Hierarchical Joint Max-Margin Learning of Mid and Top Level Representations for Visual Recognition

Simple item page
dc.contributor.authorLöbel Díaz, Hans-Albert
dc.contributor.authorVidal Navarro, René Esteban
dc.contributor.authorSoto Arriaza, Álvaro
dc.date.accessioned2022-05-13T19:15:18Z
dc.date.available2022-05-13T19:15:18Z
dc.date.issued2013
dc.description.abstractCurrently, Bag-of-Visual-Words (BoVW) and part-based methods are the most popular approaches for visual recognition. In both cases, a mid-level representation is built on top of low-level image descriptors and top-level classifiers use this mid-level representation to achieve visual recognition. While in current part-based approaches, mid- and top-level representations are usually jointly trained, this is not the usual case for BoVW schemes. A main reason for this is the complex data association problem related to the usual large dictionary size needed by BoVW approaches. As a further observation, typical solutions based on BoVW and part-based representations are usually limited to extensions of binary classification schemes, a strategy that ignores relevant correlations among classes. In this work we propose a novel hierarchical approach to visual recognition based on a BoVW scheme that jointly learns suitable mid- and top-level representations. Furthermore, using a max-margin learning framework, the proposed approach directly handles the multiclass case at both levels of abstraction. We test our proposed method using several popular benchmark datasets. As our main result, we demonstrate that, by coupling learning of mid- and top-level representations, the proposed approach fosters sharing of discriminative visual words among target classes, being able to achieve state-of-the-art recognition performance using far less visual words than previous approaches.
dc.fuente.origenIEEE
dc.identifier.doi10.1109/ICCV.2013.213
dc.identifier.isbn978-1479928408
dc.identifier.issn2380-7504
dc.identifier.urihttps://doi.org/10.1109/ICCV.2013.213
dc.identifier.urihttps://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=6751321
dc.identifier.urihttps://repositorio.uc.cl/handle/11534/63880
dc.information.autorucEscuela de ingeniería ; Lobel Díaz, Hans Albert ; S/I ; 131278
dc.information.autorucEscuela de ingeniería ; Vidal Navarro, René Esteban ; S/I ; 94710
dc.information.autorucEscuela de ingeniería ; Soto Arriaza, Álvaro ; S/I ; 73678
dc.language.isoen
dc.nota.accesoContenido parcial
dc.publisherIEEE
dc.relation.ispartofIEEE International Conference on Computer Vision (2013 : Sydney, NSW, Australia)
dc.rightsacceso restringido
dc.subjectVisualization
dc.subjectDictionaries
dc.subjectTraining
dc.subjectVectors
dc.subjectEncoding
dc.subjectSupport vector machines
dc.subjectSemantics
dc.titleHierarchical Joint Max-Margin Learning of Mid and Top Level Representations for Visual Recognitiones_ES
dc.typecomunicación de congreso
sipa.codpersvinculados131278
sipa.codpersvinculados94710
sipa.codpersvinculados73678
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Hierarchical Joint Max-Margin Learning of Mid and Top Level Representations for Visual Recognition.pdf
Size:
315.85 KB
Format:
Adobe Portable Document Format
Description:
Download
Collections
Artículos de conferencia