File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: A discriminative model for object representation and detection via sparse features

TitleA discriminative model for object representation and detection via sparse features
Authors
KeywordsObject detection
Discriminative model
Sparse features
Issue Date2010
Citation
Proceedings - International Conference on Pattern Recognition, 2010, p. 3077-3080 How to Cite?
AbstractThis paper proposes a discriminative model that represents an object category with a batch of boosted image patches, motivated by detecting and localizing objects with sparse features. Instead of designing features carefully and category-specifically as in previous work, we extract a massive number of local image patches from the positive object instances and quantize them as weak classifiers. Then we extend the Adaboost algorithm for learning the patch-based model integrating object appearance and structure information. With the learned model, a few features are activated to localize instances in the testing images. In the experiments, we apply the proposed method with several public datasets and achieve advancing performance. © 2010 IEEE.
Persistent Identifierhttp://hdl.handle.net/10722/273503
ISSN
2023 SCImago Journal Rankings: 0.584

 

DC FieldValueLanguage
dc.contributor.authorSong, Xi-
dc.contributor.authorLuo, Ping-
dc.contributor.authorLin, Liang-
dc.contributor.authorJia, Yunde-
dc.date.accessioned2019-08-12T09:55:46Z-
dc.date.available2019-08-12T09:55:46Z-
dc.date.issued2010-
dc.identifier.citationProceedings - International Conference on Pattern Recognition, 2010, p. 3077-3080-
dc.identifier.issn1051-4651-
dc.identifier.urihttp://hdl.handle.net/10722/273503-
dc.description.abstractThis paper proposes a discriminative model that represents an object category with a batch of boosted image patches, motivated by detecting and localizing objects with sparse features. Instead of designing features carefully and category-specifically as in previous work, we extract a massive number of local image patches from the positive object instances and quantize them as weak classifiers. Then we extend the Adaboost algorithm for learning the patch-based model integrating object appearance and structure information. With the learned model, a few features are activated to localize instances in the testing images. In the experiments, we apply the proposed method with several public datasets and achieve advancing performance. © 2010 IEEE.-
dc.languageeng-
dc.relation.ispartofProceedings - International Conference on Pattern Recognition-
dc.subjectObject detection-
dc.subjectDiscriminative model-
dc.subjectSparse features-
dc.titleA discriminative model for object representation and detection via sparse features-
dc.typeConference_Paper-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1109/ICPR.2010.754-
dc.identifier.scopuseid_2-s2.0-78149490858-
dc.identifier.spage3077-
dc.identifier.epage3080-
dc.identifier.issnl1051-4651-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats