Adaptive Region Proposal With Channel Regularization for Robust Object Tracking
In this paper, we propose an adaptive region proposal scheme with feature channel regularization to facilitate robust object tracking. We consider tracking as a linear regression problem and an ensemble of correlation filters is trained on-line to distinguish the foreground target from the backgroun...
Saved in:
| Published in | IEEE transactions on circuits and systems for video technology Vol. 31; no. 4; pp. 1268 - 1282 |
|---|---|
| Main Authors | , , , |
| Format | Journal Article |
| Language | English |
| Published |
New York
IEEE
01.04.2021
The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| Subjects | |
| Online Access | Get full text |
Cover
Loading…
| Abstract | In this paper, we propose an adaptive region proposal scheme with feature channel regularization to facilitate robust object tracking. We consider tracking as a linear regression problem and an ensemble of correlation filters is trained on-line to distinguish the foreground target from the background. Further, we integrate adaptively learned region proposals into an enhanced two-stream tracking framework based on correlation filters. For the tracking stream, we learn two-stage cascade correlation filters on deep convolutional features to ensure competitive tracking performance. For the detection stream, we employ adaptive region proposals, which are effective in recovering target objects from tracking failures caused by heavy occlusion or out-of-view movement. In contrast to traditional tracking-by-detection methods using random samples or sliding windows, we perform target re-detection over adaptively learned region proposals. Since region proposals naturally take the objectness information into account, we show that the proposed adaptive region proposals can handle the challenging scale estimation problem as well. In addition, we observe the channel redundancy and noisy of feature representation, especially for the convolutional features. Thus, we apply a channel regularization to the correlation filter learning. Extensive experimental validations on OTB, VOT and UAV-123 datasets demonstrate that the proposed method performs favorably against state-of-the-art tracking algorithms. |
|---|---|
| AbstractList | In this paper, we propose an adaptive region proposal scheme with feature channel regularization to facilitate robust object tracking. We consider tracking as a linear regression problem and an ensemble of correlation filters is trained on-line to distinguish the foreground target from the background. Further, we integrate adaptively learned region proposals into an enhanced two-stream tracking framework based on correlation filters. For the tracking stream, we learn two-stage cascade correlation filters on deep convolutional features to ensure competitive tracking performance. For the detection stream, we employ adaptive region proposals, which are effective in recovering target objects from tracking failures caused by heavy occlusion or out-of-view movement. In contrast to traditional tracking-by-detection methods using random samples or sliding windows, we perform target re-detection over adaptively learned region proposals. Since region proposals naturally take the objectness information into account, we show that the proposed adaptive region proposals can handle the challenging scale estimation problem as well. In addition, we observe the channel redundancy and noisy of feature representation, especially for the convolutional features. Thus, we apply a channel regularization to the correlation filter learning. Extensive experimental validations on OTB, VOT and UAV-123 datasets demonstrate that the proposed method performs favorably against state-of-the-art tracking algorithms. |
| Author | Lu, Xiankai Ni, Bingbing Yang, Xiaokang Ma, Chao |
| Author_xml | – sequence: 1 givenname: Xiankai orcidid: 0000-0002-9543-6960 surname: Lu fullname: Lu, Xiankai email: carrierlxk@gmail.com organization: School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China – sequence: 2 givenname: Chao surname: Ma fullname: Ma, Chao email: chaoma@sjtu.edu.cn organization: School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China – sequence: 3 givenname: Bingbing orcidid: 0000-0001-7339-028X surname: Ni fullname: Ni, Bingbing email: nibingbing@sjtu.edu.cn organization: School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China – sequence: 4 givenname: Xiaokang orcidid: 0000-0003-4029-3322 surname: Yang fullname: Yang, Xiaokang email: xkyang@sjtu.edu.cn organization: School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China |
| BookMark | eNp9kM9LwzAUx4NMcJv-A3opeO5M0qRLjqP4CwaTWfUYkjTdMmtT01TQv952Ew8ezOUF3vfzHu8zAaPa1QaAcwRnCEF-lWePz_kMQ8RnmBOSUnIExohSFmMM6aj_Q4pihhE9AZO23UGICCPzMVgtCtkE-2GitdlYV0cP3jWulVX0YsM2yrayrk01NLtKevslwxAqnY_WTnVtiFZqZ3SIci_1q603p-C4lFVrzn7qFDzdXOfZXbxc3d5ni2WsMachNkrzghsES62wNnKuJKKIFTIlipmUQAOVZkkKC5gkSQnLouSQEpYiTYlOVTIFl4e5jXfvnWmD2LnO1_1KgSnkmGOCeZ9ih5T2rm29KYW2YX9C8NJWAkEx6BN7fWLQJ3709Sj-gzbevkn_-T90cYCsMeYXYIwmw_sGIyJ-aw |
| CODEN | ITCTEM |
| CitedBy_id | crossref_primary_10_1007_s11042_021_10574_z crossref_primary_10_1007_s11042_021_11689_z crossref_primary_10_1007_s00371_022_02573_4 crossref_primary_10_1007_s11760_024_03772_3 crossref_primary_10_1016_j_infrared_2022_104384 crossref_primary_10_1007_s11042_021_11540_5 crossref_primary_10_3390_electronics12020420 crossref_primary_10_1016_j_displa_2023_102372 crossref_primary_10_1016_j_patrec_2023_09_010 crossref_primary_10_1002_jemt_23596 crossref_primary_10_1109_TIM_2024_3436132 crossref_primary_10_1007_s00138_024_01580_w crossref_primary_10_1109_TCSVT_2023_3335157 crossref_primary_10_1109_TCSVT_2024_3494725 crossref_primary_10_1109_TIE_2021_3088366 crossref_primary_10_1007_s44295_024_00050_3 crossref_primary_10_1007_s11042_020_09965_5 crossref_primary_10_1109_LGRS_2022_3207178 crossref_primary_10_1109_TCSVT_2021_3103063 crossref_primary_10_1007_s11042_021_10852_w crossref_primary_10_1007_s11042_020_08990_8 crossref_primary_10_1109_TCSVT_2023_3289620 crossref_primary_10_1007_s10489_022_03619_9 crossref_primary_10_1007_s11042_021_10605_9 crossref_primary_10_1016_j_jvcir_2023_103974 crossref_primary_10_1007_s11042_022_12413_1 crossref_primary_10_1109_TCSVT_2023_3271275 crossref_primary_10_1016_j_cviu_2025_104325 crossref_primary_10_1016_j_imavis_2022_104374 crossref_primary_10_1007_s11042_020_10080_8 crossref_primary_10_1007_s11042_021_10650_4 crossref_primary_10_3390_s23177516 crossref_primary_10_1109_TCSVT_2023_3272319 crossref_primary_10_1016_j_neucom_2021_05_011 crossref_primary_10_1016_j_cviu_2024_104125 crossref_primary_10_1016_j_eswa_2024_124927 crossref_primary_10_1109_TCSVT_2021_3063144 crossref_primary_10_1109_TCSVT_2024_3419910 crossref_primary_10_1007_s11042_021_10856_6 crossref_primary_10_1109_TCSVT_2024_3498349 crossref_primary_10_1016_j_infrared_2021_103907 crossref_primary_10_1007_s11042_020_09546_6 crossref_primary_10_1016_j_neucom_2022_05_064 crossref_primary_10_3390_s24248120 crossref_primary_10_1109_TCSVT_2021_3077640 crossref_primary_10_1109_TCSVT_2023_3288353 crossref_primary_10_1007_s11042_022_12437_7 crossref_primary_10_1007_s00371_023_03136_x crossref_primary_10_1109_TCSVT_2020_3023440 crossref_primary_10_3390_electronics13163221 crossref_primary_10_1007_s11042_021_11736_9 crossref_primary_10_1007_s11042_020_10170_7 crossref_primary_10_1109_TCSVT_2021_3094645 crossref_primary_10_1109_TCSVT_2022_3199325 crossref_primary_10_1007_s11042_023_15235_x crossref_primary_10_1016_j_neucom_2020_04_146 crossref_primary_10_1002_int_22933 crossref_primary_10_1007_s11042_022_12715_4 crossref_primary_10_1007_s11042_020_09361_z |
| Cites_doi | 10.1109/CVPR.2016.465 10.1109/CVPR.2018.00935 10.1109/CVPR.2016.161 10.1109/TCSVT.2016.2515309 10.1007/978-3-642-33712-3_62 10.1109/WACV.2014.6836013 10.1109/CVPR.2015.7299124 10.1109/TPAMI.2018.2865311 10.1109/78.978374 10.1109/TPAMI.2010.226 10.1109/CVPR.2015.7299177 10.1109/TITS.2017.2750082 10.1109/CVPR.2016.108 10.1109/TPAMI.2014.2388226 10.1007/978-3-030-01264-9_22 10.1109/TPAMI.2015.2465908 10.1109/CVPRW.2018.00022 10.1007/978-3-319-10602-1_26 10.1007/978-3-319-10602-1_9 10.1109/TPAMI.2012.28 10.1109/CVPR.2019.00814 10.1109/ICCV.2015.490 10.1109/CVPR.2016.467 10.1109/TCYB.2018.2803217 10.1109/CVPR.2019.00374 10.1109/ICCV.2015.355 10.1109/TPAMI.2015.2453984 10.1109/TPAMI.2013.230 10.1007/978-3-319-46484-8_2 10.1007/978-3-319-10599-4_13 10.1109/CVPR.2013.312 10.1007/978-3-319-10578-9_13 10.1109/ICCV.2015.357 10.1109/CVPR.2018.00515 10.1007/978-3-319-10602-1_8 10.1109/TPAMI.2016.2577031 10.1109/CVPR.2019.00441 10.1109/CVPR.2015.7298675 10.1109/TIP.2018.2885238 10.1109/ICCV.2015.285 10.1109/TCSVT.2015.2450331 10.1109/TMM.2018.2875360 10.1109/CVPR.2014.143 10.1109/ICCV.2011.6126456 10.1109/TPAMI.2014.2345390 10.1109/CVPR.2017.733 10.1145/2508037.2508039 10.1109/ICCV.2015.354 10.1109/CVPR.2014.81 10.1109/ICCV.2017.585 10.1109/TPAMI.2011.239 10.1109/TCSVT.2017.2701279 10.1109/TPAMI.2018.2863279 10.1109/TCSVT.2018.2889457 10.1109/TIP.2009.2019809 10.1109/CVPR.2018.00934 10.1109/CVPR.2010.5540148 10.1109/CVPR.2015.7298632 10.1109/TIP.2019.2898567 10.1016/j.neucom.2011.07.024 10.1109/ICCV.2011.6126251 10.1007/978-3-642-33718-5_35 10.1109/TCYB.2017.2716101 10.1109/ICCV.2015.352 10.1111/j.2517-6161.1996.tb02080.x 10.1109/ACCESS.2019.2903121 10.1109/ICCV.2017.279 10.1109/ICCVW.2015.84 10.1007/s11263-007-0075-7 10.1145/2733373.2807412 10.1109/CVPR.2010.5539960 10.1007/s11263-017-1061-3 10.1007/978-3-319-46448-0_27 10.5244/C.29.185 10.1111/j.1551-6708.1987.tb00862.x |
| ContentType | Journal Article |
| Copyright | Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021 |
| Copyright_xml | – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021 |
| DBID | 97E RIA RIE AAYXX CITATION 7SC 7SP 8FD JQ2 L7M L~C L~D |
| DOI | 10.1109/TCSVT.2019.2944654 |
| DatabaseName | IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE/IET Electronic Library 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/IET Electronic Library (IEL) url: https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| EISSN | 1558-2205 |
| EndPage | 1282 |
| ExternalDocumentID | 10_1109_TCSVT_2019_2944654 8853333 |
| Genre | orig-research |
| GrantInformation_xml | – fundername: Shanghai Pujiang Program – fundername: NSFC grantid: 61527804; 61906119 funderid: 10.13039/501100001809 – fundername: National Key Research and Development Program of China grantid: 2016YFB1001003 |
| 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 ASUFR ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS EJD HZ~ H~9 ICLAB IFIPE IFJZH IPLJI JAVBF LAI M43 O9- OCL P2P RIA RIE RNS RXW TAE TN5 VH1 AAYXX CITATION RIG 7SC 7SP 8FD JQ2 L7M L~C L~D |
| ID | FETCH-LOGICAL-c295t-ebc9d9e10fcb2cea7ba1518da64b8e640e0bc8360d0333f0fdf9054861c54c6b3 |
| IEDL.DBID | RIE |
| ISSN | 1051-8215 |
| IngestDate | Sun Jun 29 12:42:43 EDT 2025 Tue Jul 01 00:41:13 EDT 2025 Thu Apr 24 23:06:33 EDT 2025 Wed Aug 27 02:44:54 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 4 |
| 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-c295t-ebc9d9e10fcb2cea7ba1518da64b8e640e0bc8360d0333f0fdf9054861c54c6b3 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 |
| ORCID | 0000-0001-7339-028X 0000-0003-4029-3322 0000-0002-9543-6960 |
| PQID | 2509292429 |
| PQPubID | 85433 |
| PageCount | 15 |
| ParticipantIDs | ieee_primary_8853333 proquest_journals_2509292429 crossref_primary_10_1109_TCSVT_2019_2944654 crossref_citationtrail_10_1109_TCSVT_2019_2944654 |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | 2021-04-01 |
| PublicationDateYYYYMMDD | 2021-04-01 |
| PublicationDate_xml | – month: 04 year: 2021 text: 2021-04-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationPlace | New York |
| PublicationPlace_xml | – name: New York |
| PublicationTitle | IEEE transactions on circuits and systems for video technology |
| PublicationTitleAbbrev | TCSVT |
| PublicationYear | 2021 |
| 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 | ref57 ref13 ref56 ref12 ref15 ref58 ref14 ref53 ref52 ref55 ref11 ref54 kristan (ref25) 2015 ref17 ref16 ref19 yang (ref42) 2012 ref18 xu (ref80) 2018 ref51 ref50 ref46 ref45 ref48 ref85 ref41 ref88 ref44 ref87 ref43 ref49 ref8 ref7 ref9 cheng (ref47) 2014 ref3 ref6 ref5 ref81 ref40 ref84 ref83 ref35 ref78 ref34 ref37 he (ref82) 2018 ref36 ref75 ref31 ref74 ref30 ref77 ref33 ref76 ref32 ref2 ref39 ref38 li (ref10) 2014 simonyan (ref59) 2015 smeulders (ref1) 2014; 36 ref70 ref73 ref72 kristan (ref26) 2018 ref24 ref67 ref23 ref69 ref64 ref20 ref63 ref66 ref22 danelljan (ref68) 2014 ref21 lukeži? (ref71) 2017; 48 bhat (ref86) 2018 ref28 ref27 kai (ref79) 2001 ref29 danelljan (ref65) 2016 ref60 ref62 ref61 supancic (ref4) 2013 |
| References_xml | – ident: ref66 doi: 10.1109/CVPR.2016.465 – ident: ref56 doi: 10.1109/CVPR.2018.00935 – start-page: 95 year: 2001 ident: ref79 article-title: Template matching using fast normalized cross correlation publication-title: Proc Aerosp /Defense Sens Simulation Controls – start-page: 1918 year: 2012 ident: ref42 article-title: Multi-target tracking by online learning of non-linear motion patterns and robust appearance models publication-title: Proc IEEE Conf Comput Vis Pattern Recognit – ident: ref37 doi: 10.1109/CVPR.2016.161 – ident: ref51 doi: 10.1109/TCSVT.2016.2515309 – start-page: 2379 year: 2013 ident: ref4 article-title: Self-paced learning for long-term tracking publication-title: Proc IEEE Conf Comput Vis Pattern Recognit – ident: ref78 doi: 10.1007/978-3-642-33712-3_62 – ident: ref74 doi: 10.1109/WACV.2014.6836013 – ident: ref32 doi: 10.1109/CVPR.2015.7299124 – ident: ref36 doi: 10.1109/TPAMI.2018.2865311 – ident: ref88 doi: 10.1109/78.978374 – ident: ref77 doi: 10.1109/TPAMI.2010.226 – start-page: 254 year: 2014 ident: ref10 article-title: A scale adaptive kernel correlation filter tracker with feature integration publication-title: Proc Eur Conf Comput Vis – start-page: 132 year: 2018 ident: ref82 article-title: Towards a better match in Siamese network based visual object tracker publication-title: Proc Eur Conf Comput Vis – ident: ref11 doi: 10.1109/CVPR.2015.7299177 – ident: ref15 doi: 10.1109/TITS.2017.2750082 – ident: ref60 doi: 10.1109/CVPR.2016.108 – ident: ref21 doi: 10.1109/TPAMI.2014.2388226 – ident: ref20 doi: 10.1007/978-3-030-01264-9_22 – ident: ref46 doi: 10.1109/TPAMI.2015.2465908 – start-page: 744 year: 2015 ident: ref59 article-title: Very deep convolutional networks for large-scale image recognition publication-title: Proc Int Conf Learn Represent – ident: ref45 doi: 10.1109/CVPRW.2018.00022 – year: 2018 ident: ref80 article-title: Learning adaptive discriminative correlation filters via temporal consistency preserving spatial feature selection for robust visual tracking publication-title: arXiv 1807 11348 – ident: ref48 doi: 10.1007/978-3-319-10602-1_26 – ident: ref35 doi: 10.1007/978-3-319-10602-1_9 – ident: ref52 doi: 10.1109/TPAMI.2012.28 – ident: ref58 doi: 10.1109/CVPR.2019.00814 – ident: ref12 doi: 10.1109/ICCV.2015.490 – ident: ref30 doi: 10.1109/CVPR.2016.467 – start-page: 1121 year: 2014 ident: ref68 article-title: Accurate scale estimation for robust visual tracking publication-title: Proc BMVC – ident: ref87 doi: 10.1109/TCYB.2018.2803217 – ident: ref72 doi: 10.1109/CVPR.2019.00374 – ident: ref2 doi: 10.1109/ICCV.2015.355 – ident: ref23 doi: 10.1109/TPAMI.2015.2453984 – volume: 36 start-page: 1442 year: 2014 ident: ref1 article-title: Visual tracking: An experimental survey publication-title: IEEE Trans Pattern Anal Mach Intell doi: 10.1109/TPAMI.2013.230 – ident: ref81 doi: 10.1007/978-3-319-46484-8_2 – ident: ref22 doi: 10.1007/978-3-319-10599-4_13 – start-page: 493 year: 2018 ident: ref86 article-title: Unveiling the power of deep tracking publication-title: Proc Eur Conf Comput Vis – ident: ref5 doi: 10.1109/CVPR.2013.312 – ident: ref69 doi: 10.1007/978-3-319-10578-9_13 – ident: ref19 doi: 10.1109/ICCV.2015.357 – ident: ref83 doi: 10.1109/CVPR.2018.00515 – ident: ref76 doi: 10.1007/978-3-319-10602-1_8 – ident: ref54 doi: 10.1109/TPAMI.2016.2577031 – ident: ref57 doi: 10.1109/CVPR.2019.00441 – ident: ref14 doi: 10.1109/CVPR.2015.7298675 – ident: ref38 doi: 10.1109/TIP.2018.2885238 – start-page: 564 year: 2015 ident: ref25 article-title: The visual object tracking VOT2015 challenge results publication-title: Proc ICCV Workshops – ident: ref50 doi: 10.1109/ICCV.2015.285 – ident: ref6 doi: 10.1109/TCSVT.2015.2450331 – ident: ref39 doi: 10.1109/TMM.2018.2875360 – ident: ref31 doi: 10.1109/CVPR.2014.143 – ident: ref49 doi: 10.1109/ICCV.2011.6126456 – ident: ref8 doi: 10.1109/TPAMI.2014.2345390 – ident: ref64 doi: 10.1109/CVPR.2017.733 – ident: ref28 doi: 10.1145/2508037.2508039 – ident: ref73 doi: 10.1109/ICCV.2015.354 – ident: ref53 doi: 10.1109/CVPR.2014.81 – ident: ref40 doi: 10.1109/ICCV.2017.585 – start-page: 3 year: 2018 ident: ref26 article-title: The sixth visual object tracking VOT2018 challenge results publication-title: Proc Eur Conf Comput Vis (ECCV) Workshops – start-page: 3286 year: 2014 ident: ref47 article-title: BING: Binarized normed gradients for objectness estimation at 300 fps publication-title: Proc IEEE Conf Comput Vis Pattern Recognit – ident: ref3 doi: 10.1109/TPAMI.2011.239 – ident: ref7 doi: 10.1109/TCSVT.2017.2701279 – ident: ref55 doi: 10.1109/TPAMI.2018.2863279 – ident: ref16 doi: 10.1109/TCSVT.2018.2889457 – ident: ref18 doi: 10.1109/TIP.2009.2019809 – ident: ref84 doi: 10.1109/CVPR.2018.00934 – ident: ref43 doi: 10.1109/CVPR.2010.5540148 – ident: ref33 doi: 10.1109/CVPR.2015.7298632 – ident: ref34 doi: 10.1109/TIP.2019.2898567 – ident: ref29 doi: 10.1016/j.neucom.2011.07.024 – ident: ref9 doi: 10.1109/ICCV.2011.6126251 – ident: ref41 doi: 10.1007/978-3-642-33718-5_35 – volume: 48 start-page: 1849 year: 2017 ident: ref71 article-title: Deformable parts correlation filters for robust visual tracking publication-title: IEEE Trans Cybern doi: 10.1109/TCYB.2017.2716101 – ident: ref13 doi: 10.1109/ICCV.2015.352 – ident: ref62 doi: 10.1111/j.2517-6161.1996.tb02080.x – ident: ref44 doi: 10.1109/ACCESS.2019.2903121 – ident: ref67 doi: 10.1109/ICCV.2017.279 – ident: ref70 doi: 10.1109/ICCVW.2015.84 – start-page: 472 year: 2016 ident: ref65 article-title: Beyond correlation filters: Learning continuous convolution operators for visual tracking publication-title: Proc Eur Conf Comput Vis – ident: ref75 doi: 10.1007/s11263-007-0075-7 – ident: ref63 doi: 10.1145/2733373.2807412 – ident: ref17 doi: 10.1109/CVPR.2010.5539960 – ident: ref85 doi: 10.1007/s11263-017-1061-3 – ident: ref27 doi: 10.1007/978-3-319-46448-0_27 – ident: ref61 doi: 10.5244/C.29.185 – ident: ref24 doi: 10.1111/j.1551-6708.1987.tb00862.x |
| SSID | ssj0014847 |
| Score | 2.6094651 |
| Snippet | In this paper, we propose an adaptive region proposal scheme with feature channel regularization to facilitate robust object tracking. We consider tracking as... |
| SourceID | proquest crossref ieee |
| SourceType | Aggregation Database Enrichment Source Index Database Publisher |
| StartPage | 1268 |
| SubjectTerms | Adaptive region proposals Algorithms channel regularization Correlation correlation filters Estimation Feature extraction Object tracking Occlusion Proposals Redundancy Regularization robust object tracking Robustness (mathematics) Target detection Target tracking Tracking Visualization |
| Title | Adaptive Region Proposal With Channel Regularization for Robust Object Tracking |
| URI | https://ieeexplore.ieee.org/document/8853333 https://www.proquest.com/docview/2509292429 |
| Volume | 31 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1LTwIxEJ4gJz34QiOKpgdvutB9sj0SIiEmiEFQbpu2241GAkSWi7_embIQXzHuaZNtk26n7Xwz_WYG4DIVnmriUnCykLxVnLaUFBqtVulLheehb8v59O6i7ii4HYfjElxvYmGMMZZ8Zur0au_y05lekqusEaNuwWcLttBwW8VqbW4MgtgWE0O44Dox6rF1gAwXjWH74XFILC5R94RNIPZFCdmqKj-OYqtfOnvQW49sRSt5rS9zVdfv35I2_nfo-7BbAE3WWq2MAyiZ6SHsfEo_WIF-K5VzOu7YwBAtmd1TyYQF9np6yZ8ZBR5MzYQ-Ele1CNhkiHLZYKaWi5z1FXlxGOo7TR73Ixh1bobtrlMUWHC0J8LcMUqLVBiXZ1p52simkggA4lRGgYpNFHDDlaYoj5Tj2DOepZlAiBdHrg4DHSn_GMrT2dScAAt9YbIslFwqGQRaqwj_1-OB9tEKNm6zCu56xhNdZB-nIhiTxFohXCRWSglJKSmkVIWrTZ_5KvfGn60rNO2blsWMV6G2FmxSbM9FgrgPYSGiE3H6e68z2PaIvGIpOjUo529Lc47oI1cXdtl9ANmu1Ww |
| linkProvider | IEEE |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwzV1LT9wwEB5Remg5QIFWXR6tD-VUZXGcx8aHHhAULeVVwdJyC7YzEYjVLmKzQvS38Ff4b8x4s6s-UG9I5BQpdqR4JjPf2N_MAHwqtLItUoWgTHi3SvIvZbSjqNVExpI9jHw7n_2DtH0SfztNTqfgbpILg4iefIZNvvVn-UXfDXmrbD0j30JXTaHcxdsbCtAGX3a2SJprSm1_7Wy2g7qHQOCUTqoArdOFxlCWziqHpmUN-bisMGlsM0xjidI6TmQoJL25lGVRakIxWRq6JHapjei9L-Al4YxEjbLDJmcUcebblxFACYOMPOc4JUfq9c7m8Y8O88Z0U2lfsuwPt-f7uPxj_L1H256D-_FajIgsl81hZZvu119lIp_rYr2B2RpKi42R7s_DFPYWYOa3AouLcLhRmCs26OIImXgtvnNTiAHN-nlRnQtOrehhlx8yG7dOSRWE48VR3w4HlTi0vE8lyKM7PlN4CydP8kXvYLrX7-F7EEmksSwTI401ceycTWl9lYxdRHE-hq0GhGMJ566ur85tPrq5j7Okzr1W5KwVea0VDfg8mXM1qi7y39GLLObJyFrCDVgZK1JeG6BBTsiWgC_hL730-KyP8Krd2d_L93YOdpfhtWKqjickrcB0dT3EVcJalf3gVV7A2VOrzQMPADS8 |
| 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=Adaptive+Region+Proposal+With+Channel+Regularization+for+Robust+Object+Tracking&rft.jtitle=IEEE+transactions+on+circuits+and+systems+for+video+technology&rft.au=Lu%2C+Xiankai&rft.au=Ma%2C+Chao&rft.au=Ni%2C+Bingbing&rft.au=Yang%2C+Xiaokang&rft.date=2021-04-01&rft.pub=The+Institute+of+Electrical+and+Electronics+Engineers%2C+Inc.+%28IEEE%29&rft.issn=1051-8215&rft.eissn=1558-2205&rft.volume=31&rft.issue=4&rft.spage=1268&rft_id=info:doi/10.1109%2FTCSVT.2019.2944654&rft.externalDBID=NO_FULL_TEXT |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1051-8215&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1051-8215&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1051-8215&client=summon |