces the number of words used to represent each class. We test our proposed method on several popular benchmarks. Our results show that, by jointly learning midand high-level representations, and fostering the sharing of discriminative visual words among target classes, we are able to achieve state-of-the-art recognition performance using far less visual words than previous approaches.
dc.fuente.origenIEEE
dc.identifier.doi10.1109/TPAMI.2015.2408349
dc.identifier.eissn1939-3539
dc.identifier.issn0162-8828
dc.identifier.urihttps://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=7053941
dc.identifier.urihttps://doi.org/10.1109/TPAMI.2015.2408349
dc.identifier.urihttps://repositorio.uc.cl/handle/11534/64117
dc.information.autorucEscuela de ingeniería ; Lobel Díaz, Hans Albert ; S/I ; 131278
dc.information.autorucEscuela de ingeniería ; Vidal, R. ; S/I ; 94710
dc.information.autorucEscuela de ingeniería ; Soto Arriaza, Álvaro Marcelo ; S/I ; 73678
dc.issue.numero11
dc.language.isoen
dc.nota.accesoContenido parcial
dc.pagina.final2231
dc.pagina.inicio2218
dc.publisherIEEE
dc.revistaIEEE Transactions on Pattern Analysis and Machine Intelligence
dc.rightsacceso restringido
dc.subjectVisualization
dc.subjectDictionaries
dc.subjectJoints
dc.subjectFeature extraction
dc.subjectOptimization
dc.subjectComplexity theory
dc.subjectEncoding
dc.titleLearning Shared, Discriminative, and Compact Representations for Visual Recognitiones_ES
dc.typeartículo
dc.volumen37
sipa.codpersvinculados131278
sipa.codpersvinculados94710
sipa.codpersvinculados73678
Files
Collections
Artículos de revistas