File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: HydraPlus-Net: Attentive Deep Features for Pedestrian Analysis

TitleHydraPlus-Net: Attentive Deep Features for Pedestrian Analysis
Authors
Issue Date2017
Citation
Proceedings of the IEEE International Conference on Computer Vision, 2017, v. 2017-October, p. 350-359 How to Cite?
AbstractPedestrian analysis plays a vital role in intelligent video surveillance and is a key component for security-centric computer vision systems. Despite that the convolutional neural networks are remarkable in learning discriminative features from images, the learning of comprehensive features of pedestrians for fine-grained tasks remains an open problem. In this study, we propose a new attentionbased deep neural network, named as HydraPlus-Net (HPnet), that multi-directionally feeds the multi-level attention maps to different feature layers. The attentive deep features learned from the proposed HP-net bring unique advantages: (1) the model is capable of capturing multiple attentions from low-level to semantic-level, and (2) it explores the multi-scale selectiveness of attentive features to enrich the final feature representations for a pedestrian image. We demonstrate the effectiveness and generality of the proposed HP-net for pedestrian analysis on two tasks, i.e. pedestrian attribute recognition and person reidentification. Intensive experimental results have been provided to prove that the HP-net outperforms the state-of-theart methods on various datasets.
Persistent Identifierhttp://hdl.handle.net/10722/316488
ISSN
2023 SCImago Journal Rankings: 12.263
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorLiu, Xihui-
dc.contributor.authorZhao, Haiyu-
dc.contributor.authorTian, Maoqing-
dc.contributor.authorSheng, Lu-
dc.contributor.authorShao, Jing-
dc.contributor.authorYi, Shuai-
dc.contributor.authorYan, Junjie-
dc.contributor.authorWang, Xiaogang-
dc.date.accessioned2022-09-14T11:40:34Z-
dc.date.available2022-09-14T11:40:34Z-
dc.date.issued2017-
dc.identifier.citationProceedings of the IEEE International Conference on Computer Vision, 2017, v. 2017-October, p. 350-359-
dc.identifier.issn1550-5499-
dc.identifier.urihttp://hdl.handle.net/10722/316488-
dc.description.abstractPedestrian analysis plays a vital role in intelligent video surveillance and is a key component for security-centric computer vision systems. Despite that the convolutional neural networks are remarkable in learning discriminative features from images, the learning of comprehensive features of pedestrians for fine-grained tasks remains an open problem. In this study, we propose a new attentionbased deep neural network, named as HydraPlus-Net (HPnet), that multi-directionally feeds the multi-level attention maps to different feature layers. The attentive deep features learned from the proposed HP-net bring unique advantages: (1) the model is capable of capturing multiple attentions from low-level to semantic-level, and (2) it explores the multi-scale selectiveness of attentive features to enrich the final feature representations for a pedestrian image. We demonstrate the effectiveness and generality of the proposed HP-net for pedestrian analysis on two tasks, i.e. pedestrian attribute recognition and person reidentification. Intensive experimental results have been provided to prove that the HP-net outperforms the state-of-theart methods on various datasets.-
dc.languageeng-
dc.relation.ispartofProceedings of the IEEE International Conference on Computer Vision-
dc.titleHydraPlus-Net: Attentive Deep Features for Pedestrian Analysis-
dc.typeConference_Paper-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1109/ICCV.2017.46-
dc.identifier.scopuseid_2-s2.0-85041891926-
dc.identifier.volume2017-October-
dc.identifier.spage350-
dc.identifier.epage359-
dc.identifier.isiWOS:000425498400037-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats