liu.seSearch for publications in DiVA
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
PSTR: End-to-End One-Step Person Search With Transformers
Tianjin Univ, Peoples R China; Mohamed Bin Zayed Univ Artificial Intelligence, U Arab Emirates.
Tianjin Univ, Peoples R China.
Mohamed Bin Zayed Univ Artificial Intelligence, U Arab Emirates.
Mohamed Bin Zayed Univ Artificial Intelligence, U Arab Emirates.
Show others and affiliations
2022 (English)In: 2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), IEEE COMPUTER SOC , 2022, p. 9448-9457Conference paper, Published paper (Refereed)
Abstract [en]

We propose a novel one-step transformer-based person search framework, PSTR, that jointly performs person detection and re-identification (re-id) in a single architecture. PSTR comprises a person search-specialized (PSS) module that contains a detection encoder-decoder for person detection along with a discriminative re-id decoder for person re-id. The discriminative re-id decoder utilizes a multi-level supervision scheme with a shared decoder for discriminative re-id feature learning and also comprises a part attention block to encode relationship between different parts of a person. We further introduce a simple multi-scale scheme to support re-id across person instances at different scales. PSTR jointly achieves the diverse objectives of object-level recognition (detection) and instance-level matching (re-id). To the best of our knowledge, we are the first to propose an end-to-end one-step transformer-based person search framework. Experiments are performed on two popular benchmarks: CUHK-SYSU and PRW. Our extensive ablations reveal the merits of the proposed contributions. Further, the proposed PSTR sets a new state-of-the-art on both benchmarks. On the challenging PRW benchmark, PSTR achieves a mean average precision (mAP) score of 56.5%.

Place, publisher, year, edition, pages
IEEE COMPUTER SOC , 2022. p. 9448-9457
Series
IEEE Conference on Computer Vision and Pattern Recognition, ISSN 1063-6919
National Category
Computer Vision and Robotics (Autonomous Systems)
Identifiers
URN: urn:nbn:se:liu:diva-190652DOI: 10.1109/CVPR52688.2022.00924ISI: 000870759102051ISBN: 9781665469463 (electronic)ISBN: 9781665469470 (print)OAI: oai:DiVA.org:liu-190652DiVA, id: diva2:1720835
Conference
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, jun 18-24, 2022
Note

Funding Agencies|National Key RD Program [2018AAA0102800]; National Natural Science Foundation of China [61906131]; Tianjin Natural Science Foundation [21JCQNJC00420]; CAAI-Huawei MindSpore Open Fund

Available from: 2022-12-20 Created: 2022-12-20 Last updated: 2022-12-20

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full text

Search in DiVA

By author/editor
Khan, Fahad
By organisation
Computer VisionFaculty of Science & Engineering
Computer Vision and Robotics (Autonomous Systems)

Search outside of DiVA

GoogleGoogle Scholar

doi
isbn
urn-nbn

Altmetric score

doi
isbn
urn-nbn
Total: 20 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf