MFDNet: Collaborative Poses Perception and Matrix Fisher Distribution for Head Pose Estimation

Head pose estimation suffers from several problems, including low pose tolerance under different disturbances and ambiguity arising from common head pose representation. In this study, a robust three-branch model with triplet module and matrix Fisher distribution module is proposed to address these...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE transactions on multimedia Jg. 24; S. 2449 - 2460
Hauptverfasser:	Liu, Hai, Fang, Shuai, Zhang, Zhaoli, Li, Duantengchuan, Lin, Ke, Wang, Jiazhang
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	Piscataway IEEE 2022 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:	Euler angles Feature extraction Head Head movement Head pose estimation Matrix Fisher distribution Measurement Metric learning Modules Pose estimation Quaternions Robustness Rotation matrix Singular value decomposition Solid modeling Three-dimensional displays Triplet loss Uncertainty
ISSN:	1520-9210, 1941-0077
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Abstract	Head pose estimation suffers from several problems, including low pose tolerance under different disturbances and ambiguity arising from common head pose representation. In this study, a robust three-branch model with triplet module and matrix Fisher distribution module is proposed to address these problems. Based on metric learning, the triplet module employs triplet architecture and triplet loss. It is implemented to maximize the distance between embeddings with different pose pairs and minimize the distance between embeddings with same pose pairs. It can learn a highly discriminate and robust embedding related to head pose. Moreover, the rotation matrix instead of Euler angle and unit quaternion is utilized to represent head pose. An exponential probability density model based on the rotation matrix (referred to as the matrix Fisher distribution) is developed to model head rotation uncertainty. The matrix Fisher distribution can further analyze the head pose, and its maximum likelihood obtained using singular value decomposition provides enhanced accuracy. Extensive experiments executed over AFLW2000 and BIWI datasets demonstrate that the proposed model achieves state-of-the-art performance in comparison with traditional methods.
AbstractList	Head pose estimation suffers from several problems, including low pose tolerance under different disturbances and ambiguity arising from common head pose representation. In this study, a robust three-branch model with triplet module and matrix Fisher distribution module is proposed to address these problems. Based on metric learning, the triplet module employs triplet architecture and triplet loss. It is implemented to maximize the distance between embeddings with different pose pairs and minimize the distance between embeddings with same pose pairs. It can learn a highly discriminate and robust embedding related to head pose. Moreover, the rotation matrix instead of Euler angle and unit quaternion is utilized to represent head pose. An exponential probability density model based on the rotation matrix (referred to as the matrix Fisher distribution) is developed to model head rotation uncertainty. The matrix Fisher distribution can further analyze the head pose, and its maximum likelihood obtained using singular value decomposition provides enhanced accuracy. Extensive experiments executed over AFLW2000 and BIWI datasets demonstrate that the proposed model achieves state-of-the-art performance in comparison with traditional methods.
Author	Zhang, Zhaoli Fang, Shuai Lin, Ke Liu, Hai Li, Duantengchuan Wang, Jiazhang
Author_xml	– sequence: 1 givenname: Hai orcidid: 0000-0002-6146-5464 surname: Liu fullname: Liu, Hai email: hailiu0204@mail.ccnu.edu.cn organization: National Engineering Research Center for E-Learning, Central China Normal University, Wuhan, China – sequence: 2 givenname: Shuai orcidid: 0000-0002-1132-5391 surname: Fang fullname: Fang, Shuai email: fibreggs@gmail.com organization: National Engineering Laboratory For Educational Big Data, Central China Normal University, Wuhan, China – sequence: 3 givenname: Zhaoli orcidid: 0000-0002-0844-0719 surname: Zhang fullname: Zhang, Zhaoli email: zl.zhang@mail.ccnu.edu.cn organization: National Engineering Research Center for E-Learning, Central China Normal University, Wuhan, China – sequence: 4 givenname: Duantengchuan orcidid: 0000-0003-2902-7365 surname: Li fullname: Li, Duantengchuan email: dtclee1222@gmail.com organization: National Engineering Research Center for E-Learning, Central China Normal University, Wuhan, China – sequence: 5 givenname: Ke orcidid: 0000-0002-3429-5877 surname: Lin fullname: Lin, Ke email: sheldon.chris.lin@gmail.com organization: Control Science and Engineering, Harbin Institute of Technology, Shenzhen, China – sequence: 6 givenname: Jiazhang surname: Wang fullname: Wang, Jiazhang email: jiazhang.wang@u.northwestern.edu organization: Northwestern University, Evanston, IL, USA
BookMark	eNp9kE1PwzAMhiM0JLbBHYlLJM4dTtokDTe0D4bEYBI7U6VtIjKVZiQZgn9P9yEOHDjZlv34td8B6rWu1QhdEhgRAvJmtViMKFAySiEnuUhPUJ_IjCQAQvS6nFFIJCVwhgYhrAFIxkD00etiNnnS8RaPXdOo0nkV7afGSxd0wEvtK72J1rVYtTVeqOjtF57Z8KY9ntjQleV23zbO47lW9R7E0xDtu9o1ztGpUU3QF8c4RC-z6Wo8Tx6f7x_Gd49JRSWJCTdG5oaD0iWnwkBeG57WNQgCJi-5oampWcaUyHJRipIwZiqV1zmrKlPJdIiuD1s33n1sdYjF2m192wkWlHMKkhHCuyk4TFXeheC1KTa-O9N_FwSKnYdF52Gx87A4etgh_A9S2bh_LHplm__AqwNotda_OjJLmUxl-gPQBYDv
CODEN	ITMUF8
CitedBy_id	crossref_primary_10_1016_j_dib_2025_111331 crossref_primary_10_3390_s24248155 crossref_primary_10_1016_j_eswa_2024_124425 crossref_primary_10_1049_ipr2_13142 crossref_primary_10_1007_s00371_023_02781_6 crossref_primary_10_1007_s10489_023_04598_1 crossref_primary_10_1007_s10489_025_06509_y crossref_primary_10_1007_s10115_022_01714_4 crossref_primary_10_1016_j_isci_2025_112155 crossref_primary_10_3390_s23115133 crossref_primary_10_1016_j_compbiomed_2024_108822 crossref_primary_10_1016_j_eswa_2023_119511 crossref_primary_10_1016_j_heliyon_2023_e21361 crossref_primary_10_3390_app13010526 crossref_primary_10_1016_j_infrared_2023_104700 crossref_primary_10_3390_app12083933 crossref_primary_10_1007_s10489_023_04658_6 crossref_primary_10_1016_j_infrared_2022_104146 crossref_primary_10_1007_s10489_023_04734_x crossref_primary_10_1016_j_eswa_2022_118943 crossref_primary_10_1007_s10489_023_04714_1 crossref_primary_10_1016_j_patrec_2024_08_009 crossref_primary_10_1109_TIM_2023_3341142 crossref_primary_10_1007_s10489_023_04454_2 crossref_primary_10_1109_TIP_2023_3331309 crossref_primary_10_1016_j_heliyon_2024_e35938 crossref_primary_10_1007_s10115_022_01740_2 crossref_primary_10_1007_s10489_023_04795_y crossref_primary_10_1002_aisy_202400159 crossref_primary_10_1016_j_heliyon_2023_e16855 crossref_primary_10_3390_s22186759 crossref_primary_10_1007_s10489_022_03320_x crossref_primary_10_3390_s22165932 crossref_primary_10_3390_electronics13040774 crossref_primary_10_3390_s23177626 crossref_primary_10_1016_j_infrared_2022_104099 crossref_primary_10_1016_j_patcog_2024_110263 crossref_primary_10_1109_TMM_2023_3238548 crossref_primary_10_3390_rs15020443 crossref_primary_10_1007_s10489_023_04587_4 crossref_primary_10_1007_s10489_023_04963_0 crossref_primary_10_1016_j_eswa_2024_124659 crossref_primary_10_1109_TIP_2024_3372457 crossref_primary_10_1016_j_ijleo_2022_169986 crossref_primary_10_3390_app12157782 crossref_primary_10_1007_s10489_023_04689_z crossref_primary_10_1007_s10489_023_04695_1 crossref_primary_10_3390_electronics11142114 crossref_primary_10_1364_AO_532544 crossref_primary_10_1371_journal_pone_0284687 crossref_primary_10_1007_s10462_022_10210_8 crossref_primary_10_1016_j_engappai_2024_109070 crossref_primary_10_3390_s23135824 crossref_primary_10_3390_s24082589 crossref_primary_10_1139_tcsme_2024_0167 crossref_primary_10_1016_j_csi_2024_103921 crossref_primary_10_1007_s10489_023_04726_x crossref_primary_10_1109_JSEN_2022_3168863 crossref_primary_10_3390_electronics12102265 crossref_primary_10_1016_j_cviu_2024_103999 crossref_primary_10_1016_j_measurement_2024_115137 crossref_primary_10_1016_j_infrared_2023_104723 crossref_primary_10_1016_j_infrared_2021_104005 crossref_primary_10_1016_j_patcog_2023_110119 crossref_primary_10_1016_j_neucom_2023_01_079 crossref_primary_10_1109_ACCESS_2023_3270285 crossref_primary_10_1016_j_eswa_2023_121929 crossref_primary_10_1016_j_physbeh_2024_114561 crossref_primary_10_1007_s10489_023_04687_1 crossref_primary_10_1016_j_infrared_2023_104719 crossref_primary_10_1016_j_mtcomm_2024_109329 crossref_primary_10_2478_ijanmc_2024_0028 crossref_primary_10_3390_app12115557 crossref_primary_10_1007_s10489_021_03017_7 crossref_primary_10_1007_s10489_021_03150_3 crossref_primary_10_1016_j_displa_2024_102675 crossref_primary_10_3390_s22249835 crossref_primary_10_1016_j_image_2024_117192 crossref_primary_10_1007_s10489_022_03382_x crossref_primary_10_1016_j_neunet_2022_12_021 crossref_primary_10_1007_s10489_022_03848_y crossref_primary_10_32604_cmes_2023_024189 crossref_primary_10_1109_TMM_2022_3233251 crossref_primary_10_1016_j_infrared_2022_104310 crossref_primary_10_1007_s10489_023_04731_0 crossref_primary_10_1016_j_infrared_2023_104850 crossref_primary_10_1007_s10462_024_10936_7 crossref_primary_10_1016_j_ecoinf_2024_102925 crossref_primary_10_3390_math11092024 crossref_primary_10_1016_j_heliyon_2024_e35929 crossref_primary_10_1007_s10489_023_04740_z crossref_primary_10_1007_s10489_023_04633_1 crossref_primary_10_3390_app12073544 crossref_primary_10_1007_s10489_022_03506_3 crossref_primary_10_3390_electronics10131581 crossref_primary_10_1007_s10489_023_04614_4 crossref_primary_10_1016_j_eswa_2024_125799 crossref_primary_10_1007_s10489_022_04093_z crossref_primary_10_1016_j_image_2023_117009 crossref_primary_10_1016_j_infrared_2022_104348 crossref_primary_10_1109_ACCESS_2024_3487414 crossref_primary_10_1007_s10489_023_05140_z crossref_primary_10_1007_s00500_025_10692_y crossref_primary_10_1109_THMS_2024_3351138 crossref_primary_10_3390_app13052922 crossref_primary_10_1007_s10489_024_05343_y crossref_primary_10_1016_j_neucom_2024_129033 crossref_primary_10_1109_TIP_2024_3378180 crossref_primary_10_1016_j_heliyon_2024_e36823 crossref_primary_10_1007_s44443_025_00034_1 crossref_primary_10_3390_electronics11203403 crossref_primary_10_1007_s10489_023_04548_x crossref_primary_10_1007_s10489_023_04870_4 crossref_primary_10_1007_s10489_021_02967_2 crossref_primary_10_1016_j_neucom_2025_130490 crossref_primary_10_1016_j_infrared_2022_104297 crossref_primary_10_1016_j_patcog_2025_111536 crossref_primary_10_1109_JSEN_2021_3122258 crossref_primary_10_1007_s10489_023_04589_2 crossref_primary_10_1109_TII_2021_3123546 crossref_primary_10_1016_j_infrared_2022_104457 crossref_primary_10_1007_s10489_023_04750_x crossref_primary_10_1007_s10489_022_03781_0 crossref_primary_10_1007_s11633_023_1438_4 crossref_primary_10_1016_j_measurement_2024_114939 crossref_primary_10_1007_s10489_022_03431_5 crossref_primary_10_3390_bdcc7010037 crossref_primary_10_1016_j_asoc_2024_112011 crossref_primary_10_1109_LGRS_2022_3167401 crossref_primary_10_3390_s22134663 crossref_primary_10_1016_j_tafmec_2025_105197 crossref_primary_10_3390_en17020349 crossref_primary_10_1016_j_asoc_2024_112125 crossref_primary_10_3390_electronics11142278 crossref_primary_10_3390_app12115424 crossref_primary_10_3390_s23052613 crossref_primary_10_1016_j_cja_2023_12_028 crossref_primary_10_1016_j_neucom_2023_126270 crossref_primary_10_1007_s10489_023_05076_4 crossref_primary_10_1016_j_infrared_2023_104909 crossref_primary_10_3390_app13116422 crossref_primary_10_3390_electronics12051194 crossref_primary_10_1016_j_infrared_2022_104482 crossref_primary_10_1016_j_ipm_2024_103831 crossref_primary_10_3389_fneur_2025_1596408 crossref_primary_10_3390_app12189060 crossref_primary_10_3390_s22082929 crossref_primary_10_1016_j_ecoinf_2024_102794 crossref_primary_10_1016_j_image_2022_116895 crossref_primary_10_1007_s10489_023_04760_9 crossref_primary_10_1007_s10489_022_03623_z crossref_primary_10_1007_s10489_023_04952_3 crossref_primary_10_1007_s10489_022_03958_7 crossref_primary_10_1007_s10489_023_04499_3 crossref_primary_10_1016_j_asoc_2024_112119 crossref_primary_10_1109_LSP_2021_3138351 crossref_primary_10_1007_s13748_024_00329_w crossref_primary_10_1007_s00500_021_06622_3 crossref_primary_10_1016_j_agwat_2024_108901 crossref_primary_10_1007_s10489_022_03931_4 crossref_primary_10_1007_s10489_024_05516_9 crossref_primary_10_1007_s10489_023_05023_3 crossref_primary_10_3390_signals5040040 crossref_primary_10_1109_LGRS_2023_3274225 crossref_primary_10_1016_j_infrared_2022_104230 crossref_primary_10_1007_s10489_022_03530_3 crossref_primary_10_3390_s22197123 crossref_primary_10_1007_s10489_022_03497_1 crossref_primary_10_1109_ACCESS_2025_3561506 crossref_primary_10_3390_electronics12061360 crossref_primary_10_1007_s10489_022_03924_3 crossref_primary_10_1007_s13042_023_01933_3 crossref_primary_10_3390_sci5010010 crossref_primary_10_1016_j_ijleo_2023_170892 crossref_primary_10_1016_j_neucom_2022_07_051 crossref_primary_10_1016_j_neucom_2025_130623 crossref_primary_10_3390_s24113342 crossref_primary_10_1080_10494820_2023_2205898 crossref_primary_10_3390_e24070974 crossref_primary_10_3390_electronics13234629
Cites_doi	10.3390/sym11091066 10.1007/978-3-030-01240-3_33 10.1007/978-3-319-24261-3_7 10.1093/biomet/59.3.665 10.1109/CVPR.2018.00045 10.1109/CVPR.2017.167 10.1109/CVPR.2009.5206848 10.1016/j.imavis.2019.11.005 10.1109/ICCV.2015.416 10.1109/CVPR.2016.23 10.1109/CVPR.2019.00118 10.1002/SERIES1345 10.1016/j.patcog.2020.107316 10.1109/ICCVW.2011.6130513 10.1109/IROS.2004.1389771 10.1109/FG.2017.149 10.1109/CVPR.2013.446 10.1609/aaai.v34i07.6974 10.1007/978-3-030-01261-8_44 10.1109/CVPR.2015.7298682 10.1109/CVPR.2005.202 10.1109/TAC.2018.2797162 10.1109/TMM.2010.2051874 10.1007/978-3-642-23123-0_11 10.1016/j.neucom.2020.05.010 10.1111/j.2517-6161.1977.tb01610.x 10.1007/s11263-012-0549-0 10.1109/TMM.2015.2482819 10.1109/TMM.2017.2771396 10.1109/ROBOT.2009.5152855 10.1109/CVPR.2019.00589 10.23919/ACC45564.2020.9147703 10.1109/CVPRW.2018.00281 10.1007/978-0-387-21540-2 10.1561/0600000001 10.1109/TPAMI.2020.2983935 10.1109/TPAMI.2017.2781233 10.1109/TPAMI.2021.3054824 10.1109/ICCV.2017.74 10.1109/ICCVW.2013.59 10.1109/TMM.2018.2866770 10.1109/CVPR.2014.241 10.1109/CVPR.2006.100 10.1109/LSP.2016.2603342 10.1109/CVPR42600.2020.01367 10.1109/ICCV.2019.00380
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022
DBID	97E RIA RIE AAYXX CITATION 7SC 7SP 8FD JQ2 L7M L~C L~D
DOI	10.1109/TMM.2021.3081873
DatabaseName	IEEE Xplore (IEEE) IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef Computer and Information Systems Abstracts Electronics & Communications Abstracts Technology Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional
DatabaseTitle	CrossRef Technology Research Database Computer and Information Systems Abstracts – Academic Electronics & Communications Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Professional
DatabaseTitleList	Technology Research Database
Database_xml	– sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering Computer Science
EISSN	1941-0077
EndPage	2460
ExternalDocumentID	10_1109_TMM_2021_3081873 9435939
Genre	orig-research
GrantInformation_xml	– fundername: National Natural Science Foundation of China grantid: 62011530436; 62077020; 62005092; 61875068 funderid: 10.13039/501100001809 – fundername: Fundamental Research Funds for the Central Universities grantid: CCNU20ZT017; CCNU2020ZN008 funderid: 10.13039/501100012226
GroupedDBID	-~X 0R~ 29I 4.4 5GY 5VS 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFO ACGFS ACIWK AENEX AETIX AGQYO AGSQL AHBIQ AI. AIBXA AKJIK AKQYR ALLEH ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS EJD HZ~ H~9 IFIPE IFJZH IPLJI JAVBF LAI M43 O9- OCL P2P PQQKQ RIA RIE RNS TN5 VH1 ZY4 AAYXX CITATION 7SC 7SP 8FD JQ2 L7M L~C L~D
ID	FETCH-LOGICAL-c291t-6ff98f60aeb627f08df63dd0710f8b6f23fd545a7487b7b155fca8d85ccfc93
IEDL.DBID	RIE
ISICitedReferencesCount	165
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000793839600017&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1520-9210
IngestDate	Sun Nov 09 08:28:36 EST 2025 Tue Nov 18 21:39:56 EST 2025 Sat Nov 29 03:10:07 EST 2025 Wed Aug 27 02:37:58 EDT 2025
IsPeerReviewed	true
IsScholarly	true
Language	English
License	https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html https://doi.org/10.15223/policy-029 https://doi.org/10.15223/policy-037
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c291t-6ff98f60aeb627f08df63dd0710f8b6f23fd545a7487b7b155fca8d85ccfc93
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0002-0844-0719 0000-0002-6146-5464 0000-0002-1132-5391 0000-0003-2902-7365 0000-0002-3429-5877
PQID	2662095116
PQPubID	75737
PageCount	12
ParticipantIDs	crossref_citationtrail_10_1109_TMM_2021_3081873 crossref_primary_10_1109_TMM_2021_3081873 proquest_journals_2662095116 ieee_primary_9435939
PublicationCentury	2000
PublicationDate	20220000 2022-00-00 20220101
PublicationDateYYYYMMDD	2022-01-01
PublicationDate_xml	– year: 2022 text: 20220000
PublicationDecade	2020
PublicationPlace	Piscataway
PublicationPlace_xml	– name: Piscataway
PublicationTitle	IEEE transactions on multimedia
PublicationTitleAbbrev	TMM
PublicationYear	2022
Publisher	IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml	– name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References	ref13 ref12 ref15 ref52 ref11 ref10 Chikuse (ref14) 2003 ref17 ref16 ref19 ref18 Tan (ref43) 2019 Bulat (ref5) 2017 ref50 ref46 ref45 ref48 ref47 ref42 ref44 ref8 ref7 ref9 ref4 ref3 ref6 ref40 ref35 ref34 ref37 ref36 ref31 ref30 Ying (ref51) 2019 ref33 ref32 ref2 ref1 Martinez (ref49) 2014 ref39 ref24 ref23 ref26 ref25 ref20 ref22 ref21 Hermans (ref38) 2017 ref28 ref27 ref29 Mohlin (ref41) 2020
References_xml	– ident: ref31 doi: 10.3390/sym11091066 – ident: ref39 doi: 10.1007/978-3-030-01240-3_33 – ident: ref36 doi: 10.1007/978-3-319-24261-3_7 – ident: ref15 doi: 10.1093/biomet/59.3.665 – ident: ref18 doi: 10.1109/CVPR.2018.00045 – ident: ref30 doi: 10.1109/CVPR.2017.167 – ident: ref48 doi: 10.1109/CVPR.2009.5206848 – ident: ref24 doi: 10.1016/j.imavis.2019.11.005 – ident: ref29 doi: 10.1109/ICCV.2015.416 – ident: ref23 doi: 10.1109/CVPR.2016.23 – ident: ref8 doi: 10.1109/CVPR.2019.00118 – ident: ref13 doi: 10.1002/SERIES1345 – ident: ref20 doi: 10.1016/j.patcog.2020.107316 – ident: ref46 doi: 10.1109/ICCVW.2011.6130513 – ident: ref3 doi: 10.1109/IROS.2004.1389771 – ident: ref21 doi: 10.1109/FG.2017.149 – ident: ref17 doi: 10.1109/CVPR.2013.446 – ident: ref26 doi: 10.1609/aaai.v34i07.6974 – ident: ref2 doi: 10.1007/978-3-030-01261-8_44 – ident: ref32 doi: 10.1109/CVPR.2015.7298682 – ident: ref35 doi: 10.1109/CVPR.2005.202 – ident: ref40 doi: 10.1109/TAC.2018.2797162 – ident: ref1 doi: 10.1109/TMM.2010.2051874 – ident: ref27 doi: 10.1007/978-3-642-23123-0_11 – start-page: 7105 volume-title: Proc. Int. Conf. Mach. Learn. year: 2019 ident: ref51 article-title: Nas-bench-101: Towards reproducible neural architecture search – ident: ref25 doi: 10.1016/j.neucom.2020.05.010 – ident: ref16 doi: 10.1111/j.2517-6161.1977.tb01610.x – ident: ref45 doi: 10.1007/s11263-012-0549-0 – ident: ref28 doi: 10.1109/TMM.2015.2482819 – ident: ref4 doi: 10.1109/TMM.2017.2771396 – ident: ref12 doi: 10.1109/ROBOT.2009.5152855 – ident: ref11 doi: 10.1109/CVPR.2019.00589 – ident: ref42 doi: 10.23919/ACC45564.2020.9147703 – start-page: 1021 volume-title: Proc. Int. Conf. Comput. Vis. year: 2017 ident: ref5 – year: 2017 ident: ref38 article-title: In defense of the triplet loss for person re-identification – ident: ref7 doi: 10.1109/CVPRW.2018.00281 – volume-title: Statistics on Special Manifolds year: 2003 ident: ref14 doi: 10.1007/978-0-387-21540-2 – ident: ref10 doi: 10.1561/0600000001 – ident: ref19 doi: 10.1109/TPAMI.2020.2983935 – ident: ref22 doi: 10.1109/TPAMI.2017.2781233 – ident: ref52 doi: 10.1109/TPAMI.2021.3054824 – ident: ref50 doi: 10.1109/ICCV.2017.74 – ident: ref44 doi: 10.1109/ICCVW.2013.59 – ident: ref9 doi: 10.1109/TMM.2018.2866770 – start-page: 641 volume-title: Proc. Int. Conf. 3D Vis. year: 2014 ident: ref49 article-title: Real time head model creation and head pose estimation on consumer depth cameras – start-page: 4884 volume-title: Neural Inf. Process. Syst. year: 2020 ident: ref41 article-title: Probabilistic orientation estimation with matrix fisher distributions – ident: ref6 doi: 10.1109/CVPR.2014.241 – start-page: 6105 volume-title: Proc. Int. Conf. Mach. Learn. year: 2019 ident: ref43 article-title: Rethinking model scaling for convolutional neural networks – ident: ref37 doi: 10.1109/CVPR.2006.100 – ident: ref47 doi: 10.1109/LSP.2016.2603342 – ident: ref33 doi: 10.1109/CVPR42600.2020.01367 – ident: ref34 doi: 10.1109/ICCV.2019.00380
SSID	ssj0014507
Score	2.674637
Snippet	Head pose estimation suffers from several problems, including low pose tolerance under different disturbances and ambiguity arising from common head pose...
SourceID	proquest crossref ieee
SourceType	Aggregation Database Enrichment Source Index Database Publisher
StartPage	2449
SubjectTerms	Euler angles Feature extraction Head Head movement Head pose estimation Matrix Fisher distribution Measurement Metric learning Modules Pose estimation Quaternions Robustness Rotation matrix Singular value decomposition Solid modeling Three-dimensional displays Triplet loss Uncertainty
Title	MFDNet: Collaborative Poses Perception and Matrix Fisher Distribution for Head Pose Estimation
URI	https://ieeexplore.ieee.org/document/9435939 https://www.proquest.com/docview/2662095116
Volume	24
WOSCitedRecordID	wos000793839600017&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
journalDatabaseRights	– providerCode: PRVIEE databaseName: IEEE Electronic Library (IEL) customDbUrl: eissn: 1941-0077 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0014507 issn: 1520-9210 databaseCode: RIE dateStart: 19990101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEB6seNCD9Yn1RQ5eBLdN95FsvIm2eLClYA89uWTzAEFaabfiz3eS3a6KInjbQ5Jd9ksy32Qy3wBcSIscROkwoHmsg7grdZDHKQ2QKvBYMYXLy-vMPvDhMJ1MxGgNrupcGGOMv3xm2u7Rx_L1TC3dUVlHoG0XkWhAg3NW5mrVEYM48anRaI7wRejHrEKSVHTGgwE6gmG3HTn9Nh59M0G-psqPjdhbl37zf9-1A9sViyQ3Jey7sGame9BcVWgg1YLdg60vcoP78DTo3w1NcU1uP8F_M2Q0W5gFGdU3XIicajJw0v3vpKyMTu6cvG5VGYsgzSX3ODV8R9LDPaJMfzyAx35vfHsfVPUVAhWKbhEwa0VqGZUmZyG3NNWWRVo70mHTnNkwshoJluTo1OQ8R-ZhlUx1mihllYgOYX06m5ojICYRSWwpS3G8mEU0Z0JyyRIpcxpJzlvQWf3wTFXS464CxkvmXRAqMoQocxBlFUQtuKx7vJayG3-03XeQ1O0qNFpwusI0q9blIkM6EjpS2WXHv_c6gc3QJTj4Q5ZTWC_mS3MGG-qteF7Mz_2U-wCza9OI
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LT-MwEB7xWAk4AAuLKE8fuCBtqJs4dswNAVURTVWJHjht5PghrYRaRAvi5zN20sBqERK3HGwnymd7vvF4vgE4UQ45iDZxREtmItZRJipZRiOkCoJprnF5BZ3ZvhgMsvt7OVyA300ujLU2XD6zZ_4xxPLNRD_7o7K2RNsuE7kIyyljMa2ytZqYAUtDcjQaJHwVejLzoCSV7VGeoysYd84Sr-Amkn-MUKiq8t9WHOxLd-N7X7YJ6zWPJBcV8D9hwY63YGNeo4HUS3YL1j4IDm7Dn7x7NbCzc3L5Dv-LJcPJ1E7JsLnjQtTYkNyL97-SqjY6ufICu3VtLIJEl_RwcoSO5Bp3iSoB8hfcda9Hl72orrAQ6Vh2ZhF3TmaOU2VLHgtHM-N4YoynHS4ruYsTZ5BiKYFuTSlK5B5Oq8xkqdZOy2QHlsaTsd0FYlOZMkd5huMxntCSSyUUT5UqaaKEaEF7_sMLXYuP-xoYD0VwQqgsEKLCQ1TUELXgtOnxWAlvfNF220PStKvRaMHBHNOiXpnTAglJ7Gllh-993usYVnqjvF_0bwa3-7Aa-3SHcORyAEuzp2d7CD_0y-zv9OkoTL833CvWzw
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=article&rft.atitle=MFDNet%3A+Collaborative+Poses+Perception+and+Matrix+Fisher+Distribution+for+Head+Pose+Estimation&rft.jtitle=IEEE+transactions+on+multimedia&rft.au=Liu%2C+Hai&rft.au=Fang%2C+Shuai&rft.au=Zhang%2C+Zhaoli&rft.au=Li%2C+Duantengchuan&rft.date=2022&rft.issn=1520-9210&rft.eissn=1941-0077&rft.volume=24&rft.spage=2449&rft.epage=2460&rft_id=info:doi/10.1109%2FTMM.2021.3081873&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TMM_2021_3081873
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1520-9210&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1520-9210&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1520-9210&client=summon