File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/CVPR.2015.7299143
- Scopus: eid_2-s2.0-84959241019
- WOS: WOS:000387959205014
- Find via
Supplementary
- Citations:
- Appears in Collections:
Conference Paper: Pedestrian detection aided by deep learning semantic tasks
Title | Pedestrian detection aided by deep learning semantic tasks |
---|---|
Authors | |
Issue Date | 2015 |
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 Identifier | http://hdl.handle.net/10722/273674 |
ISSN | 2023 SCImago Journal Rankings: 10.331 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Tian, Yonglong | - |
dc.contributor.author | Luo, Ping | - |
dc.contributor.author | Wang, Xiaogang | - |
dc.contributor.author | Tang, Xiaoou | - |
dc.date.accessioned | 2019-08-12T09:56:20Z | - |
dc.date.available | 2019-08-12T09:56:20Z | - |
dc.date.issued | 2015 | - |
dc.identifier.citation | Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2015, v. 07-12-June-2015, p. 5079-5087 | - |
dc.identifier.issn | 1063-6919 | - |
dc.identifier.uri | http://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.language | eng | - |
dc.relation.ispartof | Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition | - |
dc.title | Pedestrian detection aided by deep learning semantic tasks | - |
dc.type | Conference_Paper | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1109/CVPR.2015.7299143 | - |
dc.identifier.scopus | eid_2-s2.0-84959241019 | - |
dc.identifier.volume | 07-12-June-2015 | - |
dc.identifier.spage | 5079 | - |
dc.identifier.epage | 5087 | - |
dc.identifier.isi | WOS:000387959205014 | - |
dc.identifier.issnl | 1063-6919 | - |