Hierarchical attributes learning for pedestrian re-identification via parallel stochastic gradient descent combined with momentum correction and adaptive learning rate
Convolutional neural networks (CNNs) have obtained high accuracy results for pedestrian re-identification in the past few years. There is always a trade-off between high accuracy and computational time in CNNs. Training CNN is always very difficult as it may take a long time to produce high accuracy...
Gespeichert in:
| Veröffentlicht in: | Neural computing & applications Jg. 32; H. 10; S. 5695 - 5712 |
|---|---|
| Hauptverfasser: | , , , , |
| Format: | Journal Article |
| Sprache: | Englisch |
| Veröffentlicht: |
London
Springer London
01.05.2020
Springer Nature B.V |
| Schlagworte: | |
| ISSN: | 0941-0643, 1433-3058 |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| Abstract | Convolutional neural networks (CNNs) have obtained high accuracy results for pedestrian re-identification in the past few years. There is always a trade-off between high accuracy and computational time in CNNs. Training CNN is always very difficult as it may take a long time to produce high accuracy results. To overcome this limitation, a novel method parallel stochastic gradient descent (PSGD) is proposed to train a five-hierarchical parallel CNNs that is designed according to pedestrian attributes. Moreover, the momentum correction and adaptive adjustment of learning rate are applied during training process and the time interval for updating parameters is inspected during optimization of parameters selection. The results of this paper prove the effectiveness of proposed PSGD that successfully decreases the training process by five times and surpasses the state-of-the-art methods of pedestrian re-identification in terms of both accuracy and time. The minimum reported running time of the proposed method is 8.7 s which is minimum among all other state-of-the-art methods. These promising results show the efficiency and performance of the proposed model. |
|---|---|
| AbstractList | Convolutional neural networks (CNNs) have obtained high accuracy results for pedestrian re-identification in the past few years. There is always a trade-off between high accuracy and computational time in CNNs. Training CNN is always very difficult as it may take a long time to produce high accuracy results. To overcome this limitation, a novel method parallel stochastic gradient descent (PSGD) is proposed to train a five-hierarchical parallel CNNs that is designed according to pedestrian attributes. Moreover, the momentum correction and adaptive adjustment of learning rate are applied during training process and the time interval for updating parameters is inspected during optimization of parameters selection. The results of this paper prove the effectiveness of proposed PSGD that successfully decreases the training process by five times and surpasses the state-of-the-art methods of pedestrian re-identification in terms of both accuracy and time. The minimum reported running time of the proposed method is 8.7 s which is minimum among all other state-of-the-art methods. These promising results show the efficiency and performance of the proposed model. |
| Author | Tao, Fei Zhan, Yongzhao Li, Maozhen Li, Kenli Cheng, Keyang |
| Author_xml | – sequence: 1 givenname: Keyang orcidid: 0000-0001-5240-1605 surname: Cheng fullname: Cheng, Keyang email: kycheng@ujs.edu.cn organization: School of Computer Science and Communication Engineering, Jiangsu University, National Engineering Laboratory for Public Safety Risk Perception and Control by Big Data – sequence: 2 givenname: Fei surname: Tao fullname: Tao, Fei organization: School of Computer Science and Communication Engineering, Jiangsu University – sequence: 3 givenname: Yongzhao surname: Zhan fullname: Zhan, Yongzhao organization: School of Computer Science and Communication Engineering, Jiangsu University – sequence: 4 givenname: Maozhen surname: Li fullname: Li, Maozhen organization: Department of Electronic and Computer Engineering, Brunel University, The Key Laboratory of Embedded Systems and Service Computing, Tongji University – sequence: 5 givenname: Kenli surname: Li fullname: Li, Kenli organization: College of Information Science and Engineering, Hunan University |
| BookMark | eNp9kctqHDEQRYWxIWPHP5CVIOtO9OxRL4NJ4oAhm2Qt1FL1jEy31C5pHPJF-c1oZgKGLLwqqLqnXveaXKacgJB3nH3gjG0_Fsa04B3jQ8eUMroTF2TDlZSdZNpckg0bVCv3Sr4h16U8MsZUb_SG_LmPgA79Pno3U1crxvFQodAZHKaYdnTKSFcIUFrJJYrQxQCpxqkRNeZEn6Ojq0M3zzDTUrPfu1Kjpzt0ITYlbaw_Rp-XMSYI9Fese7rkpSUPS0sjgj-1cilQF9xa4zO8bICuwltyNbm5wO2_eEN-fvn84-6-e_j-9dvdp4fOSz7Ubhz70WhQZpIquCH4drdSWgkFwoPQ0AfgW2PC1EMYjA7bwYhe6K0SQo-DkDfk_bnvivnp0I62j_mAqY20QhitOJNaNpU5qzzmUhAm62M9faOii7PlzB5tsWdbbLPFnmyxxwHiP3TFuDj8_Tokz1Bp4rQDfNnqFeov3FKmXw |
| CitedBy_id | crossref_primary_10_3233_JIFS_189834 crossref_primary_10_1109_JIOT_2021_3065368 crossref_primary_10_1007_s00521_022_07300_7 crossref_primary_10_3390_buildings13010027 crossref_primary_10_1109_TII_2021_3064358 crossref_primary_10_1016_j_cag_2023_10_016 crossref_primary_10_32604_cmes_2023_025119 crossref_primary_10_1155_2022_7835241 crossref_primary_10_1371_journal_pone_0256836 crossref_primary_10_1016_j_jksuci_2023_101558 crossref_primary_10_1016_j_neunet_2021_10_021 crossref_primary_10_1002_cpe_70029 crossref_primary_10_1007_s00500_023_08061_8 crossref_primary_10_1080_10739149_2025_2529308 crossref_primary_10_3233_JIFS_189345 crossref_primary_10_1007_s00521_021_05951_6 crossref_primary_10_3390_jmse11091807 |
| Cites_doi | 10.1109/ICCVW.2017.318 10.1109/TPDS.2014.2308221 10.1007/s00521-018-3922-2 10.1007/978-3-319-46475-6_30 10.1007/s10619-014-7156-8 10.1007/978-3-319-27674-8_24 10.1007/978-3-642-41822-8_38 10.1016/j.neunet.2017.06.003 10.1016/j.jfranklin.2017.09.003 10.1109/CVPRW.2017.129 10.1109/CVPR.2017.195 10.1109/CVPRW.2010.5543255 10.1109/IJCNN.2017.7966082 10.1109/CVPR.2010.5539926 10.1109/CVPR.2015.7298594 10.1016/j.patrec.2016.09.015 10.5244/C.26.24 10.1109/ICIP.2016.7533166 10.1109/TII.2019.2909473 10.1016/j.neucom.2013.12.017 10.1109/CVPR.2018.00709 10.1109/CVPR.2011.5995719 10.1109/CVPR.2013.461 10.1186/s40064-016-1931-0 10.1080/10543406.2014.941987 10.1016/j.neucom.2014.05.011 10.1007/s00521-017-3164-8 10.1109/TPDS.2018.2877359 10.1109/ICASSP.2017.7952446 10.1007/978-1-4471-6296-4_5 10.1109/NCVPRIPG.2013.6776234 10.1109/TC.2013.205 10.1109/ROMA.2016.7847818 10.1007/978-3-319-48881-3_2 10.1109/ICME.2018.8486604 10.1007/s00521-017-3167-5 10.1109/BigData.2015.7364091 10.5220/0006622901140122 10.1145/2897937.2897995 10.1109/ICCV.2015.314 10.1007/s00521-018-3809-2 10.3390/app9102027 10.1007/978-1-4471-6296-4_12 10.1046/j.1365-2958.1996.00063.x 10.1109/CVPR.2013.460 10.1109/DICTA.2016.7797032 10.1109/ICIP.2015.7351743 |
| ContentType | Journal Article |
| Copyright | Springer-Verlag London Ltd., part of Springer Nature 2019 Springer-Verlag London Ltd., part of Springer Nature 2019. |
| Copyright_xml | – notice: Springer-Verlag London Ltd., part of Springer Nature 2019 – notice: Springer-Verlag London Ltd., part of Springer Nature 2019. |
| DBID | AAYXX CITATION 8FE 8FG AFKRA ARAPS BENPR BGLVJ CCPQU DWQXO HCIFZ P5Z P62 PHGZM PHGZT PKEHL PQEST PQGLB PQQKQ PQUKI PRINS |
| DOI | 10.1007/s00521-019-04485-2 |
| DatabaseName | CrossRef ProQuest SciTech Collection ProQuest Technology Collection ProQuest Central UK/Ireland Advanced Technologies & Computer Science Collection ProQuest Central Technology Collection ProQuest One ProQuest Central Korea SciTech Collection (ProQuest) Advanced Technologies & Aerospace Database ProQuest Advanced Technologies & Aerospace Collection ProQuest Central Premium ProQuest One Academic (New) ProQuest One Academic Middle East (New) ProQuest One Academic Eastern Edition (DO NOT USE) One Applied & Life Sciences ProQuest One Academic (retired) ProQuest One Academic UKI Edition ProQuest Central China |
| DatabaseTitle | CrossRef Advanced Technologies & Aerospace Collection Technology Collection ProQuest One Academic Middle East (New) ProQuest Advanced Technologies & Aerospace Collection ProQuest One Academic Eastern Edition SciTech Premium Collection ProQuest One Community College ProQuest Technology Collection ProQuest SciTech Collection ProQuest Central China ProQuest Central Advanced Technologies & Aerospace Database ProQuest One Applied & Life Sciences ProQuest One Academic UKI Edition ProQuest Central Korea ProQuest Central (New) ProQuest One Academic ProQuest One Academic (New) |
| DatabaseTitleList | Advanced Technologies & Aerospace Collection |
| Database_xml | – sequence: 1 dbid: P5Z name: Advanced Technologies & Aerospace Database url: https://search.proquest.com/hightechjournals sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Computer Science |
| EISSN | 1433-3058 |
| EndPage | 5712 |
| ExternalDocumentID | 10_1007_s00521_019_04485_2 |
| GrantInformation_xml | – fundername: Young Scientists Fund grantid: 61602215 funderid: http://dx.doi.org/10.13039/501100010909 – fundername: National Engineering Laboratory Director Foundation of Big Data Application for Social Security Risk Perception and Prevention grantid: 2018 – fundername: Major Research Plan grantid: 61672268; 61972183 funderid: http://dx.doi.org/10.13039/501100010905 |
| GroupedDBID | -4Z -59 -5G -BR -EM -Y2 -~C .4S .86 .DC .VR 06D 0R~ 0VY 123 1N0 1SB 2.D 203 28- 29N 2J2 2JN 2JY 2KG 2LR 2P1 2VQ 2~H 30V 4.4 406 408 409 40D 40E 53G 5QI 5VS 67Z 6NX 8FE 8FG 8TC 8UJ 95- 95. 95~ 96X AAAVM AABHQ AACDK AAHNG AAIAL AAJBT AAJKR AANZL AAOBN AARHV AARTL AASML AATNV AATVU AAUYE AAWCG AAYIU AAYQN AAYTO AAYZH ABAKF ABBBX ABBXA ABDBF ABDZT ABECU ABFTD ABFTV ABHLI ABHQN ABJNI ABJOX ABKCH ABKTR ABLJU ABMNI ABMQK ABNWP ABQBU ABQSL ABSXP ABTEG ABTHY ABTKH ABTMW ABULA ABWNU ABXPI ACAOD ACBXY ACDTI ACGFS ACHSB ACHXU ACKNC ACMDZ ACMLO ACOKC ACOMO ACPIV ACSNA ACUHS ACZOJ ADHHG ADHIR ADIMF ADINQ ADKNI ADKPE ADMLS ADRFC ADTPH ADURQ ADYFF ADZKW AEBTG AEFIE AEFQL AEGAL AEGNC AEJHL AEJRE AEKMD AEMSY AENEX AEOHA AEPYU AESKC AETLH AEVLU AEXYK AFBBN AFEXP AFGCZ AFKRA AFLOW AFQWF AFWTZ AFZKB AGAYW AGDGC AGGDS AGJBK AGMZJ AGQEE AGQMX AGRTI AGWIL AGWZB AGYKE AHAVH AHBYD AHKAY AHSBF AHYZX AIAKS AIGIU AIIXL AILAN AITGF AJBLW AJRNO AJZVZ ALMA_UNASSIGNED_HOLDINGS ALWAN AMKLP AMXSW AMYLF AMYQR AOCGG ARAPS ARCSS ARMRJ ASPBG AVWKF AXYYD AYJHY AZFZN B-. B0M BA0 BBWZM BDATZ BENPR BGLVJ BGNMA BSONS CAG CCPQU COF CS3 CSCUP DDRTE DL5 DNIVK DPUIP DU5 EAD EAP EBLON EBS ECS EDO EIOEI EJD EMI EMK EPL ESBYG EST ESX F5P FEDTE FERAY FFXSO FIGPU FINBP FNLPD FRRFC FSGXE FWDCC GGCAI GGRSB GJIRD GNWQR GQ6 GQ7 GQ8 GXS H13 HCIFZ HF~ HG5 HG6 HMJXF HQYDN HRMNR HVGLF HZ~ I-F I09 IHE IJ- IKXTQ ITM IWAJR IXC IZIGR IZQ I~X I~Z J-C J0Z JBSCW JCJTX JZLTJ KDC KOV KOW LAS LLZTM M4Y MA- N2Q N9A NB0 NDZJH NPVJJ NQJWS NU0 O9- O93 O9G O9I O9J OAM P19 P2P P62 P9O PF0 PT4 PT5 QOK QOS R4E R89 R9I RHV RIG RNI RNS ROL RPX RSV RZK S16 S1Z S26 S27 S28 S3B SAP SCJ SCLPG SCO SDH SDM SHX SISQX SJYHP SNE SNPRN SNX SOHCF SOJ SPISZ SRMVM SSLCW STPWE SZN T13 T16 TSG TSK TSV TUC TUS U2A UG4 UOJIU UTJUX UZXMN VC2 VFIZW W23 W48 WK8 YLTOR Z45 Z5O Z7R Z7S Z7V Z7W Z7X Z7Y Z7Z Z81 Z83 Z86 Z88 Z8M Z8N Z8P Z8Q Z8R Z8S Z8T Z8U Z8W Z92 ZMTXR ~8M ~EX AAPKM AAYXX ABBRH ABDBE ABFSG ABRTQ ACSTC ADHKG ADKFA AEZWR AFDZB AFFHD AFHIU AFOHR AGQPQ AHPBZ AHWEU AIXLP ATHPR AYFIA CITATION PHGZM PHGZT PQGLB DWQXO PKEHL PQEST PQQKQ PQUKI PRINS |
| ID | FETCH-LOGICAL-c319t-bb6b85e48f34da9dc094445424e2ce25e6de1788df6ed985d798262574225b923 |
| IEDL.DBID | RSV |
| ISICitedReferencesCount | 17 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000529745200032&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0941-0643 |
| IngestDate | Tue Nov 04 22:07:32 EST 2025 Sat Nov 29 02:59:13 EST 2025 Tue Nov 18 22:15:19 EST 2025 Fri Feb 21 02:35:55 EST 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 10 |
| Keywords | Pedestrian attributes CNN Parameter exchanging Parallel SGD Pedestrian re-identification |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c319t-bb6b85e48f34da9dc094445424e2ce25e6de1788df6ed985d798262574225b923 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 |
| ORCID | 0000-0001-5240-1605 |
| PQID | 2285410353 |
| PQPubID | 2043988 |
| PageCount | 18 |
| ParticipantIDs | proquest_journals_2285410353 crossref_citationtrail_10_1007_s00521_019_04485_2 crossref_primary_10_1007_s00521_019_04485_2 springer_journals_10_1007_s00521_019_04485_2 |
| PublicationCentury | 2000 |
| PublicationDate | 20200500 2020-05-00 20200501 |
| PublicationDateYYYYMMDD | 2020-05-01 |
| PublicationDate_xml | – month: 5 year: 2020 text: 20200500 |
| PublicationDecade | 2020 |
| PublicationPlace | London |
| PublicationPlace_xml | – name: London – name: Heidelberg |
| PublicationTitle | Neural computing & applications |
| PublicationTitleAbbrev | Neural Comput & Applic |
| PublicationYear | 2020 |
| Publisher | Springer London Springer Nature B.V |
| Publisher_xml | – name: Springer London – name: Springer Nature B.V |
| References | Li Y, Tong G, Li X, Wang Y, Zou B, Liu Y (2019) PARNet: a joint loss function and dynamic weights network for pedestrian semantic attributes recognition of smart surveillance image. In: Multidisciplinary digital publishing institute, applied sciences, p 2027 MwakalongeJLSiuhiSWhiteJDistracted walking: examining the extent to pedestrian safety problemsJ Traffic Transp Eng201525327337 Dass J, Sharma M, Hassan E, Ghosh H (2013) A density based method for automatic hairstyle discovery and recognition. In: Proceedings of the national conference on computer vision, pattern recognition, image processing and graphics, pp 1–4 Guo J, Gould S (2016) Depth dropout: efficient training of residual convolutional neural networks. In: Proceedings of the international conference on digital image computing: techniques and applications, pp 1–7 Botev A, Lever G, Barber D (2016) Nesterov’s accelerated gradient and momentum as approximations to regularised update descent In: Proceedings of the international joint conference on neural network, pp 1899–1903 Farenzena M, Bazzani L, Perina A, Murino V, Cristani M (2010) Person re-identification by symmetry-driven accumulation of local features. In: Computer vision and pattern recognition, pp 2360–2367 Flores A, Belongie SJ (2010) Removing pedestrians from google street view images. In: Computer vision and pattern recognition, pp 53–58 Song L, Wang Y, Han Y, Zhao X, Liu B, Li X (2016) C-brain: a deep learning accelerator that tames the diversity of cnns through adaptive data-level parallelization. In: Proceedings of the design automation conference, p 123 Huanzhou Z, Zhuoer G, Haiming Z, Keyang C, Chang-Tsun L, Ligang H (2018) Developing a pattern discovery method in time series data and its GPU acceleration. In: TUP, Big data mining and analytics, pp 266–283 Gray D, Brennan S, Tao H (2007) Evaluating appearance models for recognition, reacquisition, and tracking. In: Proceedings of the IEEE international workshop on performance evaluation for tracking and surveillance, vol 3(5), pp 501–512 Umeda T, Sun Y, Irie G, Sudo K, Kinebuchi T (2016) Attribute discovery for person re-identification. In: International conference on multimedia modeling. Springer, New York, pp 268–276 Zhang J, Wang N, Zhang L (2018) Multi-shot pedestrian re-identification via sequential decision making. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 6781–6789 LatifiAFoglinoMTanakaKWilliamsPLazdunskiAA hierarchical quorum-sensing cascade in pseudomonas aeruginosa links the transcriptional activators lasr and rhir (vsmr) to expression of the stationary-phase sigma factor rposMol Microbiol19962161137114610.1046/j.1365-2958.1996.00063.x Szegedy C, Liu W, Jia Y, Sermanet P, Reed SE, Anguelov D, Rabinovich A (2015) Going deeper with convolutions In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1–9 Layne R, Hospedales TM, Gong S (2014) Attributes-based re-identification. Springer, London (Person Re-Identification) ChengKXuFTaoFQiMLiMData-driven pedestrian re-identification based on hierarchical semantic representationConcurr Comput Pract Exp20179e4403 Jung H, Choi MK, Jung J, Lee JH, Kwon S, Jung WY (2017) Resnet-based vehicle classification and localization in traffic surveillance systems. In: Proceedings of the IEEE conference on computer vision and pattern recognition workshops, pp 934–940 ChatzipavlisATsekourasGETrygonisVVelegrakisAFTsimikasJRigosASalmasCModeling beach realignment using a neuro-fuzzy network optimized by a novel backtracking search algorithmNeural Comput Appl2019311747176310.1007/s00521-018-3809-2 LiKYangWLiKPerformance analysis and optimization for SpMV on GPU using probabilistic modelingIEEE Trans Parallel Distrib Syst2015261196205338126910.1109/TPDS.2014.2308221 Chen Z, Li A, Wang Y (2019) Video-Based Pedestrian Attribute Recognition In: Computer vision and pattern recognition. arXiv:1901.05742 DongXTsongYShenMEquivalence tests for interchangeability based on two one-sided probabilitiesJ Biopharm Stat201424613321348327378910.1080/10543406.2014.941987 Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition. In: Proceedings of the international conference on learning representations CaiLZhuJZengHChenJCaiCMaKHog-assisted deep feature learning for pedestrian gender recognitionJ Frank Inst20183551991200810.1016/j.jfranklin.2017.09.003 Wang X, Zheng S, Yang R, Luo B, Tang J (2019) Pedestrian attribute recognition: a survey. In: Computer vision and pattern recognition. arXiv:1901.07474 Wang L, Yang Y, Min MR, Chakradhar ST (2017) Accelerating deep neural network training with inconsistent stochastic gradient descent. In: Neural networks the official journal of the international neural network society. Elsevier, pp 219–229 Nguyen TP, Manzanera A, Kropatsch WG (2014) Impact of topology-related attributes from local binary patterns on texture classification. In: Proceedings of the European conference on computer vision, pp 80–93 Vedaldi A, Lenc K (2014) Matconvnet: convolutional neural networks for matlab. In: Proceedings of the 23rd ACM international conference on multimedia, pp 689–692 Roth PM, Hirzer M, Kostinger M, Beleznai C, Bischof H (2014) Mahalanobis distance learning for person re-identification. In: Springer, London (Person Re-Identification), pp 247–267 Chen J, Li K, Deng Q, Li K (2019) Distributed deep learning model for intelligent video surveillance systems with edge computing. In: IEEE, transactions on industrial informatics, p 1 Loshchilov I, Hutter F (2016) Sgdr: stochastic gradient descent with restarts. In: Proceedings of the international conference on learning representations Hadgu AT, Nigam A, Diaz-Aviles E (2015) Large-scale learning with adagrad on spark. In: Proceedings of the IEEE international conference on Big Data, pp 2828–2830 Gao M, Ai H, Bai B (2016) A feature fusion strategy for person re-identification In: Proceedings of the international conference on image processing, pp 4274–4278 MoscaAMagoulasGDCustomised ensemble methodologies for deep learning: Boosted Residual Networks and related approachesNeural Comput Appl2019311713173110.1007/s00521-018-3922-2 Yan Z, Zhang H, Piramuthu R, Jagadeesh V (2015) Hd-cnn: Hierarchical deep convolutional neural networks for large scale visual recognition. In: Proceedings of the IEEE international conference on computer vision, pp 2740–2748 Li D, Zhang Z, Chen X, Ling H, Huang K (2016) A richly annotated dataset for pedestrian attribute recognition. In: Computer vision and pattern recognition. arXiv:1603.07054 HajjNadineAwadMarietteA piecewise weight update rule for a supervised training of cortical algorithmsNeural Comput Appl2019311915193010.1007/s00521-017-3167-5 Cheng K, Hui K, Zhan Y (2017) Sparse representations based distributed attribute learning for person re-identification In: Multimedia tools and applications. Springer, New York, pp 25015–25037 Cheng K, Tan X, Li M (2014) Sparse representations based attribute learning for flower classification. In: Neurocomputing. Elsevier, pp 416–426 FanQWuWZuradaJMConvergence of batch gradient learning with smoothing regularization and adaptive momentum for neural networksSpringerPlus20165129510.1186/s40064-016-1931-0 Chollet François (2017) Xception: Deep learning with depthwise separable convolutions In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1251–1258 Iandola FN, Han S, Moskewicz MW, Ashraf K, Dally WJ, Keutzer K (2016) SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$< 0.5$$\end{document} MB model size. In: Computer vision and pattern recognition. arXiv:1602.07360 Zhao R, Ouyang W, Wang X (2013) Unsupervised salience learning for person re-identification. In: Proceedings of the ieee conference on computer vision and pattern recognition, pp 3586–3593 Lazo-Cortes MS, Carrasco-Ochoa JA, Sanchez-Diaz G (2013) Easy categorization of attributes in decision tables based on basic binary discernibility matrix. In: Iberoamerican congress on pattern recognition. Springer, New York, pp 302–310 Layne R, Hospedales TM, Gong S (2012) Person re-identification by attributes. In: British machine vision conference, pp 1–11 Li D, Chen X, Zhang Z, Huang K (2018) Pose guided deep model for pedestrian attribute recognition in surveillance scenarios. In: Proceedings of the IEEE international conference on multimedia and expo (ICME), pp 1–6 Bhinge S, Levin-Schwartz Y, Adal T (2017) Data-driven fusion of multi-camera video sequences: application to abandoned object detection. In: Proceedings of the IEEE international conference on acoustics, speech and signal processing, pp 1697–1701 Chen J, Li K, Bilal K, Zhou X, Li K, Yu PS (2019) A bi-layered parallel training architecture for large-scale convolutional neural networks. In: IEEE, transactions on parallel and distributed systems, pp 965–976 Rafegas I, Vanrell M (2017) Color representation in cnns: parallelisms with biological vision. In: Proceedings of the IEEE international conference on computer vision workshop, pp 2697–2705 LiKTangXVeeravalliBLiKScheduling precedence constrained stochastic tasks on heterogeneous cluster systemsIEEE Trans Comput201564119120432967881360.6827610.1109/TC.2013.205 Li W, Wang X (2013) Locally aligned feature transforms across views. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3594–3601 Ristani E, Solera F, Zou R, Cucchiara R, Tomasi C (2016) Performance measures and a data set for multi-target, multi-camera tracking. In: Proceedings of the European conference on computer vision workshops, pp 17–35 LiuYYangJHuangYXuLLiSQiMMapreduce based parallel neural networks in enabling large scale machine learningComput Intell Neurosci2015201529767229 VD Hoang (4485_CR54) 2014; 135 Q Fan (4485_CR35) 2016; 5 4485_CR53 K Cheng (4485_CR11) 2017; 9 4485_CR52 4485_CR51 4485_CR50 G Xiao (4485_CR24) 2015; 33 A Latifi (4485_CR5) 1996; 21 4485_CR19 L Cai (4485_CR45) 2018; 355 4485_CR18 4485_CR13 4485_CR57 4485_CR12 4485_CR56 4485_CR55 4485_CR10 4485_CR17 4485_CR16 4485_CR15 4485_CR59 4485_CR58 4485_CR60 4485_CR20 4485_CR64 4485_CR63 X Dong (4485_CR49) 2014; 24 4485_CR62 4485_CR61 K Li (4485_CR28) 2015; 64 EG Danaci (4485_CR14) 2016; 84 A Chatzipavlis (4485_CR41) 2019; 31 A Mosca (4485_CR9) 2019; 31 4485_CR23 4485_CR21 4485_CR65 Y Liu (4485_CR22) 2015; 2015 4485_CR27 4485_CR26 4485_CR25 4485_CR7 4485_CR6 4485_CR4 4485_CR31 4485_CR3 4485_CR30 4485_CR1 4485_CR34 4485_CR33 4485_CR32 4485_CR39 Nadine Hajj (4485_CR40) 2019; 31 4485_CR38 4485_CR37 4485_CR36 JL Mwakalonge (4485_CR2) 2015; 2 4485_CR42 MM Oghaz (4485_CR8) 2019; 31 K Li (4485_CR29) 2015; 26 4485_CR46 4485_CR44 4485_CR43 4485_CR48 4485_CR47 |
| References_xml | – reference: Wang X, Zheng S, Yang R, Luo B, Tang J (2019) Pedestrian attribute recognition: a survey. In: Computer vision and pattern recognition. arXiv:1901.07474 – reference: Iandola FN, Han S, Moskewicz MW, Ashraf K, Dally WJ, Keutzer K (2016) SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$< 0.5$$\end{document} MB model size. In: Computer vision and pattern recognition. arXiv:1602.07360 – reference: Hadgu AT, Nigam A, Diaz-Aviles E (2015) Large-scale learning with adagrad on spark. In: Proceedings of the IEEE international conference on Big Data, pp 2828–2830 – reference: LiuYYangJHuangYXuLLiSQiMMapreduce based parallel neural networks in enabling large scale machine learningComput Intell Neurosci20152015297672297672 – reference: XiaoGLiKLiKXuZEfficient top-(k, l) top range query processing for uncertain data based on multicore architecturesDistrib Parallel Databases201533338141310.1007/s10619-014-7156-8 – reference: Flores A, Belongie SJ (2010) Removing pedestrians from google street view images. In: Computer vision and pattern recognition, pp 53–58 – reference: Layne R, Hospedales TM, Gong S (2014) Attributes-based re-identification. Springer, London (Person Re-Identification) – reference: Huanzhou Z, Zhuoer G, Haiming Z, Keyang C, Chang-Tsun L, Ligang H (2018) Developing a pattern discovery method in time series data and its GPU acceleration. In: TUP, Big data mining and analytics, pp 266–283 – reference: ChengKXuFTaoFQiMLiMData-driven pedestrian re-identification based on hierarchical semantic representationConcurr Comput Pract Exp20179e4403 – reference: FanQWuWZuradaJMConvergence of batch gradient learning with smoothing regularization and adaptive momentum for neural networksSpringerPlus20165129510.1186/s40064-016-1931-0 – reference: Li W, Wang X (2013) Locally aligned feature transforms across views. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3594–3601 – reference: Farenzena M, Bazzani L, Perina A, Murino V, Cristani M (2010) Person re-identification by symmetry-driven accumulation of local features. In: Computer vision and pattern recognition, pp 2360–2367 – reference: Ali H, Hariharan M, Yaacob S, Adom AH, Zaba SK, Elshaikh M (2016) Facial emotion recognition under partial occlusion using empirical mode decomposition. In: Proceedings of the IEEE international symposium on robotics and manufacturing automation, pp 1–6 – reference: Roth PM, Hirzer M, Kostinger M, Beleznai C, Bischof H (2014) Mahalanobis distance learning for person re-identification. In: Springer, London (Person Re-Identification), pp 247–267 – reference: OghazMMMaarofMARohaniMFZainalAShaidSZAn optimized skin texture model using gray-level co-occurrence matrixNeural Comput Appl2019311835185310.1007/s00521-017-3164-8 – reference: Dass J, Sharma M, Hassan E, Ghosh H (2013) A density based method for automatic hairstyle discovery and recognition. In: Proceedings of the national conference on computer vision, pattern recognition, image processing and graphics, pp 1–4 – reference: LatifiAFoglinoMTanakaKWilliamsPLazdunskiAA hierarchical quorum-sensing cascade in pseudomonas aeruginosa links the transcriptional activators lasr and rhir (vsmr) to expression of the stationary-phase sigma factor rposMol Microbiol19962161137114610.1046/j.1365-2958.1996.00063.x – reference: Song L, Wang Y, Han Y, Zhao X, Liu B, Li X (2016) C-brain: a deep learning accelerator that tames the diversity of cnns through adaptive data-level parallelization. In: Proceedings of the design automation conference, p 123 – reference: Li D, Chen X, Zhang Z, Huang K (2018) Pose guided deep model for pedestrian attribute recognition in surveillance scenarios. In: Proceedings of the IEEE international conference on multimedia and expo (ICME), pp 1–6 – reference: Gao M, Ai H, Bai B (2016) A feature fusion strategy for person re-identification In: Proceedings of the international conference on image processing, pp 4274–4278 – reference: Lazo-Cortes MS, Carrasco-Ochoa JA, Sanchez-Diaz G (2013) Easy categorization of attributes in decision tables based on basic binary discernibility matrix. In: Iberoamerican congress on pattern recognition. Springer, New York, pp 302–310 – reference: Jung H, Choi MK, Jung J, Lee JH, Kwon S, Jung WY (2017) Resnet-based vehicle classification and localization in traffic surveillance systems. In: Proceedings of the IEEE conference on computer vision and pattern recognition workshops, pp 934–940 – reference: Loshchilov I, Hutter F (2016) Sgdr: stochastic gradient descent with restarts. In: Proceedings of the international conference on learning representations – reference: Bo L, Lai K, Ren X, Fox D (2011) Object recognition with hierarchical kernel descriptors. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1729–1736 – reference: Botev A, Lever G, Barber D (2016) Nesterov’s accelerated gradient and momentum as approximations to regularised update descent In: Proceedings of the international joint conference on neural network, pp 1899–1903 – reference: Gray D, Brennan S, Tao H (2007) Evaluating appearance models for recognition, reacquisition, and tracking. In: Proceedings of the IEEE international workshop on performance evaluation for tracking and surveillance, vol 3(5), pp 501–512 – reference: Zhang J, Wang N, Zhang L (2018) Multi-shot pedestrian re-identification via sequential decision making. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 6781–6789 – reference: Chen J, Li K, Bilal K, Zhou X, Li K, Yu PS (2019) A bi-layered parallel training architecture for large-scale convolutional neural networks. In: IEEE, transactions on parallel and distributed systems, pp 965–976 – reference: Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition. In: Proceedings of the international conference on learning representations – reference: Kang S, Lee D, Yoo CD (2015) Face attribute classification using attribute-aware correlation map and gated convolutional neural networks. In: Proceedings of the international conference on image processing, pp 4922–4926 – reference: Nguyen TP, Manzanera A, Kropatsch WG (2014) Impact of topology-related attributes from local binary patterns on texture classification. In: Proceedings of the European conference on computer vision, pp 80–93 – reference: DongXTsongYShenMEquivalence tests for interchangeability based on two one-sided probabilitiesJ Biopharm Stat201424613321348327378910.1080/10543406.2014.941987 – reference: Cheng K, Hui K, Zhan Y (2017) Sparse representations based distributed attribute learning for person re-identification In: Multimedia tools and applications. Springer, New York, pp 25015–25037 – reference: Chollet François (2017) Xception: Deep learning with depthwise separable convolutions In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1251–1258 – reference: Chen J, Li K, Deng Q, Li K (2019) Distributed deep learning model for intelligent video surveillance systems with edge computing. In: IEEE, transactions on industrial informatics, p 1 – reference: Vedaldi A, Lenc K (2014) Matconvnet: convolutional neural networks for matlab. In: Proceedings of the 23rd ACM international conference on multimedia, pp 689–692 – reference: Li W, Zhao R, Wang X (2012) Human reidentification with transferred metric learning. In: Asian conference on computer vision. Springer, New York, pp 31–44 – reference: Umeda T, Sun Y, Irie G, Sudo K, Kinebuchi T (2016) Attribute discovery for person re-identification. In: International conference on multimedia modeling. Springer, New York, pp 268–276 – reference: Bhinge S, Levin-Schwartz Y, Adal T (2017) Data-driven fusion of multi-camera video sequences: application to abandoned object detection. In: Proceedings of the IEEE international conference on acoustics, speech and signal processing, pp 1697–1701 – reference: Li D, Zhang Z, Chen X, Ling H, Huang K (2016) A richly annotated dataset for pedestrian attribute recognition. In: Computer vision and pattern recognition. arXiv:1603.07054 – reference: Chen Y, Duffner S, Stoian A, Dufour J, Baskurt A (2018) Pedestrian attribute recognition with part-based CNN and combined feature representations. In: Proceedings of the international joint conference on computer vision imaging and computer graphics theory and applications, pp 114–122 – reference: MwakalongeJLSiuhiSWhiteJDistracted walking: examining the extent to pedestrian safety problemsJ Traffic Transp Eng201525327337 – reference: Chen Z, Li A, Wang Y (2019) Video-Based Pedestrian Attribute Recognition In: Computer vision and pattern recognition. arXiv:1901.05742 – reference: Bottou Leon (2012) Stochastic gradient descent tricks. In: Neural networks: tricks of the trade. Springer, New York, pp 421–436 – reference: Su C, Zhang S, Xing J, Gao W, Tian Q (2016) Deep attributes driven multi-camera person re-identification. In: Proceedings of the European conference on computer vision, pp 475–491 – reference: Zhao R, Ouyang W, Wang X (2013) Unsupervised salience learning for person re-identification. In: Proceedings of the ieee conference on computer vision and pattern recognition, pp 3586–3593 – reference: Yan Z, Zhang H, Piramuthu R, Jagadeesh V (2015) Hd-cnn: Hierarchical deep convolutional neural networks for large scale visual recognition. In: Proceedings of the IEEE international conference on computer vision, pp 2740–2748 – reference: Rafegas I, Vanrell M (2017) Color representation in cnns: parallelisms with biological vision. In: Proceedings of the IEEE international conference on computer vision workshop, pp 2697–2705 – reference: Layne R, Hospedales TM, Gong S (2012) Person re-identification by attributes. In: British machine vision conference, pp 1–11 – reference: ChatzipavlisATsekourasGETrygonisVVelegrakisAFTsimikasJRigosASalmasCModeling beach realignment using a neuro-fuzzy network optimized by a novel backtracking search algorithmNeural Comput Appl2019311747176310.1007/s00521-018-3809-2 – reference: Szegedy C, Liu W, Jia Y, Sermanet P, Reed SE, Anguelov D, Rabinovich A (2015) Going deeper with convolutions In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1–9 – reference: Wang L, Yang Y, Min MR, Chakradhar ST (2017) Accelerating deep neural network training with inconsistent stochastic gradient descent. In: Neural networks the official journal of the international neural network society. Elsevier, pp 219–229 – reference: LiKYangWLiKPerformance analysis and optimization for SpMV on GPU using probabilistic modelingIEEE Trans Parallel Distrib Syst2015261196205338126910.1109/TPDS.2014.2308221 – reference: CaiLZhuJZengHChenJCaiCMaKHog-assisted deep feature learning for pedestrian gender recognitionJ Frank Inst20183551991200810.1016/j.jfranklin.2017.09.003 – reference: HajjNadineAwadMarietteA piecewise weight update rule for a supervised training of cortical algorithmsNeural Comput Appl2019311915193010.1007/s00521-017-3167-5 – reference: Guo J, Gould S (2016) Depth dropout: efficient training of residual convolutional neural networks. In: Proceedings of the international conference on digital image computing: techniques and applications, pp 1–7 – reference: Sutskever I, Martens J, Dahl GE, Hinton GE (2013) On the importance of initialization and momentum in deep learning. In: Proceedings of the international conference on machine learning, pp 1139–1147 – reference: MoscaAMagoulasGDCustomised ensemble methodologies for deep learning: Boosted Residual Networks and related approachesNeural Comput Appl2019311713173110.1007/s00521-018-3922-2 – reference: Kingma DP, Ba JL (2015) Adam: a method for stochastic optimization. In: Proceedings of the international conference on learning representations – reference: HoangVDLeMHJoKHHybrid cascade boosting machine using variant scale blocks based hog features for pedestrian detectionNeurocomputing2014135C35736610.1016/j.neucom.2013.12.017 – reference: Ristani E, Solera F, Zou R, Cucchiara R, Tomasi C (2016) Performance measures and a data set for multi-target, multi-camera tracking. In: Proceedings of the European conference on computer vision workshops, pp 17–35 – reference: DanaciEGIkizlercinbisNLow-level features for visual attribute recognitionPattern Recognit Lett20168418519110.1016/j.patrec.2016.09.015 – reference: Cheng K, Tan X, Li M (2014) Sparse representations based attribute learning for flower classification. In: Neurocomputing. Elsevier, pp 416–426 – reference: LiKTangXVeeravalliBLiKScheduling precedence constrained stochastic tasks on heterogeneous cluster systemsIEEE Trans Comput201564119120432967881360.6827610.1109/TC.2013.205 – reference: Li Y, Tong G, Li X, Wang Y, Zou B, Liu Y (2019) PARNet: a joint loss function and dynamic weights network for pedestrian semantic attributes recognition of smart surveillance image. In: Multidisciplinary digital publishing institute, applied sciences, p 2027 – ident: 4485_CR25 doi: 10.1109/ICCVW.2017.318 – volume: 26 start-page: 196 issue: 1 year: 2015 ident: 4485_CR29 publication-title: IEEE Trans Parallel Distrib Syst doi: 10.1109/TPDS.2014.2308221 – volume: 31 start-page: 1713 year: 2019 ident: 4485_CR9 publication-title: Neural Comput Appl doi: 10.1007/s00521-018-3922-2 – ident: 4485_CR13 doi: 10.1007/978-3-319-46475-6_30 – volume: 33 start-page: 381 issue: 3 year: 2015 ident: 4485_CR24 publication-title: Distrib Parallel Databases doi: 10.1007/s10619-014-7156-8 – ident: 4485_CR55 – ident: 4485_CR64 doi: 10.1007/978-3-319-27674-8_24 – ident: 4485_CR32 – ident: 4485_CR16 – ident: 4485_CR20 doi: 10.1007/978-3-642-41822-8_38 – ident: 4485_CR59 – ident: 4485_CR33 doi: 10.1016/j.neunet.2017.06.003 – volume: 355 start-page: 1991 year: 2018 ident: 4485_CR45 publication-title: J Frank Inst doi: 10.1016/j.jfranklin.2017.09.003 – ident: 4485_CR56 doi: 10.1109/CVPRW.2017.129 – ident: 4485_CR58 doi: 10.1109/CVPR.2017.195 – ident: 4485_CR46 – ident: 4485_CR1 doi: 10.1109/CVPRW.2010.5543255 – ident: 4485_CR36 doi: 10.1109/IJCNN.2017.7966082 – ident: 4485_CR62 doi: 10.1109/CVPR.2010.5539926 – ident: 4485_CR48 – ident: 4485_CR57 doi: 10.1109/CVPR.2015.7298594 – volume: 84 start-page: 185 year: 2016 ident: 4485_CR14 publication-title: Pattern Recognit Lett doi: 10.1016/j.patrec.2016.09.015 – ident: 4485_CR63 doi: 10.5244/C.26.24 – volume: 2015 start-page: 297672 year: 2015 ident: 4485_CR22 publication-title: Comput Intell Neurosci – ident: 4485_CR23 – ident: 4485_CR50 – ident: 4485_CR15 doi: 10.1109/ICIP.2016.7533166 – ident: 4485_CR30 doi: 10.1109/TII.2019.2909473 – volume: 135 start-page: 357 issue: C year: 2014 ident: 4485_CR54 publication-title: Neurocomputing doi: 10.1016/j.neucom.2013.12.017 – ident: 4485_CR3 doi: 10.1109/CVPR.2018.00709 – ident: 4485_CR4 doi: 10.1109/CVPR.2011.5995719 – ident: 4485_CR51 doi: 10.1109/CVPR.2013.461 – volume: 5 start-page: 295 issue: 1 year: 2016 ident: 4485_CR35 publication-title: SpringerPlus doi: 10.1186/s40064-016-1931-0 – volume: 24 start-page: 1332 issue: 6 year: 2014 ident: 4485_CR49 publication-title: J Biopharm Stat doi: 10.1080/10543406.2014.941987 – ident: 4485_CR17 doi: 10.1016/j.neucom.2014.05.011 – volume: 31 start-page: 1835 year: 2019 ident: 4485_CR8 publication-title: Neural Comput Appl doi: 10.1007/s00521-017-3164-8 – ident: 4485_CR47 – ident: 4485_CR27 doi: 10.1109/TPDS.2018.2877359 – ident: 4485_CR12 doi: 10.1109/ICASSP.2017.7952446 – ident: 4485_CR60 doi: 10.1007/978-1-4471-6296-4_5 – ident: 4485_CR18 doi: 10.1109/NCVPRIPG.2013.6776234 – volume: 64 start-page: 191 issue: 1 year: 2015 ident: 4485_CR28 publication-title: IEEE Trans Comput doi: 10.1109/TC.2013.205 – ident: 4485_CR6 doi: 10.1109/ROMA.2016.7847818 – ident: 4485_CR53 doi: 10.1007/978-3-319-48881-3_2 – ident: 4485_CR34 – ident: 4485_CR43 doi: 10.1109/ICME.2018.8486604 – ident: 4485_CR44 – volume: 31 start-page: 1915 year: 2019 ident: 4485_CR40 publication-title: Neural Comput Appl doi: 10.1007/s00521-017-3167-5 – ident: 4485_CR37 doi: 10.1109/BigData.2015.7364091 – ident: 4485_CR21 – ident: 4485_CR31 – ident: 4485_CR42 doi: 10.5220/0006622901140122 – ident: 4485_CR26 doi: 10.1145/2897937.2897995 – ident: 4485_CR52 – ident: 4485_CR38 – ident: 4485_CR7 doi: 10.1109/ICCV.2015.314 – volume: 9 start-page: e4403 year: 2017 ident: 4485_CR11 publication-title: Concurr Comput Pract Exp – volume: 2 start-page: 327 issue: 5 year: 2015 ident: 4485_CR2 publication-title: J Traffic Transp Eng – volume: 31 start-page: 1747 year: 2019 ident: 4485_CR41 publication-title: Neural Comput Appl doi: 10.1007/s00521-018-3809-2 – ident: 4485_CR39 doi: 10.3390/app9102027 – ident: 4485_CR61 doi: 10.1007/978-1-4471-6296-4_12 – volume: 21 start-page: 1137 issue: 6 year: 1996 ident: 4485_CR5 publication-title: Mol Microbiol doi: 10.1046/j.1365-2958.1996.00063.x – ident: 4485_CR65 doi: 10.1109/CVPR.2013.460 – ident: 4485_CR10 doi: 10.1109/DICTA.2016.7797032 – ident: 4485_CR19 doi: 10.1109/ICIP.2015.7351743 |
| SSID | ssj0004685 |
| Score | 2.314347 |
| Snippet | Convolutional neural networks (CNNs) have obtained high accuracy results for pedestrian re-identification in the past few years. There is always a trade-off... |
| SourceID | proquest crossref springer |
| SourceType | Aggregation Database Enrichment Source Index Database Publisher |
| StartPage | 5695 |
| SubjectTerms | Accuracy Adaptive learning Advances in Parallel and Distributed Computing for Neural Computing Artificial Intelligence Artificial neural networks Computational Biology/Bioinformatics Computational Science and Engineering Computer Science Computing time Data Mining and Knowledge Discovery Identification methods Image Processing and Computer Vision Learning Momentum Optimization Parameters Probability and Statistics in Computer Science Training |
| SummonAdditionalLinks | – databaseName: Advanced Technologies & Aerospace Database dbid: P5Z link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1NT9wwELX4OnAp0ILYFtAcuFGLjWPvZk9VhUAcEOIACPUSOfYEVgphmw38Jf4mM16HbZHgwjVxLEfPHs_YM-8JsZ-Sx9b3w1LylZ3UrsxkURIgOhn20bjCmCAHdH02PD_Pbm5GF_HAbRrTKjubGAy1f3B8Rn6ouNQv6acm_TX5K1k1im9Xo4TGolhmlgSWbrgwf_6piwySnBTBcHaPTmPRTCid4_NQDqT5akBnRqr_N6a5t_nmgjTsOydrnx3xuvgSPU74PZsiG2IB669irVNzgLi4v4nn0zEXIwdtlApsO5PCwilEYYlbIP8WJugxSH3U0KAc-5hsFPCFp7EF5hKvKqyAvEp3Z5kGGm6bkFjWgp-RRwH9AEXk6IGPgeGeWSDax3t63AQDTF3Z2oP1dsLWeD4C5rXYFFcnx5dHpzLKOEhH67uVRTEoMoM6K1Pt7cg7wkNro5VG5VAZHHhMKBL35QD9KDN-OKKYh0yJJltTkAO6JZbqhxq3BaTKugwpoHflQCdeWZ8mFFFm1KhgR6Mnkg7D3EWOc5baqPJXduaAe0645wH3XPXEwes3kxnDx4etdzqw87jap_kc6Z742U2X-ev3e_v-cW8_xKri8D7kV-6IpbZ5xF2x4p7a8bTZC3P9BZFSBr4 priority: 102 providerName: ProQuest |
| Title | Hierarchical attributes learning for pedestrian re-identification via parallel stochastic gradient descent combined with momentum correction and adaptive learning rate |
| URI | https://link.springer.com/article/10.1007/s00521-019-04485-2 https://www.proquest.com/docview/2285410353 |
| Volume | 32 |
| WOSCitedRecordID | wos000529745200032&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: PRVPQU databaseName: Advanced Technologies & Aerospace Database customDbUrl: eissn: 1433-3058 dateEnd: 20241214 omitProxy: false ssIdentifier: ssj0004685 issn: 0941-0643 databaseCode: P5Z dateStart: 20120101 isFulltext: true titleUrlDefault: https://search.proquest.com/hightechjournals providerName: ProQuest – providerCode: PRVPQU databaseName: ProQuest Central customDbUrl: eissn: 1433-3058 dateEnd: 20241214 omitProxy: false ssIdentifier: ssj0004685 issn: 0941-0643 databaseCode: BENPR dateStart: 20120101 isFulltext: true titleUrlDefault: https://www.proquest.com/central providerName: ProQuest – providerCode: PRVAVX databaseName: SpringerLINK Contemporary 1997-Present customDbUrl: eissn: 1433-3058 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0004685 issn: 0941-0643 databaseCode: RSV dateStart: 19970101 isFulltext: true titleUrlDefault: https://link.springer.com/search?facet-content-type=%22Journal%22 providerName: Springer Nature |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1NT9tAEB210EMvQGkrQmk0h96opdjeTZwjRSAOKIr6gRAXa707ppGMiRzDX-JvMrNZJwW1ldqrvV6tNLPjebsz7wF8SjljG7hRGcmVXaRsmUVFyQZR8WhA2hZaezmgi_PRZJJdXo6noSls0VW7d1eSPlKvmt3kBFOgrxzmq0xHHHg3tbDNCEb_dvFLN6QX4mTcIjU9Kg2tMr-f4-nvaJ1jPrsW9X-b0-3_W-cObIXsEo-W7vAGXlC9C9udcgOGjfwWHs5m0njsdVAqNO1S9ooWGEQkrpFzWZyTIy_rUWND0cyFwiJvS7yfGRTe8KqiCjmDtD-NUD7jdeOLyFp0S6Io5FUz-iaHcuSLN8L40N7d8OPGB1ueytQOjTNzibzrFQiHxTv4cXry_fgsCpINkeW93EZFMSwyTSorU-XM2Fm2glJaJYoSS4mmoaOYUbcrh-TGmXajMeMbDhuK40rByeZ72Khva9oDTBNjM2Lwbsuhil1iXBozesx4UCFJRQ_iznK5DXzmIqtR5SsmZm-JnC2Re0vkSQ8OV9_Ml2wefx190DlEHnb2Ik-k5TQepDrtwefOAdav_zzb_r8N_wCvE4H2vrbyADba5o4-wit7384WTR82v5xMpl_78HKqr_re_x8BKC__RA |
| linkProvider | Springer Nature |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Nb9QwEB1VLRJcKJ_q0gJzgBNYJI6dTQ4IIaDaqsuqh4IqLiGxnbJSmi7ZtIhfxI3fyIyTdAGJ3nrgmjhWZD-PZ-yZ9wCeROSxBXZcCr6yE8qUiShKmhAVjgOnTaG1lwP6OB3PZsnRUXqwBj-HWhhOqxxsojfU9tTwGfkLyaV-YRDp6NXiq2DVKL5dHSQ0Oljsu-_fKGRbvtx7S_P7VMrdd4dvJqJXFRCG4NaKooiLRDuVlJGyeWoNBThKaSWVk8ZJ7WLrQgoMbRk7mybajlNywQnZiqBfpEx0QCZ_QykZsGLCgf70Wx2mlwClDjmbSEV9kY4v1ePzVw7c-SpCJVrIPzfClXf714Ws3-d2N_-3EboFN3uPGl93S-A2rLn6DmwOahXYG6-78GMy52Jrr_1SYd52Ul9uib1wxjGS_44LZ52XMqmxcWJu-2Qqj188n-fIXOlV5Sokr9l8yZnmGo8bnzjXou3IsZAGrCD33SIfc-MJs1y0Zyf0uPEbDHWV1xZzmy94t1n9AfN23IMPVzJc92G9Pq3dFmAkc5O4OA1MGavQytxGIUXMCTUq2JEaQThgJjM9hztLiVTZBfu0x1lGOMs8zjI5gmcX3yw6BpNLW-8M4Mp6a7bMVsgawfMBnqvX_-7tweW9PYbrk8P302y6N9vfhhuSjzJ8LukOrLfNmXsI18x5O182j_w6Q_h81bD9BTdbYiU |
| linkToPdf | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1NT-MwELUQIMRlWb5EgYU5cIOIJrHb9Ih2twKBKsSXuEWOPYFKIVulgb_E32TGSVpYARLimjiWo7HH8-yZ94TYCylia9tu6vGVnSdNGnlJSgaRfreNyiRKOTmgm7PuYBDd3vbOX1Xxu2z35kqyqmlglqa8PBzZ9HBS-ManmQyD-WBfRsojJzwnCclwUtfF5c2rykgnykkYhvN7ZFiXzbzfx9utaRpv_ndF6nae_tL3x_xT_KijTjiqpsmymMF8RSw1ig5QL_BV8Xw85IJkp4-SgS4rOSwcQy0ucQcU48IILTq5jxwK9Ia2TjhyNoanoQbmE88yzIAiS3OvmQoa7gqXXFaCrQikgP6AUDla4KNgeGAmiPLxgR4XzglTVzq3oK0esUeejoC5LdbEdf_v1e9jr5Zy8Ayt8dJLkk4SKZRRGkqre9aQRaRUMpAYGAwUdiz6hMZt2kHbi5Tt9gj3kDuR5G8SCkLXxWz-L8cNAWGgTYQE6k3akb4NtA19QpURNUo42GgJv7FibGqec5bbyOIJQ7OzREyWiJ0l4qAl9iffjCqWj09bbzeTI65X_DgOuBTVb4cqbImDZjJMX3_c2-bXmu-KhfM__fjsZHC6JRYDRv8u_XJbzJbFI_4S8-apHI6LHbcQXgCHrgiB |
| 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=Hierarchical+attributes+learning+for+pedestrian+re-identification+via+parallel+stochastic+gradient+descent+combined+with+momentum+correction+and+adaptive+learning+rate&rft.jtitle=Neural+computing+%26+applications&rft.au=Cheng%2C+Keyang&rft.au=Tao%2C+Fei&rft.au=Zhan%2C+Yongzhao&rft.au=Li%2C+Maozhen&rft.date=2020-05-01&rft.pub=Springer+London&rft.issn=0941-0643&rft.eissn=1433-3058&rft.volume=32&rft.issue=10&rft.spage=5695&rft.epage=5712&rft_id=info:doi/10.1007%2Fs00521-019-04485-2&rft.externalDocID=10_1007_s00521_019_04485_2 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0941-0643&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0941-0643&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0941-0643&client=summon |