Pose Recognition with Cascade Transformers

In this paper, we present a regression-based pose recognition method using cascade Transformers. One way to categorize the existing approaches in this domain is to separate them into 1). heatmap-based and 2). regression-based. In general, heatmap-based methods achieve higher accuracy but are subject...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) s. 1944 - 1953
Hlavní autori: Li, Ke, Wang, Shijie, Zhang, Xiang, Xu, Yifan, Xu, Weijian, Tu, Zhuowen
Médium: Konferenčný príspevok..
Jazyk:English
Vydavateľské údaje: IEEE 01.06.2021
Predmet:
ISSN:1063-6919
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract In this paper, we present a regression-based pose recognition method using cascade Transformers. One way to categorize the existing approaches in this domain is to separate them into 1). heatmap-based and 2). regression-based. In general, heatmap-based methods achieve higher accuracy but are subject to various heuristic designs (not end-to-end mostly), whereas regression-based approaches attain relatively lower accuracy but they have less intermediate non-differentiable steps. Here we utilize the encoder-decoder structure in Transformers to perform regression-based person and keypoint detection that is general-purpose and requires less heuristic design compared with the existing approaches. We demonstrate the keypoint hypothesis (query) refinement process across different self-attention layers to reveal the recursive self-attention mechanism in Transformers. In the experiments, we report competitive results for pose recognition when compared with the competing regression-based methods.
AbstractList In this paper, we present a regression-based pose recognition method using cascade Transformers. One way to categorize the existing approaches in this domain is to separate them into 1). heatmap-based and 2). regression-based. In general, heatmap-based methods achieve higher accuracy but are subject to various heuristic designs (not end-to-end mostly), whereas regression-based approaches attain relatively lower accuracy but they have less intermediate non-differentiable steps. Here we utilize the encoder-decoder structure in Transformers to perform regression-based person and keypoint detection that is general-purpose and requires less heuristic design compared with the existing approaches. We demonstrate the keypoint hypothesis (query) refinement process across different self-attention layers to reveal the recursive self-attention mechanism in Transformers. In the experiments, we report competitive results for pose recognition when compared with the competing regression-based methods.
Author Xu, Weijian
Tu, Zhuowen
Xu, Yifan
Zhang, Xiang
Li, Ke
Wang, Shijie
Author_xml – sequence: 1
  givenname: Ke
  surname: Li
  fullname: Li, Ke
  email: keliictcas@gmail.com
  organization: University of Chinese Academy of Sciences,Beijing,China
– sequence: 2
  givenname: Shijie
  surname: Wang
  fullname: Wang, Shijie
  email: wang98thu@gmail.com
  organization: Tsinghua University,Beijing,China
– sequence: 3
  givenname: Xiang
  surname: Zhang
  fullname: Zhang, Xiang
  email: zx1239856@gmail.com
  organization: Tsinghua University,Beijing,China
– sequence: 4
  givenname: Yifan
  surname: Xu
  fullname: Xu, Yifan
  email: yix081@ucsd.edu
  organization: University of California San Diego,San Diego,USA
– sequence: 5
  givenname: Weijian
  surname: Xu
  fullname: Xu, Weijian
  email: wex041@ucsd.edu
  organization: University of California San Diego,San Diego,USA
– sequence: 6
  givenname: Zhuowen
  surname: Tu
  fullname: Tu, Zhuowen
  email: ztu@ucsd.edu
  organization: University of California San Diego,San Diego,USA
BookMark eNotzstKw0AUgOFRFGxrn0AXWQuJ58wtM0sJ3qBgKcFtOZk50RGbSCYgvr0FXf27n28pzoZxYCGuESpE8LfN63anrVZ1JUFiBYDenYglWmu0NuDlqVggWFVaj_5CrHP-AAAlEa13C3GzHTMXOw7j25DmNA7Fd5rfi4ZyoMhFO9GQ-3E68JQvxXlPn5nX_12J9uG-bZ7Kzcvjc3O3KZMENZcx2A5r6DG4QEeSYdtDiNpH6oyGozI400fjFRmqZRfqyKQ8krPasVQrcfW3Tcy8_5rSgaafvTe1U1qrX_KjQ9c
CODEN IEEPAD
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/CVPR46437.2021.00198
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan (POP) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP) 1998-present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Applied Sciences
EISBN 1665445092
9781665445092
EISSN 1063-6919
EndPage 1953
ExternalDocumentID 9578344
Genre orig-research
GroupedDBID 6IE
6IH
6IL
6IN
AAWTH
ABLEC
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IEGSK
IJVOP
OCL
RIE
RIL
RIO
ID FETCH-LOGICAL-i203t-dc6b170f1c8ca0215e6f0cd49dab540202c85fd593a5a72bc7dea391a8648e23
IEDL.DBID RIE
ISICitedReferencesCount 215
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000739917302014&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Wed Aug 27 02:24:15 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i203t-dc6b170f1c8ca0215e6f0cd49dab540202c85fd593a5a72bc7dea391a8648e23
PageCount 10
ParticipantIDs ieee_primary_9578344
PublicationCentury 2000
PublicationDate 2021-June
PublicationDateYYYYMMDD 2021-06-01
PublicationDate_xml – month: 06
  year: 2021
  text: 2021-June
PublicationDecade 2020
PublicationTitle Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online)
PublicationTitleAbbrev CVPR
PublicationYear 2021
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0003211698
Score 2.6211445
Snippet In this paper, we present a regression-based pose recognition method using cascade Transformers. One way to categorize the existing approaches in this domain...
SourceID ieee
SourceType Publisher
StartPage 1944
SubjectTerms Computer vision
Decoding
Heating systems
Pattern recognition
Task analysis
Transformers
Visualization
Title Pose Recognition with Cascade Transformers
URI https://ieeexplore.ieee.org/document/9578344
WOSCitedRecordID wos000739917302014&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEB5q8eCpaiu-ycGTuHZfeZ2LxVNZSpHeyiSZQC-70m39_W6224rgxVvIJUwefPP4vgzAU3NpjDRNdKIU6Sj33kWInofvtZXgGp0R2DabkLOZWi510YOXoxaGiFryGb2GYVvLd5XdhVTZWPO2LcQJnEgp91qtYz4layIZoVWnjktiPZ58FPM81KWaKDBNQslBq189VFoImQ7-t_g5jH60eKw4oswF9Ki8hEHnPLLuadZDeC6qmtj8wAeqShZSrGyCdWDAs8XBQW3cvREspm-LyXvUNUKI1mmcbSNnhUlk7BOrLAaQJuFj63Lt0PAQAKZWce-4zpCjTI2VjjDTCSqRK0qzK-iXVUnXwIQMkkDiynDKLWqUgvLAzfSpb3BJ3sAwWL763H91seqMvv17-g7OwtbumVP30N9udvQAp_Zru643j-35fAO38JC2
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1JS8NAFH7UKuipaivu5uBJjM0y67lYKtYSSpDeymTmDfSSlKb195tJ04rgxdswl-HNwveW75sH8FhdmoxnVXQiBEqfWGt8pSx132sLRqUyGVN1swk-mYjZTCYteN5rYRCxJp_hixvWtXxT6I1LlfUlrdtCHMAhJSQKt2qtfUYlrmIZJkWjjwsD2R98JlPiKlNVHBiFruggxa8uKjWIDDv_W_4Uej9qPC_Z48wZtDA_h07jPnrN4yy78JQUJXrTHSOoyD2XZPUGqnQceC_duaiVw9eDdPiaDkZ-0wrBX0RBvPaNZlnIAxtqoZWDaWQ20IZIozLqQsBIC2oNlbGiikeZ5gZVLEMlGBEYxRfQzoscL8Fj3IkCkYqMItFKKs6QOHamjWyFTPwKus7y-XL72cW8Mfr67-kHOB6lH-P5-G3yfgMnbpu3PKpbaK9XG7yDI_21XpSr-_qsvgFy_pP9
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=proceeding&rft.title=Proceedings+%28IEEE+Computer+Society+Conference+on+Computer+Vision+and+Pattern+Recognition.+Online%29&rft.atitle=Pose+Recognition+with+Cascade+Transformers&rft.au=Li%2C+Ke&rft.au=Wang%2C+Shijie&rft.au=Zhang%2C+Xiang&rft.au=Xu%2C+Yifan&rft.date=2021-06-01&rft.pub=IEEE&rft.eissn=1063-6919&rft.spage=1944&rft.epage=1953&rft_id=info:doi/10.1109%2FCVPR46437.2021.00198&rft.externalDocID=9578344