Robust appearance feature learning using pixel‐wise discrimination for visual tracking
Considering the high dimensions of video sequences, it is often challenging to acquire a sufficient dataset to train the tracking models. From this perspective, we propose to revisit the idea of hand‐crafted feature learning to avoid such a requirement from a dataset. The proposed tracking approach...
Saved in:
| Published in | ETRI journal Vol. 41; no. 4; pp. 483 - 493 |
|---|---|
| Main Authors | , |
| Format | Journal Article |
| Language | English |
| Published |
Electronics and Telecommunications Research Institute (ETRI)
01.08.2019
한국전자통신연구원 |
| Subjects | |
| Online Access | Get full text |
| ISSN | 1225-6463 2233-7326 |
| DOI | 10.4218/etrij.2018-0486 |
Cover
| Abstract | Considering the high dimensions of video sequences, it is often challenging to acquire a sufficient dataset to train the tracking models. From this perspective, we propose to revisit the idea of hand‐crafted feature learning to avoid such a requirement from a dataset. The proposed tracking approach is composed of two phases, detection and tracking, according to how severely the appearance of a target changes. The detection phase addresses severe and rapid variations by learning a new appearance model that classifies the pixels into foreground (or target) and background. We further combine the raw pixel features of the color intensity and spatial location with convolutional feature activations for robust target representation. The tracking phase tracks a target by searching for frame regions where the best pixel‐level agreement to the model learned from the detection phase is achieved. Our two‐phase approach results in efficient and accurate tracking, outperforming recent methods in various challenging cases of target appearance changes. |
|---|---|
| AbstractList | Considering the high dimensions of video sequences, it is often challenging to acquire a sufficient dataset to train the tracking models. From this perspective, we propose to revisit the idea of hand‐crafted feature learning to avoid such a requirement from a dataset. The proposed tracking approach is composed of two phases, detection and tracking, according to how severely the appearance of a target changes. The detection phase addresses severe and rapid variations by learning a new appearance model that classifies the pixels into foreground (or target) and background. We further combine the raw pixel features of the color intensity and spatial location with convolutional feature activations for robust target representation. The tracking phase tracks a target by searching for frame regions where the best pixel‐level agreement to the model learned from the detection phase is achieved. Our two‐phase approach results in efficient and accurate tracking, outperforming recent methods in various challenging cases of target appearance changes. KCI Citation Count: 2 Considering the high dimensions of video sequences, it is often challenging to acquire a sufficient dataset to train the tracking models. From this perspective, we propose to revisit the idea of hand‐crafted feature learning to avoid such a requirement from a dataset. The proposed tracking approach is composed of two phases, detection and tracking, according to how severely the appearance of a target changes. The detection phase addresses severe and rapid variations by learning a new appearance model that classifies the pixels into foreground (or target) and background. We further combine the raw pixel features of the color intensity and spatial location with convolutional feature activations for robust target representation. The tracking phase tracks a target by searching for frame regions where the best pixel‐level agreement to the model learned from the detection phase is achieved. Our two‐phase approach results in efficient and accurate tracking, outperforming recent methods in various challenging cases of target appearance changes. Considering the high dimensions of video sequences, it is often challenging to acquire a sufficient dataset to train the tracking models. From this perspective, we propose to revisit the idea of hand‐crafted feature learning to avoid such a requirement from a dataset. The proposed tracking approach is composed of two phases, detection and tracking , according to how severely the appearance of a target changes. The detection phase addresses severe and rapid variations by learning a new appearance model that classifies the pixels into foreground (or target) and background. We further combine the raw pixel features of the color intensity and spatial location with convolutional feature activations for robust target representation. The tracking phase tracks a target by searching for frame regions where the best pixel‐level agreement to the model learned from the detection phase is achieved. Our two‐phase approach results in efficient and accurate tracking, outperforming recent methods in various challenging cases of target appearance changes. |
| Author | Kim, Sungchan Kim, Minji |
| Author_xml | – sequence: 1 givenname: Minji surname: Kim fullname: Kim, Minji organization: Chonbuk National University – sequence: 2 givenname: Sungchan orcidid: 0000-0002-5887-5606 surname: Kim fullname: Kim, Sungchan email: s.kim@chonbuk.ac.kr organization: Chonbuk National University |
| BackLink | https://www.kci.go.kr/kciportal/ci/sereArticleSearch/ciSereArtiView.kci?sereArticleSearchBean.artiId=ART002492156$$DAccess content in National Research Foundation of Korea (NRF) |
| BookMark | eNqFkc9q20AQxpeSQB0n51x17UHO_vfqaIzbGAIB40Jvy2g1MmurWrMrN_Utj5Bn7JNUkksOPbSXGZj9ft-w892Qqza0SMg9ozPJmXnALvr9jFNmciqN_kAmnAuRzwXXV2TCOFe5llp8JDcp7SnlVCozId82oTylLoPjESFC6zCrEbpTxKzpB61vd9kpDfXof2Lz6_XtxSfMKp9c9N99C50PbVaHmP3w6QRN1kVwh15_S65raBLe_elT8vXzart8zJ-ev6yXi6fcSV7I3EBVKiEoq0ohETg4WrmyZKgpyEKUCjRHBVKbojR9YboEoZxCxnihHYop-XTxbWNtD87bAH7su2AP0S4227VVhSrYnPba9UVbBdjbY_8BiOcRGAch7izEzrsGbSUNaBQFIKVSV3NT1DUD4KilQWqGvQ8XLxdDShHrdz9G7RCIHQOxQyB2CKQn1F-E8914v_5mvvkHpy_ci2_w_L81drXdcNY_SPEbMwKmPg |
| CitedBy_id | crossref_primary_10_3390_math7111059 crossref_primary_10_3390_app112311570 |
| Cites_doi | 10.1109/ACCESS.2018.2872691 10.1109/TPAMI.2016.2516982 10.1109/TIP.2018.2868561 10.1109/TPAMI.2014.2388226 10.1049/el.2016.3011 10.1016/j.patrec.2018.10.002 10.1016/j.neucom.2016.06.048 10.1109/TIP.2017.2777183 10.1109/TCSVT.2012.2201794 10.1007/s10044-013-0347-5 10.1016/j.patcog.2018.05.017 10.1016/j.patcog.2018.03.029 10.1145/1015706.1015720 10.1109/TIP.2015.2481325 10.1109/TPAMI.2011.239 10.1016/j.cviu.2016.02.003 10.1109/CVPR.2009.5206848 |
| ContentType | Journal Article |
| Copyright | 2019 ETRI |
| Copyright_xml | – notice: 2019 ETRI |
| DBID | AAYXX CITATION DOA ACYCR |
| DOI | 10.4218/etrij.2018-0486 |
| DatabaseName | CrossRef DOAJ Directory of Open Access Journals Korean Citation Index |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | CrossRef |
| Database_xml | – sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| EISSN | 2233-7326 |
| EndPage | 493 |
| ExternalDocumentID | oai_kci_go_kr_ARTI_5959170 oai_doaj_org_article_d48a6e39ae0046d789ff1aa2e648e08e 10_4218_etrij_2018_0486 ETR212184 |
| Genre | article |
| GrantInformation_xml | – fundername: Chonbuk National University |
| GroupedDBID | -~X .4S .DC .UV 0R~ 1OC 29G 2WC 5GY 5VS 9ZL AAKPC AAYBS ACGFS ACXQS ACYCR ADBBV ADDVE AENEX ALMA_UNASSIGNED_HOLDINGS ARCSS AVUZU BCNDV DU5 E3Z EBS EDO EJD GROUPED_DOAJ IPNFZ ITG ITH JDI KQ8 KVFHK MK~ ML~ O9- OK1 P5Y RIG RNS TR2 TUS WIN XSB AAYXX ADMLS CITATION OVT AAMMB AEFGJ AGXDD AIDQK AIDYY 08R |
| ID | FETCH-LOGICAL-c4294-8adb53301db34ea2ac0dcbb1e60a493b5a62e5a4689b868916ba35c5e11296ce3 |
| IEDL.DBID | DOA |
| ISSN | 1225-6463 |
| IngestDate | Tue Nov 21 21:43:30 EST 2023 Wed Aug 27 01:29:02 EDT 2025 Thu Apr 24 23:10:59 EDT 2025 Tue Jul 01 02:03:18 EDT 2025 Wed Jan 22 16:40:50 EST 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 4 |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c4294-8adb53301db34ea2ac0dcbb1e60a493b5a62e5a4689b868916ba35c5e11296ce3 |
| Notes | Funding information This work was funded by the research funds of Chonbuk National University in 2014. https://doi.org/10.4218/etrij.2018-0486 |
| ORCID | 0000-0002-5887-5606 |
| OpenAccessLink | https://doaj.org/article/d48a6e39ae0046d789ff1aa2e648e08e |
| PageCount | 11 |
| ParticipantIDs | nrf_kci_oai_kci_go_kr_ARTI_5959170 doaj_primary_oai_doaj_org_article_d48a6e39ae0046d789ff1aa2e648e08e crossref_primary_10_4218_etrij_2018_0486 crossref_citationtrail_10_4218_etrij_2018_0486 wiley_primary_10_4218_etrij_2018_0486_ETR212184 |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | August 2019 |
| PublicationDateYYYYMMDD | 2019-08-01 |
| PublicationDate_xml | – month: 08 year: 2019 text: August 2019 |
| PublicationDecade | 2010 |
| PublicationTitle | ETRI journal |
| PublicationYear | 2019 |
| Publisher | Electronics and Telecommunications Research Institute (ETRI) 한국전자통신연구원 |
| Publisher_xml | – name: Electronics and Telecommunications Research Institute (ETRI) – name: 한국전자통신연구원 |
| References | 2015; 37 2012 2011 2010 2009 2018; 81 2016; 53 2018; 83 2016; 38 2012; 34 2018; 27 2014; 23 2015; 24 2018; 6 2013; 16 2019; 28 2018 2017 2016 2015 2014 2016; 214 2013 2012; 22 2016; 153 Hong S. (e_1_2_6_5_1) 2015 Hare S. (e_1_2_6_35_1) 2011 Simonyan K. (e_1_2_6_34_1) 2014 e_1_2_6_10_1 Tsai Y.‐H. (e_1_2_6_30_1) 2016 Lan X. (e_1_2_6_32_1) 2017 Lan X. (e_1_2_6_31_1) 2016 e_1_2_6_19_1 Wu Y. (e_1_2_6_2_1) 2013 e_1_2_6_36_1 Lan X. (e_1_2_6_33_1) 2018 Hariharan B. (e_1_2_6_15_1) 2015 e_1_2_6_17_1 e_1_2_6_18_1 e_1_2_6_16_1 Nam H. (e_1_2_6_7_1) 2016 e_1_2_6_21_1 e_1_2_6_20_1 Lan X. (e_1_2_6_27_1) 2014 Lee D. (e_1_2_6_13_1) 2014 Zhong W. (e_1_2_6_14_1) 2012 e_1_2_6_9_1 Song Y. (e_1_2_6_6_1) 2018 Jia X. (e_1_2_6_12_1) 2012 e_1_2_6_25_1 e_1_2_6_24_1 e_1_2_6_3_1 e_1_2_6_23_1 e_1_2_6_22_1 e_1_2_6_29_1 Danelljan M. (e_1_2_6_8_1) 2017 e_1_2_6_28_1 Ma C. (e_1_2_6_4_1) 2015 Alt N. (e_1_2_6_11_1) 2010 e_1_2_6_26_1 |
| References_xml | – start-page: 1355 year: 2010 end-page: 1362 article-title: Rapid selection of reliable templates for visual tracking publication-title: IEEE Comput. Soc. Conf. Comput. Vision Pattern Recogn. – start-page: 4293 year: 2016 end-page: 4302 article-title: Learning multi‐domain convolutional neural networks for visual tracking publication-title: IEEE Conf. Comput. Vision Pattern Recogn. – start-page: 1838 year: 2012 end-page: 1845 article-title: Robust object tracking via sparsity‐based: collaborative model publication-title: IEEE Conf. Comput. Vision Pattern Recogn. – volume: 6 start-page: 56526 year: 2018 end-page: 56538 article-title: Complementary tracking via dual color clustering and spatio‐temporal regularized correlation learning publication-title: IEEE Access – start-page: 7008 year: 2018 end-page: 7015 article-title: Robust collaborative discriminative learning for RGB‐infrared tracking publication-title: Proc. AAAI Conf. Artif. Intell. – volume: 24 start-page: 5826 issue: 12 year: 2015 end-page: 5841 article-title: Joint sparse representation and robust feature‐level fusion for multi‐cue visual tracking publication-title: IEEE Trans. Image Process. – start-page: 3403 year: 2016 end-page: 3410 article-title: Robust joint discriminative feature learning for visual tracking publication-title: Proc. Int. Joint Conf. Artif. Intell. – volume: 22 start-page: 1365 issue: 9 year: 2012 end-page: 1376 article-title: Pixel‐wise spatial pyramid‐based hybrid tracking publication-title: IEEE Trans. Circuits Syst. Video Technol. – volume: 16 start-page: 647 issue: 4 year: 2013 end-page: 661 article-title: Fast and effective color‐based object tracking by boosted color distribution publication-title: Pattern Anal. Appicat. – volume: 37 start-page: 1834 issue: 9 year: 2015 end-page: 1848 article-title: Object tracking benchmark publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – start-page: 3074 year: 2015 end-page: 3082 article-title: Hierarchical convolutional features for visual tracking publication-title: IEEE Int Conf. Comput – volume: 83 start-page: 185 year: 2018 end-page: 195 article-title: Visual tracking using spatio‐temporally nonlocally regularized correlation filter publication-title: Pattern Recogn. – start-page: 1194 year: 2014 end-page: 1201 article-title: Multi‐cue visual tracking using robust feature‐level fusion based on joint sparse representation publication-title: IEEE Conf. Comput. Vision Pattern Recogn. – start-page: 3899 year: 2016 end-page: 3908 article-title: Video segmentation via object flow publication-title: IEEE Conf. Comput. Vision Pattern Recogn. – start-page: 248 year: 2009 end-page: 255 – volume: 81 start-page: 147 year: 2018 end-page: 160 article-title: Visual tracking via boolean map representations publication-title: Pattern Recog. – volume: 214 start-page: 607 year: 2016 end-page: 617 article-title: Robust visual tracking via patch based kernel correlation filters with adaptive multiple feature ensemble publication-title: Neurocomput. – volume: 53 start-page: 20 issue: 1 year: 2016 end-page: 22 article-title: Robust visual tracking via self‐similarity learning publication-title: Electron. Lett. – start-page: 8990 year: 2018 end-page: 8999 article-title: VITAL: VIsual Tracking via Adversarial Learning publication-title: IEEE/CVF Conf. COmput. CIsion Pattern Recogn. – start-page: 6638 year: 2017 end-page: 6646 article-title: ECO: efficient convolution operators for tracking publication-title: IEEE Conf. Comput. Vision Pattern Recogn. – start-page: 597 year: 2015 end-page: 606 article-title: Online tracking by learning discriminative saliency map with convolutional neural network publication-title: Int. Conf. Machine Learn. – volume: 28 start-page: 479 issue: 1 year: 2019 end-page: 491 article-title: Parallel attentive correlation tracking publication-title: IEEE Trans. Image Proc. – volume: 153 start-page: 100 year: 2016 end-page: 108 article-title: Robust object tracking by online Fisher discrimination boosting feature selection publication-title: Comput. Vis. Image Underst. – start-page: 3486 year: 2014 end-page: 3493 article-title: Visual tracking using pertinent patch selection and masking publication-title: IEEE Conf. Comput. Vision Pattern Recogn. – start-page: 1257 year: 2012 end-page: 1264 article-title: Visual tracking via adaptive structural local sparse appearance model publication-title: IEEE Conf. Comput. Vision Pattern Recogn. – volume: 34 start-page: 1409 issue: 7 year: 2012 end-page: 1422 article-title: Tracking‐learning‐detection publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – volume: 27 start-page: 2022 issue: 4 year: 2018 end-page: 2037 article-title: Learning common and feature‐specific patterns: a novel multiple‐sparse‐representation‐based tracker publication-title: IEEE Trans. Image Proc. – volume: 23 start-page: 309 issue: 3 year: 2014 end-page: 314 article-title: Grabcut: interactive foreground extraction using iterated graph cuts publication-title: ACM Trans. Graphics – start-page: 447 year: 2015 end-page: 456 article-title: Hypercolumns for object segmentation and fine‐grained localization publication-title: IEEE Conf. Comput. Vision Pattern Recogn. – year: 2018 article-title: Modality‐correlation‐aware sparse representation for RGB‐infrared object tracking publication-title: Pattern Recog. Lett. – start-page: 263 year: 2011 end-page: 270 article-title: Struck: structured output tracking with kernels publication-title: Int. Conf. Comput – start-page: 4118 year: 2017 end-page: 4125 article-title: Robust MIL‐based feature template learning for object tracking publication-title: Proc. AAAI Conf. Artif. Intell. – start-page: 2411 year: 2013 end-page: 2418 article-title: Online object tracking: a benchmark publication-title: IEEE Conf Comput Vision Pattern Recogn. – volume: 38 start-page: 2137 issue: 11 year: 2016 end-page: 2155 article-title: A novel performance evaluation methodology for single‐target trackers publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – year: 2014 article-title: Very deep convolutional networks for large‐scale image recognition publication-title: arXiv:1409.1556. – start-page: 263 year: 2011 ident: e_1_2_6_35_1 article-title: Struck: structured output tracking with kernels publication-title: Int. Conf. Comput – start-page: 1194 year: 2014 ident: e_1_2_6_27_1 article-title: Multi‐cue visual tracking using robust feature‐level fusion based on joint sparse representation publication-title: IEEE Conf. Comput. Vision Pattern Recogn. – start-page: 4293 year: 2016 ident: e_1_2_6_7_1 article-title: Learning multi‐domain convolutional neural networks for visual tracking publication-title: IEEE Conf. Comput. Vision Pattern Recogn. – ident: e_1_2_6_22_1 doi: 10.1109/ACCESS.2018.2872691 – start-page: 3899 year: 2016 ident: e_1_2_6_30_1 article-title: Video segmentation via object flow publication-title: IEEE Conf. Comput. Vision Pattern Recogn. – ident: e_1_2_6_10_1 doi: 10.1109/TPAMI.2016.2516982 – ident: e_1_2_6_21_1 doi: 10.1109/TIP.2018.2868561 – ident: e_1_2_6_3_1 doi: 10.1109/TPAMI.2014.2388226 – ident: e_1_2_6_18_1 doi: 10.1049/el.2016.3011 – ident: e_1_2_6_26_1 doi: 10.1016/j.patrec.2018.10.002 – start-page: 597 year: 2015 ident: e_1_2_6_5_1 article-title: Online tracking by learning discriminative saliency map with convolutional neural network publication-title: Int. Conf. Machine Learn. – start-page: 3486 year: 2014 ident: e_1_2_6_13_1 article-title: Visual tracking using pertinent patch selection and masking publication-title: IEEE Conf. Comput. Vision Pattern Recogn. – ident: e_1_2_6_19_1 doi: 10.1016/j.neucom.2016.06.048 – ident: e_1_2_6_25_1 doi: 10.1109/TIP.2017.2777183 – ident: e_1_2_6_17_1 doi: 10.1109/TCSVT.2012.2201794 – start-page: 1355 year: 2010 ident: e_1_2_6_11_1 article-title: Rapid selection of reliable templates for visual tracking publication-title: IEEE Comput. Soc. Conf. Comput. Vision Pattern Recogn. – ident: e_1_2_6_16_1 doi: 10.1007/s10044-013-0347-5 – start-page: 7008 year: 2018 ident: e_1_2_6_33_1 article-title: Robust collaborative discriminative learning for RGB‐infrared tracking publication-title: Proc. AAAI Conf. Artif. Intell. – start-page: 3074 year: 2015 ident: e_1_2_6_4_1 article-title: Hierarchical convolutional features for visual tracking publication-title: IEEE Int Conf. Comput – ident: e_1_2_6_20_1 doi: 10.1016/j.patcog.2018.05.017 – start-page: 6638 year: 2017 ident: e_1_2_6_8_1 article-title: ECO: efficient convolution operators for tracking publication-title: IEEE Conf. Comput. Vision Pattern Recogn. – start-page: 1838 year: 2012 ident: e_1_2_6_14_1 article-title: Robust object tracking via sparsity‐based: collaborative model publication-title: IEEE Conf. Comput. Vision Pattern Recogn. – ident: e_1_2_6_24_1 doi: 10.1016/j.patcog.2018.03.029 – ident: e_1_2_6_29_1 doi: 10.1145/1015706.1015720 – start-page: 4118 year: 2017 ident: e_1_2_6_32_1 article-title: Robust MIL‐based feature template learning for object tracking publication-title: Proc. AAAI Conf. Artif. Intell. – start-page: 447 year: 2015 ident: e_1_2_6_15_1 article-title: Hypercolumns for object segmentation and fine‐grained localization publication-title: IEEE Conf. Comput. Vision Pattern Recogn. – start-page: 2411 year: 2013 ident: e_1_2_6_2_1 article-title: Online object tracking: a benchmark publication-title: IEEE Conf Comput Vision Pattern Recogn. – ident: e_1_2_6_28_1 doi: 10.1109/TIP.2015.2481325 – ident: e_1_2_6_36_1 doi: 10.1109/TPAMI.2011.239 – start-page: 1257 year: 2012 ident: e_1_2_6_12_1 article-title: Visual tracking via adaptive structural local sparse appearance model publication-title: IEEE Conf. Comput. Vision Pattern Recogn. – year: 2014 ident: e_1_2_6_34_1 article-title: Very deep convolutional networks for large‐scale image recognition publication-title: arXiv:1409.1556. – ident: e_1_2_6_23_1 doi: 10.1016/j.cviu.2016.02.003 – start-page: 3403 year: 2016 ident: e_1_2_6_31_1 article-title: Robust joint discriminative feature learning for visual tracking publication-title: Proc. Int. Joint Conf. Artif. Intell. – start-page: 8990 year: 2018 ident: e_1_2_6_6_1 article-title: VITAL: VIsual Tracking via Adversarial Learning publication-title: IEEE/CVF Conf. COmput. CIsion Pattern Recogn. – ident: e_1_2_6_9_1 doi: 10.1109/CVPR.2009.5206848 |
| SSID | ssj0020458 |
| Score | 2.2197046 |
| Snippet | Considering the high dimensions of video sequences, it is often challenging to acquire a sufficient dataset to train the tracking models. From this... |
| SourceID | nrf doaj crossref wiley |
| SourceType | Open Website Enrichment Source Index Database Publisher |
| StartPage | 483 |
| SubjectTerms | convolutional neural networks detection pixel‐wise feature learning support vector machines visual tracking 전자/정보통신공학 |
| Title | Robust appearance feature learning using pixel‐wise discrimination for visual tracking |
| URI | https://onlinelibrary.wiley.com/doi/abs/10.4218%2Fetrij.2018-0486 https://doaj.org/article/d48a6e39ae0046d789ff1aa2e648e08e https://www.kci.go.kr/kciportal/ci/sereArticleSearch/ciSereArtiView.kci?sereArticleSearchBean.artiId=ART002492156 |
| Volume | 41 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| ispartofPNX | ETRI Journal, 2019, 41(4), , pp.483-493 |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1Nb9QwELVQT3BAlA-xtCALceBiNokd1z5S1KogwaFqpb1ZY3u8WlrtrvYDOPIT-I38ks4kadUeUC9cEimyE-vNKDMvGb8R4h02sdTaRaWLz8poQBUbU1S22dligDgJbxT--s2enJsvk3Zyq9UX14T18sA9cONsHFjUHpCpXD5wvpQaoEFrHFYO-e1b-eqaTA1Ui3__MdUib1XWWN2L-hiKZ2NuVPWda7qcYrm5O_Gok-2nKDNflbvJahdtjp-Ix0OaKD_2y9sVD3D-VDy6JR74TExOF3G73khYLslb2XiyYCfTKYdWEFPJVe1TuZz9wsu_v__8nK1R8jbcvpUXm0RSzip_zNZbethmBYk_nD8X58dHZ59O1NAnQSWKJkY5yJGLROsctUFoIFU5xVijrcB4HVuwDbZgrPPR0aG2EXSbWuRcyybUL8TOfDHHl0KaRCkfYNLYZNOA8wdV8rFJtrAqkCkj8eEarZAGEXHuZXEZiEwwvKGDNzC8geEdifc3E5a9fsa_hx4y_DfDWPi6u0DuEAZ3CPe5w0i8JeOFizTr5vN5uggXq0D04HNofUv0tBqJcWfb-1YUjs5OKbQTCX71P9a2Jx7SrX1fPrgvdjarLb6mlGYT33TeewVE-_P8 |
| linkProvider | Directory of Open Access Journals |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Lb9QwELZge4AeKp5iWx4W4sAlNIkd1zkW1GoLbQ_VLlpxsfwYr0Kr3VU2Cxz5CfxGfgkzSVi1SAhxSaTIdqwZT2Y-Z_wNY68gdzET2iUiliGRwkLichmToIJWUVrEJHRQ-OxcjSby_bSYXjsL0_FDbDbcyDLa7zUZOG1Ik5VLdEukxaauPlNylk6IN-4226LYJh-wrcOPk0-TDeyiX4EEu3DlJkoq0RH80CD7fwxxwze1FP7oceZ1vBm4tp7n-B7b6UNGftjp-D67BfMHbPsakeBDNr1YuPWq4Xa5xJVLiuQRWspO3peFmHHKcJ_xZfUNrn5-__G1WgGnI7ldWS9SD8f4lX-pVmt8WVNbT5voj9jk-Gj8bpT0NRMSj55FJtoGRwmjWXBCgs2tT4N3LgOVWlkKV1iVQ2Gl0qXTeMmUs6LwBVDcpTyIx2wwX8zhCePSY_hnwQvIg8ytLg9SX7rcq0gMQTIO2Zvf0jK-JxSnuhZXBoEFide04jUkXkPiHbLXmw7Ljkvj703fkvg3zYgEu32wqGemtykTpLYKBM6RUH440GWMmbU5KKkh1TBkL1F55tJXbX-6zxbmsjYIFU5MURYIVdMh2291-68ZmaPxBbp5BMS7_93jBbszGp-dmtOT8w977C62KLscwqds0NRreIZxTeOe9wv3F-dZ9A0 |
| linkToPdf | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Lb9QwELaglRA9VDzFtjwsxIFLaBI7rnMspauWR4WqLqq4WH6MV6HVbpTNAkd-Ar-RX9KZJF1RJIS4JFJkO9Y8MvM548-MvYDcxUxol4hYhkQKC4nLZUyCClpFaRGT0EbhD8fqcCLfnhVX1YS0F6bnh1gtuJFndN9rcvA6RHJyiVGJlNg21ReqzdIJ0cbdZOvElYemvr73afJ5skJd9CeQUBcabqKkEj2_Dw2y88cQ10JTx-CPAWfWxOt5axd4xnfY5pAx8r1exXfZDZjdYxu_8QjeZ2cnc7dctNzWNRou6ZFH6Bg7-XAqxJRTgfuU19V3uPj14-e3agGcduT2p3qRdjimr_xrtVjiy9rGelpDf8Am44PT_cNkODIh8RhYZKJtcFQvmgUnJNjc-jR45zJQqZWlcIVVORRWKl06jZdMOSsKXwClXcqDeMjWZvMZPGJcesz-LHgBeZC51eVu6kuXexWJIEjGEXt1JS3jBz5xOtbiwiCuIPGaTryGxGtIvCP2ctWh7qk0_t70NYl_1Yw4sLsH82ZqBpcyQWqrQOAcCeSHXV3GmFmbg5IaUg0j9hyVZ8591fWn-3RuzhuDSOHIFGWBSDUdsZ1Ot_-akTk4PcEoj3h46797PGO3Pr4Zm_dHx--22W1sUPYVhI_ZWtss4QlmNa17OtjtJW5y8zY |
| 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=Robust+appearance+feature+learning+using+pixel%E2%80%90wise+discrimination+for+visual+tracking&rft.jtitle=ETRI+journal&rft.au=%EA%B9%80%EB%AF%BC%EC%A7%80&rft.au=%EA%B9%80%EC%84%B1%EC%B0%AC&rft.date=2019-08-01&rft.pub=%ED%95%9C%EA%B5%AD%EC%A0%84%EC%9E%90%ED%86%B5%EC%8B%A0%EC%97%B0%EA%B5%AC%EC%9B%90&rft.issn=1225-6463&rft.eissn=2233-7326&rft.spage=483&rft.epage=493&rft_id=info:doi/10.4218%2Fetrij.2018-0486&rft.externalDBID=n%2Fa&rft.externalDocID=oai_kci_go_kr_ARTI_5959170 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1225-6463&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1225-6463&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1225-6463&client=summon |