Rethinking the Competition Between Detection and ReID in Multiobject Tracking
Due to balanced accuracy and speed, one-shot models which jointly learn detection and identification embeddings, have drawn great attention in multi-object tracking (MOT). However, the inherent differences and relations between detection and re-identification (ReID) are unconsciously overlooked beca...
Saved in:
| Published in: | IEEE transactions on image processing Vol. 31; pp. 3182 - 3196 |
|---|---|
| Main Authors: | , , , , , |
| Format: | Journal Article |
| Language: | English |
| Published: |
New York
IEEE
2022
The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| Subjects: | |
| ISSN: | 1057-7149, 1941-0042, 1941-0042 |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract | Due to balanced accuracy and speed, one-shot models which jointly learn detection and identification embeddings, have drawn great attention in multi-object tracking (MOT). However, the inherent differences and relations between detection and re-identification (ReID) are unconsciously overlooked because of treating them as two isolated tasks in the one-shot tracking paradigm. This leads to inferior performance compared with existing two-stage methods. In this paper, we first dissect the reasoning process for these two tasks, which reveals that the competition between them inevitably would destroy task-dependent representations learning. To tackle this problem, we propose a novel reciprocal network (REN) with a self-relation and cross-relation design so that to impel each branch to better learn task-dependent representations. The proposed model aims to alleviate the deleterious tasks competition, meanwhile improve the cooperation between detection and ReID. Furthermore, we introduce a scale-aware attention network (SAAN) that prevents semantic level misalignment to improve the association capability of ID embeddings. By integrating the two delicately designed networks into a one-shot online MOT system, we construct a strong MOT tracker, namely CSTrack. Our tracker achieves the state-of-the-art performance on MOT16, MOT17 and MOT20 datasets, without other bells and whistles. Moreover, CSTrack is efficient and runs at 16.4 FPS on a single modern GPU, and its lightweight version even runs at 34.6 FPS. The complete code has been released at https://github.com/JudasDie/SOTS |
|---|---|
| AbstractList | Due to balanced accuracy and speed, one-shot models which jointly learn detection and identification embeddings, have drawn great attention in multi-object tracking (MOT). However, the inherent differences and relations between detection and re-identification (ReID) are unconsciously overlooked because of treating them as two isolated tasks in the one-shot tracking paradigm. This leads to inferior performance compared with existing two-stage methods. In this paper, we first dissect the reasoning process for these two tasks, which reveals that the competition between them inevitably would destroy task-dependent representations learning. To tackle this problem, we propose a novel reciprocal network (REN) with a self-relation and cross-relation design so that to impel each branch to better learn task-dependent representations. The proposed model aims to alleviate the deleterious tasks competition, meanwhile improve the cooperation between detection and ReID. Furthermore, we introduce a scale-aware attention network (SAAN) that prevents semantic level misalignment to improve the association capability of ID embeddings. By integrating the two delicately designed networks into a one-shot online MOT system, we construct a strong MOT tracker, namely CSTrack. Our tracker achieves the state-of-the-art performance on MOT16, MOT17 and MOT20 datasets, without other bells and whistles. Moreover, CSTrack is efficient and runs at 16.4 FPS on a single modern GPU, and its lightweight version even runs at 34.6 FPS. The complete code has been released at https://github.com/JudasDie/SOTS.Due to balanced accuracy and speed, one-shot models which jointly learn detection and identification embeddings, have drawn great attention in multi-object tracking (MOT). However, the inherent differences and relations between detection and re-identification (ReID) are unconsciously overlooked because of treating them as two isolated tasks in the one-shot tracking paradigm. This leads to inferior performance compared with existing two-stage methods. In this paper, we first dissect the reasoning process for these two tasks, which reveals that the competition between them inevitably would destroy task-dependent representations learning. To tackle this problem, we propose a novel reciprocal network (REN) with a self-relation and cross-relation design so that to impel each branch to better learn task-dependent representations. The proposed model aims to alleviate the deleterious tasks competition, meanwhile improve the cooperation between detection and ReID. Furthermore, we introduce a scale-aware attention network (SAAN) that prevents semantic level misalignment to improve the association capability of ID embeddings. By integrating the two delicately designed networks into a one-shot online MOT system, we construct a strong MOT tracker, namely CSTrack. Our tracker achieves the state-of-the-art performance on MOT16, MOT17 and MOT20 datasets, without other bells and whistles. Moreover, CSTrack is efficient and runs at 16.4 FPS on a single modern GPU, and its lightweight version even runs at 34.6 FPS. The complete code has been released at https://github.com/JudasDie/SOTS. Due to balanced accuracy and speed, one-shot models which jointly learn detection and identification embeddings, have drawn great attention in multi-object tracking (MOT). However, the inherent differences and relations between detection and re-identification (ReID) are unconsciously overlooked because of treating them as two isolated tasks in the one-shot tracking paradigm. This leads to inferior performance compared with existing two-stage methods. In this paper, we first dissect the reasoning process for these two tasks, which reveals that the competition between them inevitably would destroy task-dependent representations learning. To tackle this problem, we propose a novel reciprocal network (REN) with a self-relation and cross-relation design so that to impel each branch to better learn task-dependent representations. The proposed model aims to alleviate the deleterious tasks competition, meanwhile improve the cooperation between detection and ReID. Furthermore, we introduce a scale-aware attention network (SAAN) that prevents semantic level misalignment to improve the association capability of ID embeddings. By integrating the two delicately designed networks into a one-shot online MOT system, we construct a strong MOT tracker, namely CSTrack. Our tracker achieves the state-of-the-art performance on MOT16, MOT17 and MOT20 datasets, without other bells and whistles. Moreover, CSTrack is efficient and runs at 16.4 FPS on a single modern GPU, and its lightweight version even runs at 34.6 FPS. The complete code has been released at https://github.com/JudasDie/SOTS |
| Author | Hu, Weiming Liang, Chao Zhu, Shuyuan Zhang, Zhipeng Li, Bing Zhou, Xue |
| Author_xml | – sequence: 1 givenname: Chao orcidid: 0000-0003-4707-5774 surname: Liang fullname: Liang, Chao email: 201921060415@std.uestc.edu.cn organization: School of Automation Engineering, University of Electronic Science and Technology of China (UESTC), Chengdu, China – sequence: 2 givenname: Zhipeng orcidid: 0000-0003-0479-332X surname: Zhang fullname: Zhang, Zhipeng email: zhangzhipeng2017@ia.ac.cn organization: National Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China – sequence: 3 givenname: Xue orcidid: 0000-0003-1654-2157 surname: Zhou fullname: Zhou, Xue email: zhouxue@uestc.edu.cn organization: School of Automation Engineering, Shenzhen Institute of Advanced Study, University of Electronic Science and Technology of China (UESTC), Chengdu, China – sequence: 4 givenname: Bing orcidid: 0000-0002-5888-6735 surname: Li fullname: Li, Bing organization: National Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China – sequence: 5 givenname: Shuyuan orcidid: 0000-0003-4450-3868 surname: Zhu fullname: Zhu, Shuyuan organization: School of Information and Communication Engineering, University of Electronic Science and Technology of China (UESTC), Chengdu, China – sequence: 6 givenname: Weiming orcidid: 0000-0001-9237-8825 surname: Hu fullname: Hu, Weiming organization: National Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China |
| BookMark | eNp9kLtPAzEMxiNURMtjR2I5iYXlSpxXmxHKqxIIhMp8SnMOTbnmyl0qxH9PjiIGBrzYsn-fZX_7pBfqgIQcAx0CUH0-mz4NGWVsyEFJPlI7ZABaQE6pYL1UUznKRyB0n-y37ZJSEBLUHulzKYDpMRuQh2eMCx_efHjN4gKzSb1aY_TR1yG7xPiBGLIrjGi_OyaU2TNOrzIfsodNlXrzZRpls8bYbsUh2XWmavHoJx-Ql5vr2eQuv3-8nU4u7nPLNY25RhTOIUMjtCgNc-XccJhTLplitnSAIJl01qLmAoVyWlDUDqA0jjoL_ICcbfeum_p9g20sVr61WFUmYL1pC6aE7kKME3r6B13Wmyak6xIl5ViKsaSJUlvKNnXbNugK66Ppfo6N8VUBtOgML5LhRWd48WN4EtI_wnXjV6b5_E9yspV4RPzF9UgqxhX_AsHDi2k |
| CODEN | IIPRE4 |
| CitedBy_id | crossref_primary_10_1117_1_JEI_32_5_053007 crossref_primary_10_1016_j_neucom_2025_130182 crossref_primary_10_1007_s40747_024_01474_4 crossref_primary_10_1007_s11554_024_01513_w crossref_primary_10_1016_j_eswa_2025_126846 crossref_primary_10_1002_cav_2272 crossref_primary_10_1016_j_cviu_2024_103973 crossref_primary_10_1109_TMM_2024_3394683 crossref_primary_10_1109_TII_2024_3366983 crossref_primary_10_3390_s23187938 crossref_primary_10_1109_TGRS_2023_3276357 crossref_primary_10_1016_j_compeleceng_2024_109078 crossref_primary_10_1109_ACCESS_2024_3362673 crossref_primary_10_1109_TCSVT_2023_3275813 crossref_primary_10_1016_j_neucom_2024_128420 crossref_primary_10_1186_s13634_024_01144_0 crossref_primary_10_1109_TITS_2023_3315222 crossref_primary_10_3390_s23208439 crossref_primary_10_26599_BDMA_2025_9020024 crossref_primary_10_1016_j_patcog_2024_110785 crossref_primary_10_1016_j_eswa_2025_128359 crossref_primary_10_1109_TMM_2023_3240881 crossref_primary_10_3390_rs16010070 crossref_primary_10_1007_s11263_024_02237_x crossref_primary_10_1016_j_compag_2025_110377 crossref_primary_10_3390_app15179727 crossref_primary_10_1093_bib_bbae591 crossref_primary_10_1109_TCSVT_2023_3245607 crossref_primary_10_3390_s22155863 crossref_primary_10_1007_s11227_025_07381_w crossref_primary_10_1049_cvi2_70010 crossref_primary_10_1007_s11263_024_02176_7 crossref_primary_10_1016_j_aap_2025_108105 crossref_primary_10_1016_j_imavis_2024_105303 crossref_primary_10_3390_rs17122042 crossref_primary_10_1007_s11760_024_03715_y crossref_primary_10_1016_j_knosys_2024_111369 crossref_primary_10_3390_app142311098 crossref_primary_10_1109_JSTARS_2023_3289293 crossref_primary_10_1109_TIP_2025_3592524 crossref_primary_10_3390_rs16173347 crossref_primary_10_1016_j_engappai_2022_105770 crossref_primary_10_1016_j_inffus_2025_103349 crossref_primary_10_1109_TCSVT_2023_3263884 crossref_primary_10_3390_s24010229 crossref_primary_10_1016_j_compmedimag_2022_102175 crossref_primary_10_1016_j_measurement_2025_118009 crossref_primary_10_1016_j_asoc_2024_111860 crossref_primary_10_1016_j_neucom_2024_127635 crossref_primary_10_1007_s11263_025_02407_5 crossref_primary_10_1109_TCSVT_2024_3524670 crossref_primary_10_1007_s11760_025_04240_2 crossref_primary_10_1007_s40747_022_00946_9 crossref_primary_10_3390_s22145267 crossref_primary_10_1007_s00521_022_08079_3 crossref_primary_10_1016_j_aap_2024_107847 crossref_primary_10_1109_TASE_2025_3529283 crossref_primary_10_1109_JIOT_2025_3585134 crossref_primary_10_1109_JSEN_2024_3522021 crossref_primary_10_1016_j_imavis_2025_105695 crossref_primary_10_1109_TIM_2024_3449952 crossref_primary_10_1109_TSP_2024_3472068 crossref_primary_10_1016_j_knosys_2024_111859 crossref_primary_10_1109_TCE_2025_3541839 crossref_primary_10_54097_2efrm195 crossref_primary_10_1016_j_patcog_2024_110369 crossref_primary_10_1109_TITS_2024_3437645 crossref_primary_10_1080_23311916_2025_2532808 crossref_primary_10_1007_s00530_025_01722_8 crossref_primary_10_1007_s11760_025_04748_7 crossref_primary_10_1007_s11227_025_07466_6 crossref_primary_10_3390_s24186015 crossref_primary_10_1109_TGRS_2025_3539462 crossref_primary_10_1109_ACCESS_2024_3411617 crossref_primary_10_1109_TCSVT_2022_3218880 crossref_primary_10_1007_s00371_023_02901_2 crossref_primary_10_1109_TIP_2025_3526066 crossref_primary_10_3390_app15020736 crossref_primary_10_3390_ani15111543 crossref_primary_10_1145_3626825 crossref_primary_10_1016_j_fmre_2023_02_003 crossref_primary_10_1016_j_knosys_2025_114072 crossref_primary_10_1016_j_neucom_2025_129563 crossref_primary_10_1109_LSP_2023_3329419 crossref_primary_10_1109_TGRS_2024_3416326 crossref_primary_10_1016_j_eswa_2024_123581 crossref_primary_10_1007_s11042_024_20360_2 crossref_primary_10_1007_s11042_023_17983_2 crossref_primary_10_1016_j_measurement_2024_116205 crossref_primary_10_1016_j_neucom_2023_03_068 crossref_primary_10_3390_app13010440 crossref_primary_10_1007_s11227_025_07664_2 crossref_primary_10_1007_s11554_024_01514_9 crossref_primary_10_1016_j_image_2023_117099 crossref_primary_10_1109_TPAMI_2025_3529926 crossref_primary_10_1007_s42979_024_02922_1 crossref_primary_10_1109_TIP_2024_3494600 crossref_primary_10_1109_LSP_2022_3191549 crossref_primary_10_1109_TCSVT_2024_3478758 crossref_primary_10_1016_j_compmedimag_2024_102439 crossref_primary_10_3390_s23094546 crossref_primary_10_1016_j_compeleceng_2024_109392 crossref_primary_10_1016_j_knosys_2024_112760 crossref_primary_10_1109_JSEN_2024_3435856 crossref_primary_10_1109_ACCESS_2024_3432156 crossref_primary_10_3389_fmars_2022_1071618 crossref_primary_10_1016_j_knosys_2024_112528 crossref_primary_10_1007_s40747_023_01273_3 crossref_primary_10_1109_LSP_2023_3236262 crossref_primary_10_1109_TITS_2024_3360875 crossref_primary_10_3390_w17142111 crossref_primary_10_1007_s13042_024_02182_8 crossref_primary_10_1016_j_neucom_2024_128906 crossref_primary_10_1088_1361_6501_ad5c8b crossref_primary_10_1109_ACCESS_2025_3596684 crossref_primary_10_3390_s22228693 crossref_primary_10_1109_JIOT_2023_3242739 crossref_primary_10_1016_j_knosys_2024_112130 crossref_primary_10_1016_j_compag_2024_109161 crossref_primary_10_1016_j_neunet_2023_09_047 crossref_primary_10_1109_TCSVT_2023_3249162 crossref_primary_10_1109_TNNLS_2024_3384446 crossref_primary_10_1007_s00371_023_02983_y crossref_primary_10_1109_TCSVT_2024_3392939 crossref_primary_10_3389_fpls_2022_1003243 crossref_primary_10_1016_j_ijtst_2025_05_007 crossref_primary_10_1109_TCSVT_2023_3238716 crossref_primary_10_1109_TITS_2025_3565334 crossref_primary_10_1002_rob_22279 crossref_primary_10_1007_s40747_024_01475_3 crossref_primary_10_1016_j_inffus_2024_102496 crossref_primary_10_1109_TMM_2025_3557710 crossref_primary_10_1111_mice_13461 crossref_primary_10_1007_s00521_025_11518_6 crossref_primary_10_1007_s10489_023_04617_1 crossref_primary_10_1109_TMM_2023_3256761 crossref_primary_10_1007_s00371_025_03872_2 crossref_primary_10_1109_JSEN_2025_3558588 crossref_primary_10_1109_TITS_2023_3316691 crossref_primary_10_1109_ACCESS_2025_3551672 crossref_primary_10_1007_s11227_022_04776_x crossref_primary_10_1016_j_imavis_2024_104964 crossref_primary_10_1016_j_jvcir_2022_103750 crossref_primary_10_1007_s10489_024_06037_1 crossref_primary_10_1109_TMM_2023_3323852 crossref_primary_10_1109_TCSVT_2024_3404275 crossref_primary_10_1109_TIP_2023_3298538 crossref_primary_10_1007_s10586_024_05059_1 crossref_primary_10_1109_ACCESS_2025_3586901 crossref_primary_10_1007_s00371_025_03861_5 crossref_primary_10_1109_TCSVT_2023_3339609 crossref_primary_10_1109_TC_2023_3343102 crossref_primary_10_1016_j_knosys_2024_112075 crossref_primary_10_1016_j_neucom_2024_127328 crossref_primary_10_1016_j_neucom_2022_09_045 crossref_primary_10_1016_j_engappai_2024_108882 crossref_primary_10_3390_s25175325 crossref_primary_10_1007_s00530_025_01694_9 crossref_primary_10_1117_1_JEI_31_6_063025 crossref_primary_10_1109_LSP_2024_3371331 crossref_primary_10_3390_app13179528 crossref_primary_10_3390_app15010107 crossref_primary_10_1016_j_neucom_2025_130988 crossref_primary_10_1177_09544070251370923 |
| Cites_doi | 10.1109/TPAMI.2009.167 10.1109/CVPR42600.2020.01468 10.1109/CVPR.2009.5206735 10.1109/CVPR.2009.5206631 10.1007/978-3-319-10602-1_48 10.1016/j.patcog.2020.107480 10.1155/2008/246309 10.1109/CVPR.2017.357 10.1109/TMM.2019.2958756 10.1109/ICIP.2016.7533003 10.1109/CVPR.2017.474 10.1007/978-3-319-48881-3_3 10.1109/ICPR.2018.8545450 10.1109/ICCV.2019.00103 10.1007/978-3-319-48881-3_2 10.1007/978-3-030-01234-2_1 10.1016/j.artint.2020.103448 10.1109/CVPR.2018.00077 10.1109/ICIP.2017.8296962 10.1007/s11042-018-6467-6 10.1109/CVPR42600.2020.00634 10.1109/WACV.2018.00057 10.1007/978-3-030-58548-8_9 10.1109/ICCV.2017.324 10.1609/aaai.v34i07.6999 10.1109/CVPR.2017.360 10.1007/978-3-030-58621-8_7 10.5244/C.30.87 10.1109/CVPR.2008.4587581 10.1109/AVSS.2017.8078516 10.1109/WACV.2019.00023 10.1145/3394171.3416297 10.1109/CVPR42600.2020.00628 10.1109/CVPR.2016.234 10.1109/CVPR.2017.106 10.1007/978-3-030-58548-8_28 10.1109/TPAMI.2016.2577031 10.1109/ICCV.2019.00409 10.1109/TNNLS.2020.2997006 |
| ContentType | Journal Article |
| Copyright | Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022 |
| Copyright_xml | – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022 |
| DBID | 97E RIA RIE AAYXX CITATION 7SC 7SP 8FD JQ2 L7M L~C L~D 7X8 |
| DOI | 10.1109/TIP.2022.3165376 |
| DatabaseName | IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef Computer and Information Systems Abstracts Electronics & Communications Abstracts Technology Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional MEDLINE - Academic |
| 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 MEDLINE - Academic |
| DatabaseTitleList | MEDLINE - Academic Technology Research Database |
| Database_xml | – sequence: 1 dbid: RIE name: IEEE/IET Electronic Library (IEL) (UW System Shared) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher – sequence: 2 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Applied Sciences Engineering |
| EISSN | 1941-0042 |
| EndPage | 3196 |
| ExternalDocumentID | 10_1109_TIP_2022_3165376 9756236 |
| Genre | orig-research |
| GrantInformation_xml | – fundername: Sichuan Science and Technology Program grantid: 2020YJ0036 funderid: 10.13039/100012542 – fundername: Natural Science Foundation of China grantid: 61972071; U20A20184 funderid: 10.13039/501100001809 – fundername: Open Project Program of the National Laboratory of Pattern Recognition grantid: 201900014 funderid: 10.13039/501100011222 – fundername: Research Program of Zhejiang Laboratory grantid: 2019KDAB02 – fundername: Intelligent Terminal Key Laboratory of Sichuan Province grantid: SCITLAB-1005 |
| GroupedDBID | --- -~X .DC 0R~ 29I 4.4 53G 5GY 5VS 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABFSI 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 E.L EBS EJD F5P HZ~ H~9 ICLAB IFIPE IFJZH IPLJI JAVBF LAI M43 MS~ O9- OCL P2P RIA RIE RNS TAE TN5 VH1 AAYXX CITATION 7SC 7SP 8FD JQ2 L7M L~C L~D 7X8 |
| ID | FETCH-LOGICAL-c390t-9ee4ffe2ea494da2fdba31b035262cdf1e1525fcce934e46f940e9f11daf0fc13 |
| IEDL.DBID | RIE |
| ISICitedReferencesCount | 206 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000794186400002&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1057-7149 1941-0042 |
| IngestDate | Sat Sep 27 21:46:51 EDT 2025 Mon Jun 30 10:11:17 EDT 2025 Sat Nov 29 03:21:16 EST 2025 Tue Nov 18 22:21:56 EST 2025 Wed Aug 27 02:40:27 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Language | English |
| License | https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html https://doi.org/10.15223/policy-029 https://doi.org/10.15223/policy-037 |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c390t-9ee4ffe2ea494da2fdba31b035262cdf1e1525fcce934e46f940e9f11daf0fc13 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23 |
| ORCID | 0000-0001-9237-8825 0000-0002-5888-6735 0000-0003-0479-332X 0000-0003-4450-3868 0000-0003-1654-2157 0000-0003-4707-5774 |
| PMID | 35412982 |
| PQID | 2655854850 |
| PQPubID | 85429 |
| PageCount | 15 |
| ParticipantIDs | ieee_primary_9756236 crossref_citationtrail_10_1109_TIP_2022_3165376 crossref_primary_10_1109_TIP_2022_3165376 proquest_journals_2655854850 proquest_miscellaneous_2649999948 |
| PublicationCentury | 2000 |
| PublicationDate | 20220000 2022-00-00 20220101 |
| PublicationDateYYYYMMDD | 2022-01-01 |
| PublicationDate_xml | – year: 2022 text: 20220000 |
| PublicationDecade | 2020 |
| PublicationPlace | New York |
| PublicationPlace_xml | – name: New York |
| PublicationTitle | IEEE transactions on image processing |
| PublicationTitleAbbrev | TIP |
| PublicationYear | 2022 |
| Publisher | IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| Publisher_xml | – name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| References | ref13 ref12 ref34 ref15 ref14 ref36 ref31 ref30 ref11 ref32 ref2 ref1 ref17 ref39 ref16 ref38 ref18 Zhang (ref10) 2020 Shao (ref35) 2018 Vaswani (ref26) 2017 Zhou (ref21) 2019 ref24 Lin (ref46) 2020 ref23 Milan (ref33) 2016 ref45 Dendorfer (ref37) 2020 ref25 ref47 ref20 ref42 ref41 ref22 ref44 ref43 ref28 ref27 ref29 ref8 ref7 ref9 ref4 ref3 ref6 ref5 Redmon (ref19) 2018 ref40 |
| References_xml | – ident: ref16 doi: 10.1109/TPAMI.2009.167 – ident: ref9 doi: 10.1109/CVPR42600.2020.01468 – ident: ref40 doi: 10.1109/CVPR.2009.5206735 – ident: ref32 doi: 10.1109/CVPR.2009.5206631 – ident: ref36 doi: 10.1007/978-3-319-10602-1_48 – ident: ref44 doi: 10.1016/j.patcog.2020.107480 – ident: ref38 doi: 10.1155/2008/246309 – ident: ref34 doi: 10.1109/CVPR.2017.357 – ident: ref6 doi: 10.1109/TMM.2019.2958756 – ident: ref12 doi: 10.1109/ICIP.2016.7533003 – ident: ref31 doi: 10.1109/CVPR.2017.474 – ident: ref3 doi: 10.1007/978-3-319-48881-3_3 – volume-title: arXiv:2003.09003 year: 2020 ident: ref37 article-title: MOT20: A benchmark for multi object tracking in crowded scenes – ident: ref4 doi: 10.1109/ICPR.2018.8545450 – ident: ref24 doi: 10.1109/ICCV.2019.00103 – volume-title: arXiv:1805.00123 year: 2018 ident: ref35 article-title: CrowdHuman: A benchmark for detecting human in a crowd – ident: ref39 doi: 10.1007/978-3-319-48881-3_2 – ident: ref28 doi: 10.1007/978-3-030-01234-2_1 – ident: ref1 doi: 10.1016/j.artint.2020.103448 – ident: ref27 doi: 10.1109/CVPR.2018.00077 – ident: ref2 doi: 10.1109/ICIP.2017.8296962 – ident: ref42 doi: 10.1007/s11042-018-6467-6 – ident: ref23 doi: 10.1109/CVPR42600.2020.00634 – volume-title: arXiv:1706.03762 year: 2017 ident: ref26 article-title: Attention is all you need – ident: ref5 doi: 10.1109/WACV.2018.00057 – ident: ref22 doi: 10.1007/978-3-030-58548-8_9 – volume-title: arXiv:1603.00831 year: 2016 ident: ref33 article-title: MOT16: A benchmark for multi-object tracking – ident: ref20 doi: 10.1109/ICCV.2017.324 – ident: ref29 doi: 10.1609/aaai.v34i07.6999 – ident: ref7 doi: 10.1109/CVPR.2017.360 – ident: ref8 doi: 10.1007/978-3-030-58621-8_7 – ident: ref47 doi: 10.5244/C.30.87 – ident: ref30 doi: 10.1109/CVPR.2008.4587581 – ident: ref13 doi: 10.1109/AVSS.2017.8078516 – ident: ref41 doi: 10.1109/WACV.2019.00023 – volume-title: arXiv:2004.01888 year: 2020 ident: ref10 article-title: FairMOT: On the fairness of detection and re-identification in multiple object tracking – volume-title: arXiv:1804.02767 year: 2018 ident: ref19 article-title: YOLOv3: An incremental improvement – volume-title: arXiv:1904.07850 year: 2019 ident: ref21 article-title: Objects as points – ident: ref45 doi: 10.1145/3394171.3416297 – ident: ref18 doi: 10.1109/CVPR42600.2020.00628 – ident: ref15 doi: 10.1109/CVPR.2016.234 – ident: ref11 doi: 10.1109/CVPR.2017.106 – ident: ref25 doi: 10.1007/978-3-030-58548-8_28 – ident: ref14 doi: 10.1109/TPAMI.2016.2577031 – ident: ref17 doi: 10.1109/ICCV.2019.00409 – ident: ref43 doi: 10.1109/TNNLS.2020.2997006 – volume-title: arXiv:2005.04490 year: 2020 ident: ref46 article-title: Human in events: A large-scale benchmark for human-centric video analysis in complex events |
| SSID | ssj0014516 |
| Score | 2.715429 |
| Snippet | Due to balanced accuracy and speed, one-shot models which jointly learn detection and identification embeddings, have drawn great attention in multi-object... |
| SourceID | proquest crossref ieee |
| SourceType | Aggregation Database Enrichment Source Index Database Publisher |
| StartPage | 3182 |
| SubjectTerms | Bells Competition Computational modeling Detectors Feature extraction ID embedding Misalignment Multiobject tracking Multiple target tracking Object detection one-shot reciprocal representation learning Representations scale-aware attention Semantics Target tracking Task analysis |
| Title | Rethinking the Competition Between Detection and ReID in Multiobject Tracking |
| URI | https://ieeexplore.ieee.org/document/9756236 https://www.proquest.com/docview/2655854850 https://www.proquest.com/docview/2649999948 |
| Volume | 31 |
| WOSCitedRecordID | wos000794186400002&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVIEE databaseName: IEEE/IET Electronic Library (IEL) (UW System Shared) customDbUrl: eissn: 1941-0042 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0014516 issn: 1057-7149 databaseCode: RIE dateStart: 19920101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3fS9xAEB5UpOhDbbXFs1a20JdC00s2m83uY9WKQisiFu4t7I9ZFEpOvJx_vzubXGipFPoWyGYTdmYyMzuz3wfwsapL5SrMM-tQZoJzkxmHRBlGSCASa-UTuv73-vJSzWb6ag0-j2dhEDE1n-EXuky1fD93S9oqm-qavLVch_W6lv1ZrbFiQISzqbJZ1Vkdw_5VSTLX05uLq5gIch7zU0noJVvwoqxEdHSK_-GNEr3KX__k5GjOdv7vE1_ByyGgZF97DXgNa9juws4QXLLBdBe7sP0b8uAe_LjG7ranTWAxBGQnKXxO7VvsuG_dYqfYpT6tlpnWs2u8OGV3LUsndueWtm9YdHSOpngDP8--3ZycZwOzQuZKnXeZRhQhIEcjtPCGB29NWVjCRpXc-VAg0SIF51CXAoUMWuSoQ1F4E_LgivItbLTzFveB6TJXmksbrAnCWGdQVR4L5DF049bbCUxXK9y4AXac2C9-NSn9yHUTxdOQeJpBPBP4ND5x30Nu_GPsHslgHDcs_wQOV0JsBptcNFxWMTcSqson8GG8Ha2JSiSmxfmSxlAGqLVQB8_P_A626P39JswhbHQPS3wPm-6xu1s8HEXFnKmjpJhPTvDeQg |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3daxQxEB9qFW0frLZKr7YawRfB9bLZ7Ece7Rc9vB6lnNC3JR8TLMie9Pb8-5vJ7i2KIvRtYbMhZDI7M5mZ3w_gQ15mlc2RJ8ZikUghdKItEmUYIYEUWFYuoutPy9msurlRVxvwaeiFQcRYfIaf6THm8t3CruiqbKxKstbFI3icSyl416015AyIcjbmNvMyKYPjv05KcjWeT65CKChEiFALwi_ZgqdZLoOpq8Qf9igSrPz1V46m5nznYYt8Ac97l5J96c7AS9jAZhd2eveS9cq73IXt37AH9-DyGtvvHXECC04gO4kOdCzgYsdd8RY7xTZWajVMN45d4-SU3TYs9uwuDF3gsGDqLE3xCr6dn81PLpKeWyGxmeJtohCl9yhQSyWdFt4ZnaWG0FELYZ1PkYiRvLWoMomy8EpyVD5Nnfbc2zR7DZvNosF9YCrjlRKF8UZ7qY3VWOUOUxTBeRPGmRGM1ztc2x54nPgvftQxAOGqDuKpSTx1L54RfBy--NmBbvxn7B7JYBjXb_8IDtdCrHutXNaiyEN0JKucj-D98DroEyVJdIOLFY2hGFApWR38e-Z38Oxifjmtp5PZ1zewRWvprmQOYbO9W-ERPLG_2tvl3dt4PO8Bx1jgoQ |
| 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=Rethinking+the+Competition+Between+Detection+and+ReID+in+Multiobject+Tracking&rft.jtitle=IEEE+transactions+on+image+processing&rft.au=Liang%2C+Chao&rft.au=Zhang%2C+Zhipeng&rft.au=Zhou%2C+Xue&rft.au=Li%2C+Bing&rft.date=2022&rft.pub=IEEE&rft.issn=1057-7149&rft.volume=31&rft.spage=3182&rft.epage=3196&rft_id=info:doi/10.1109%2FTIP.2022.3165376&rft_id=info%3Apmid%2F35412982&rft.externalDocID=9756236 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1057-7149&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1057-7149&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1057-7149&client=summon |