File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/CVPR.2014.120
- Scopus: eid_2-s2.0-84911449919
- WOS: WOS:000361555600114
- Find via
Supplementary
- Citations:
- Appears in Collections:
Conference Paper: Switchable deep network for pedestrian detection
Title | Switchable deep network for pedestrian detection |
---|---|
Authors | |
Issue Date | 2014 |
Citation | Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2014, p. 899-905 How to Cite? |
Abstract | © 2014 IEEE. In this paper, we propose a Switchable Deep Network (SDN) for pedestrian detection. The SDN automatically learns hierarchical features, salience maps, and mixture representations of different body parts. Pedestrian detection faces the challenges of background clutter and large variations of pedestrian appearance due to pose and viewpoint changes and other factors. One of our key contributions is to propose a Switchable Restricted Boltzmann Machine (SRBM) to explicitly model the complex mixture of visual variations at multiple levels. At the feature levels, it automatically estimates saliency maps for each test sample in order to separate background clutters from discriminative regions for pedestrian detection. At the part and body levels, it is able to infer the most appropriate template for the mixture models of each part and the whole body. We have devised a new generative algorithm to effectively pretrain the SDN and then fine-tune it with back-propagation. Our approach is evaluated on the Caltech and ETH datasets and achieves the state-of-the-art detection performance. |
Persistent Identifier | http://hdl.handle.net/10722/273671 |
ISSN | 2023 SCImago Journal Rankings: 10.331 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Luo, Ping | - |
dc.contributor.author | Tian, Yonglong | - |
dc.contributor.author | Wang, Xiaogang | - |
dc.contributor.author | Tang, Xiaoou | - |
dc.date.accessioned | 2019-08-12T09:56:19Z | - |
dc.date.available | 2019-08-12T09:56:19Z | - |
dc.date.issued | 2014 | - |
dc.identifier.citation | Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2014, p. 899-905 | - |
dc.identifier.issn | 1063-6919 | - |
dc.identifier.uri | http://hdl.handle.net/10722/273671 | - |
dc.description.abstract | © 2014 IEEE. In this paper, we propose a Switchable Deep Network (SDN) for pedestrian detection. The SDN automatically learns hierarchical features, salience maps, and mixture representations of different body parts. Pedestrian detection faces the challenges of background clutter and large variations of pedestrian appearance due to pose and viewpoint changes and other factors. One of our key contributions is to propose a Switchable Restricted Boltzmann Machine (SRBM) to explicitly model the complex mixture of visual variations at multiple levels. At the feature levels, it automatically estimates saliency maps for each test sample in order to separate background clutters from discriminative regions for pedestrian detection. At the part and body levels, it is able to infer the most appropriate template for the mixture models of each part and the whole body. We have devised a new generative algorithm to effectively pretrain the SDN and then fine-tune it with back-propagation. Our approach is evaluated on the Caltech and ETH datasets and achieves the state-of-the-art detection performance. | - |
dc.language | eng | - |
dc.relation.ispartof | Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition | - |
dc.title | Switchable deep network for pedestrian detection | - |
dc.type | Conference_Paper | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1109/CVPR.2014.120 | - |
dc.identifier.scopus | eid_2-s2.0-84911449919 | - |
dc.identifier.spage | 899 | - |
dc.identifier.epage | 905 | - |
dc.identifier.isi | WOS:000361555600114 | - |
dc.identifier.issnl | 1063-6919 | - |