File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Pedestrian detection aided by deep learning semantic tasks

TitlePedestrian detection aided by deep learning semantic tasks
Authors
Issue Date2015
Citation
Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2015, v. 07-12-June-2015, p. 5079-5087 How to Cite?
Abstract© 2015 IEEE. Deep learning methods have achieved great successes in pedestrian detection, owing to its ability to learn discriminative features from raw pixels. However, they treat pedestrian detection as a single binary classification task, which may confuse positive with hard negative samples (Fig.1 (a)). To address this ambiguity, this work jointly optimize pedestrian detection with semantic tasks, including pedestrian attributes (e.g. 'carrying backpack') and scene attributes (e.g. 'vehicle', 'tree', and 'horizontal'). Rather than expensively annotating scene attributes, we transfer attributes information from existing scene segmentation datasets to the pedestrian dataset, by proposing a novel deep model to learn high-level features from multiple tasks and multiple data sources. Since distinct tasks have distinct convergence rates and data from different datasets have different distributions, a multi-task deep model is carefully designed to coordinate tasks and reduce discrepancies among datasets. Extensive evaluations show that the proposed approach outperforms the state-of-the-art on the challenging Caltech [9] and ETH [10] datasets where it reduces the miss rates of previous deep models by 17 and 5.5 percent, respectively.
Persistent Identifierhttp://hdl.handle.net/10722/273674
ISSN
2023 SCImago Journal Rankings: 10.331
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorTian, Yonglong-
dc.contributor.authorLuo, Ping-
dc.contributor.authorWang, Xiaogang-
dc.contributor.authorTang, Xiaoou-
dc.date.accessioned2019-08-12T09:56:20Z-
dc.date.available2019-08-12T09:56:20Z-
dc.date.issued2015-
dc.identifier.citationProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2015, v. 07-12-June-2015, p. 5079-5087-
dc.identifier.issn1063-6919-
dc.identifier.urihttp://hdl.handle.net/10722/273674-
dc.description.abstract© 2015 IEEE. Deep learning methods have achieved great successes in pedestrian detection, owing to its ability to learn discriminative features from raw pixels. However, they treat pedestrian detection as a single binary classification task, which may confuse positive with hard negative samples (Fig.1 (a)). To address this ambiguity, this work jointly optimize pedestrian detection with semantic tasks, including pedestrian attributes (e.g. 'carrying backpack') and scene attributes (e.g. 'vehicle', 'tree', and 'horizontal'). Rather than expensively annotating scene attributes, we transfer attributes information from existing scene segmentation datasets to the pedestrian dataset, by proposing a novel deep model to learn high-level features from multiple tasks and multiple data sources. Since distinct tasks have distinct convergence rates and data from different datasets have different distributions, a multi-task deep model is carefully designed to coordinate tasks and reduce discrepancies among datasets. Extensive evaluations show that the proposed approach outperforms the state-of-the-art on the challenging Caltech [9] and ETH [10] datasets where it reduces the miss rates of previous deep models by 17 and 5.5 percent, respectively.-
dc.languageeng-
dc.relation.ispartofProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition-
dc.titlePedestrian detection aided by deep learning semantic tasks-
dc.typeConference_Paper-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1109/CVPR.2015.7299143-
dc.identifier.scopuseid_2-s2.0-84959241019-
dc.identifier.volume07-12-June-2015-
dc.identifier.spage5079-
dc.identifier.epage5087-
dc.identifier.isiWOS:000387959205014-
dc.identifier.issnl1063-6919-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats