Attribute-Aware Pedestrian Detection in a Crowd
Pedestrian detection is an initial step to perform outdoor scene analysis, which plays an essential role in many real-world applications. Although having enjoyed the merits of deep learning frameworks from the generic object detectors, pedestrian detection is still a very challenging task due to hea...
Saved in:
| Published in: | IEEE transactions on multimedia Vol. 23; pp. 3085 - 3097 |
|---|---|
| Main Authors: | , , , , , , |
| Format: | Journal Article |
| Language: | English |
| Published: |
Piscataway
IEEE
2021
The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| Subjects: | |
| ISSN: | 1520-9210, 1941-0077 |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract | Pedestrian detection is an initial step to perform outdoor scene analysis, which plays an essential role in many real-world applications. Although having enjoyed the merits of deep learning frameworks from the generic object detectors, pedestrian detection is still a very challenging task due to heavy occlusions, and highly crowded group. Generally, the conventional detectors are unable to differentiate individuals from each other effectively under such a dense environment. To tackle this critical problem, we propose an attribute-aware pedestrian detector to explicitly model people's semantic attributes in a high-level feature detection fashion. Besides the typical semantic features, center position, target's scale, and offset, we introduce a pedestrian-oriented attribute feature to encode the high-level semantic differences among the crowd. Moreover, a novel attribute-feature-based Non-Maximum Suppression (NMS) is proposed to distinguish the person from a highly overlapped group by adaptively rejecting the false-positive results in a very crowd settings. Furthermore, an enhanced ground truth target is designed to alleviate the difficulties caused by the attribute configuration, and to ease the class imbalance issue during training. Finally, we evaluate our proposed attribute-aware pedestrian detector on three benchmark datasets including CityPerson, CrowdHuman, and EuroCityPerson, and achieves the state-of-the-art results. |
|---|---|
| AbstractList | Pedestrian detection is an initial step to perform outdoor scene analysis, which plays an essential role in many real-world applications. Although having enjoyed the merits of deep learning frameworks from the generic object detectors, pedestrian detection is still a very challenging task due to heavy occlusions, and highly crowded group. Generally, the conventional detectors are unable to differentiate individuals from each other effectively under such a dense environment. To tackle this critical problem, we propose an attribute-aware pedestrian detector to explicitly model people's semantic attributes in a high-level feature detection fashion. Besides the typical semantic features, center position, target's scale, and offset, we introduce a pedestrian-oriented attribute feature to encode the high-level semantic differences among the crowd. Moreover, a novel attribute-feature-based Non-Maximum Suppression (NMS) is proposed to distinguish the person from a highly overlapped group by adaptively rejecting the false-positive results in a very crowd settings. Furthermore, an enhanced ground truth target is designed to alleviate the difficulties caused by the attribute configuration, and to ease the class imbalance issue during training. Finally, we evaluate our proposed attribute-aware pedestrian detector on three benchmark datasets including CityPerson, CrowdHuman, and EuroCityPerson, and achieves the state-of-the-art results. |
| Author | Lin, Lixiang Chen, Yun-chen Hu, Yao Hoi, Steven C. H. Zhu, Jianke Li, Yang Zhang, Jialiang |
| Author_xml | – sequence: 1 givenname: Jialiang orcidid: 0000-0001-5085-3771 surname: Zhang fullname: Zhang, Jialiang email: zjialiang@zju.edu.cn organization: College of Computer Science, Zhejiang University, Hangzhou, China – sequence: 2 givenname: Lixiang orcidid: 0000-0001-8319-2009 surname: Lin fullname: Lin, Lixiang email: lxlin@zju.edu.cn organization: College of Computer Science, Zhejiang University, Hangzhou, China – sequence: 3 givenname: Jianke orcidid: 0000-0003-1831-0106 surname: Zhu fullname: Zhu, Jianke email: jkzhu@zju.edu.cn organization: College of Computer Science, Zhejiang University, Hangzhou 310027, China, and also with the Alibaba-Zhejiang University Joint Research Institute of Frontier Technologies, Hangzhou, China – sequence: 4 givenname: Yang orcidid: 0000-0001-9427-7665 surname: Li fullname: Li, Yang email: liyang89@zju.edu.cn organization: College of Computer Science, Zhejiang University, Hangzhou, China – sequence: 5 givenname: Yun-chen surname: Chen fullname: Chen, Yun-chen email: jeanchen@smu.edu.sg organization: School of Information Systems, Singapore Management University, Singapore – sequence: 6 givenname: Yao surname: Hu fullname: Hu, Yao email: yaoohu@alibaba-inc.com organization: Company of Alibaba, Youku Cognitive, and Intelligent Lab., Beijing, China – sequence: 7 givenname: Steven C. H. orcidid: 0000-0002-4584-3453 surname: Hoi fullname: Hoi, Steven C. H. email: chhoi@smu.edu.sg organization: School of Information Systems, Singapore Management University, Singapore |
| BookMark | eNp9kD1rwzAQhkVJoUnavdDF0NnJnWxZ1hjST0hoh3QWsnwCh9ROZYXQf18Fhw4dutwdx_vexzNho7ZribFbhBkiqPlmvZ5x4DDLYigUXrAxqhxTAClHsRYcUsURrtik77cAmAuQYzZfhOCb6hAoXRyNp-Sdaupjy7TJAwWyoenapGkTkyx9d6yv2aUzu55uznnKPp4eN8uXdPX2_LpcrFLLFYbUGgIUFmvhDNZoiaikHLg0KF1ZGcerkmdkqjqXSFYWVmQGpBHOFUWZ5dmU3Q9z9777OsSL9LY7-Dau1FxIoUrgKouqYlBZ3_W9J6dtE8zp5OBNs9MI-gRHRzj6BEef4UQj_DHuffNp_Pd_lrvB0sRnfuUKyxyBZz8EH3BE |
| CODEN | ITMUF8 |
| CitedBy_id | crossref_primary_10_1109_ACCESS_2025_3563311 crossref_primary_10_1109_TIP_2023_3307222 crossref_primary_10_1109_TMM_2022_3192729 crossref_primary_10_1109_TITS_2022_3142445 crossref_primary_10_1016_j_neucom_2022_08_026 crossref_primary_10_1016_j_patcog_2024_110539 crossref_primary_10_3390_s24144747 crossref_primary_10_1109_TPAMI_2023_3273210 crossref_primary_10_3390_electronics12081781 crossref_primary_10_1007_s40815_025_02039_4 crossref_primary_10_1109_ACCESS_2025_3599213 crossref_primary_10_1109_TMM_2022_3203870 crossref_primary_10_3233_JIFS_236811 crossref_primary_10_1109_TIM_2024_3428635 crossref_primary_10_4018_IJSWIS_345651 crossref_primary_10_3390_rs15133265 crossref_primary_10_1109_TMM_2023_3328189 crossref_primary_10_1109_ACCESS_2023_3287488 crossref_primary_10_3390_s21103312 crossref_primary_10_1109_TITS_2024_3495814 crossref_primary_10_1109_LSP_2024_3525397 crossref_primary_10_1016_j_patcog_2022_109071 crossref_primary_10_1007_s11227_022_04815_7 crossref_primary_10_1109_TMM_2023_3293333 crossref_primary_10_1109_TITS_2022_3171250 crossref_primary_10_1109_TMM_2021_3103605 crossref_primary_10_1109_LSP_2022_3215920 crossref_primary_10_3390_app13148073 crossref_primary_10_1109_TETCI_2024_3440193 crossref_primary_10_1109_TMM_2024_3381377 crossref_primary_10_1111_coin_70032 crossref_primary_10_1109_ACCESS_2022_3150988 crossref_primary_10_1109_TCSVT_2024_3383914 crossref_primary_10_1109_TMM_2024_3401549 crossref_primary_10_1109_TMM_2021_3075566 crossref_primary_10_3390_math10010139 crossref_primary_10_1007_s40747_022_00728_3 |
| Cites_doi | 10.1109/CVPR.2017.474 10.1109/CVPR42600.2020.01223 10.1007/978-3-030-01216-8_33 10.1007/978-3-319-46466-4_20 10.1109/TMM.2017.2759508 10.1109/CVPR.2017.106 10.1007/978-3-030-01219-9_39 10.1109/CVPR.2018.00255 10.1109/ICCV.2013.190 10.1109/CVPR.2013.473 10.1109/TMM.2016.2642789 10.1109/CVPR.2019.00662 10.1007/978-3-030-01264-9_48 10.1109/CVPR.2015.7299143 10.1023/A:1008162616689 10.1007/978-3-319-46448-0_2 10.1109/ICCV.2015.221 10.1109/CVPR.2010.5540111 10.1109/ICCV.2017.593 10.1109/TMM.2019.2929005 10.1109/ICCV.2019.00507 10.1109/CVPR.2019.00533 10.1109/CVPR.2015.7298784 10.1109/TPAMI.2019.2897684 10.1109/CVPR.2018.00811 10.1109/CVPR.2018.00378 10.1109/CVPR.2017.690 10.1109/TPAMI.2014.2300479 10.1109/CVPR42600.2020.01188 10.1007/978-3-030-01264-9_38 10.1007/s11263-015-0816-y 10.1109/ICCV.2017.377 10.1109/TPAMI.2009.167 10.1109/CVPR.2017.639 10.1007/978-3-030-01234-2_17 10.1007/978-3-319-46493-0_22 10.1109/TMM.2018.2829602 10.1007/978-3-030-01246-5_9 10.1007/978-3-030-01234-2_33 10.1109/CVPR.2016.90 10.1109/CVPR.2017.685 10.1109/CVPR.2018.00719 10.1109/ICCV.2017.324 10.1109/ICCV.2015.169 10.1109/CVPR.2016.350 |
| 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/TMM.2020.3020691 |
| DatabaseName | IEEE Xplore (IEEE) IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef Computer and Information Systems Abstracts Electronics & Communications Abstracts Technology Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional |
| DatabaseTitle | CrossRef Technology Research Database Computer and Information Systems Abstracts – Academic Electronics & Communications Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Professional |
| DatabaseTitleList | Technology Research Database |
| Database_xml | – sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering Computer Science |
| EISSN | 1941-0077 |
| EndPage | 3097 |
| ExternalDocumentID | 10_1109_TMM_2020_3020691 9184102 |
| Genre | orig-research |
| GrantInformation_xml | – fundername: National Natural Science Foundation of China grantid: 61831015 funderid: 10.13039/501100001809 |
| GroupedDBID | -~X 0R~ 29I 4.4 5GY 5VS 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFO ACGFS ACIWK AENEX AETIX AGQYO AGSQL AHBIQ AI. AIBXA AKJIK AKQYR ALLEH ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS EJD HZ~ H~9 IFIPE IFJZH IPLJI JAVBF LAI M43 O9- OCL P2P PQQKQ RIA RIE RNS TN5 VH1 ZY4 AAYXX CITATION 7SC 7SP 8FD JQ2 L7M L~C L~D |
| ID | FETCH-LOGICAL-c291t-cae015c1d5fa1d1ceee8e4027a17f8baf2b823eabd471ec76c53a07a5ff668343 |
| IEDL.DBID | RIE |
| ISICitedReferencesCount | 50 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000698902000011&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1520-9210 |
| IngestDate | Sun Nov 09 07:17:36 EST 2025 Tue Nov 18 21:57:15 EST 2025 Sat Nov 29 03:10:05 EST 2025 Wed Aug 27 05:08:48 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Language | English |
| License | https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html https://doi.org/10.15223/policy-029 https://doi.org/10.15223/policy-037 |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c291t-cae015c1d5fa1d1ceee8e4027a17f8baf2b823eabd471ec76c53a07a5ff668343 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 |
| ORCID | 0000-0002-4584-3453 0000-0003-1831-0106 0000-0001-8319-2009 0000-0001-9427-7665 0000-0001-5085-3771 |
| PQID | 2575980293 |
| PQPubID | 75737 |
| PageCount | 13 |
| ParticipantIDs | crossref_citationtrail_10_1109_TMM_2020_3020691 crossref_primary_10_1109_TMM_2020_3020691 ieee_primary_9184102 proquest_journals_2575980293 |
| PublicationCentury | 2000 |
| PublicationDate | 20210000 2021-00-00 20210101 |
| PublicationDateYYYYMMDD | 2021-01-01 |
| PublicationDate_xml | – year: 2021 text: 20210000 |
| PublicationDecade | 2020 |
| PublicationPlace | Piscataway |
| PublicationPlace_xml | – name: Piscataway |
| PublicationTitle | IEEE transactions on multimedia |
| PublicationTitleAbbrev | TMM |
| 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 | ref13 ref56 ref12 ref15 ren (ref37) 2015 ref14 ref53 zhang (ref49) 2016 ref52 ref55 ref11 ref54 nam (ref30) 2014 ouyang (ref31) 2012 ref16 ref19 ref51 ref50 ref46 ref45 ref48 ref47 ref41 ref44 ref43 ref8 ref7 ref9 ref4 ref3 ref6 ref5 ref35 zhou (ref57) 2019 ref36 tarvainen (ref42) 2017 ref33 ref32 law (ref18) 2018 ref2 ref1 ref39 ref38 kingma (ref17) 2015 ref24 ref23 ref26 liu (ref25) 2016 ref20 ref22 ref21 ref28 ref27 ref29 shao (ref40) 2018 hasan (ref10) 2020 paszke (ref34) 2017 |
| References_xml | – ident: ref51 doi: 10.1109/CVPR.2017.474 – ident: ref4 doi: 10.1109/CVPR42600.2020.01223 – ident: ref14 doi: 10.1007/978-3-030-01216-8_33 – ident: ref19 doi: 10.1007/978-3-319-46466-4_20 – ident: ref20 doi: 10.1109/TMM.2017.2759508 – ident: ref22 doi: 10.1109/CVPR.2017.106 – start-page: 91 year: 2015 ident: ref37 article-title: Faster R-CNN: Towards real-time object detection with region proposal networks publication-title: Proc Adv Neural Inform Process Syst – ident: ref53 doi: 10.1007/978-3-030-01219-9_39 – ident: ref48 doi: 10.1109/CVPR.2018.00255 – ident: ref29 doi: 10.1109/ICCV.2013.190 – ident: ref38 doi: 10.1109/CVPR.2013.473 – ident: ref21 doi: 10.1109/TMM.2016.2642789 – ident: ref24 doi: 10.1109/CVPR.2019.00662 – year: 2018 ident: ref40 article-title: Crowdhuman: A benchmark for detecting human in a crowd publication-title: CoRR – ident: ref15 doi: 10.1007/978-3-030-01264-9_48 – ident: ref44 doi: 10.1109/CVPR.2015.7299143 – ident: ref33 doi: 10.1023/A:1008162616689 – start-page: 21 year: 2016 ident: ref25 article-title: SSD: Single shot multibox detector publication-title: Proc Comput Vis - ECCV 2016-14th Eur Conf part I doi: 10.1007/978-3-319-46448-0_2 – ident: ref43 doi: 10.1109/ICCV.2015.221 – ident: ref7 doi: 10.1109/CVPR.2010.5540111 – start-page: 424 year: 2014 ident: ref30 article-title: Local decorrelation for improved pedestrian detection publication-title: Proc Advances Neural Inform Process Syst 27 Annu Conf Neural Inform Process Syst – ident: ref1 doi: 10.1109/ICCV.2017.593 – ident: ref54 doi: 10.1109/TMM.2019.2929005 – start-page: 1195 year: 2017 ident: ref42 article-title: Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results publication-title: Proc Adv Neural Inform Process Syst – ident: ref32 doi: 10.1109/ICCV.2019.00507 – ident: ref27 doi: 10.1109/CVPR.2019.00533 – ident: ref50 doi: 10.1109/CVPR.2015.7298784 – ident: ref52 doi: 10.1109/CVPR.2017.474 – ident: ref2 doi: 10.1109/TPAMI.2019.2897684 – ident: ref47 doi: 10.1109/CVPR.2018.00811 – ident: ref13 doi: 10.1109/CVPR.2018.00378 – ident: ref36 doi: 10.1109/CVPR.2017.690 – ident: ref6 doi: 10.1109/TPAMI.2014.2300479 – ident: ref16 doi: 10.1109/CVPR42600.2020.01188 – ident: ref26 doi: 10.1007/978-3-030-01264-9_38 – ident: ref39 doi: 10.1007/s11263-015-0816-y – ident: ref55 doi: 10.1109/ICCV.2017.377 – ident: ref8 doi: 10.1109/TPAMI.2009.167 – year: 2015 ident: ref17 article-title: Adam: A method for stochastic optimization publication-title: Proc Int Conf Learn Representations San Diego CA USA Conf Track Proc – ident: ref28 doi: 10.1109/CVPR.2017.639 – ident: ref35 doi: 10.1007/978-3-030-01234-2_17 – year: 2020 ident: ref10 article-title: Pedestrian detection: The elephant in the room publication-title: CoRR – ident: ref3 doi: 10.1007/978-3-319-46493-0_22 – ident: ref46 doi: 10.1109/TMM.2018.2829602 – ident: ref56 doi: 10.1007/978-3-030-01246-5_9 – year: 2017 ident: ref34 article-title: Automatic differentiation in PyTorch publication-title: NIPS Autodiff Workshop – ident: ref41 doi: 10.1007/978-3-030-01234-2_33 – start-page: 3258 year: 2012 ident: ref31 article-title: A discriminative deep model for pedestrian detection with occlusion handling publication-title: Proc IEEE Conf Comput Vis Pattern Recognit – start-page: 443 year: 2016 ident: ref49 article-title: Is faster R-CNN doing well for pedestrian detection publication-title: Proc Eur Conf Comput Vis – ident: ref11 doi: 10.1109/CVPR.2016.90 – ident: ref12 doi: 10.1109/CVPR.2017.685 – ident: ref45 doi: 10.1109/CVPR.2018.00719 – ident: ref23 doi: 10.1109/ICCV.2017.324 – start-page: 734 year: 2018 ident: ref18 article-title: Cornernet: Detecting objects as paired keypoints publication-title: Proc Eur Conf Comput Vis – ident: ref9 doi: 10.1109/ICCV.2015.169 – year: 2019 ident: ref57 article-title: Objects as points publication-title: CoRR – ident: ref5 doi: 10.1109/CVPR.2016.350 |
| SSID | ssj0014507 |
| Score | 2.549488 |
| Snippet | Pedestrian detection is an initial step to perform outdoor scene analysis, which plays an essential role in many real-world applications. Although having... |
| SourceID | proquest crossref ieee |
| SourceType | Aggregation Database Enrichment Source Index Database Publisher |
| StartPage | 3085 |
| SubjectTerms | Attribute-aware Detectors Feature extraction non-maximum suppression (nms) Object detection pedestrian detection Proposals Scene analysis Semantics Task analysis Training |
| Title | Attribute-Aware Pedestrian Detection in a Crowd |
| URI | https://ieeexplore.ieee.org/document/9184102 https://www.proquest.com/docview/2575980293 |
| Volume | 23 |
| WOSCitedRecordID | wos000698902000011&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVIEE databaseName: IEEE Electronic Library (IEL) customDbUrl: eissn: 1941-0077 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0014507 issn: 1520-9210 databaseCode: RIE dateStart: 19990101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEB5q8aAHq1WxWmUPXgRjN9t9JMeiFi8tPVTwtiTZCQiySrvVv-8kuy2KInhZ9jCBZSbZmS_z-AAuMQ41Cs6Z0SGyWArNtEwjpopEcU2bxoqabCKbTsXTk5y14HrTC4OIvvgMb9yrz-UXr2blrsoGkuAId5Mjt7IsrXu1NhmDOPGt0eSOQiYJx6xTkqEczCcTAoIR4VN6pJJ_c0GeU-XHj9h7l3Hnf9-1D3tNFBmMarMfQAvLLnTWDA1Bc2C7sPtl3OAhDEZVzW-FbPShFhjMsEDP21EGd1j5oqwyeC4DFdwSOi-O4HF8P799YA1hAjOR5BUzCsm7G14kVvGCk_9DQcaIMsUzK7SykRbREJUuyCWhyVKTDFWYqcTaNBXDeHgM7fK1xBMIZKEdAYRFG8axMVaTpKVgitAOhYRp0oPBWoe5aaaJO1KLl9yjilDmpPXcaT1vtN6Dq82Kt3qSxh-yh07LG7lGwT3or82UN0dtmUeOYlSEFLac_r7qDHYiV4ji70360K4WKzyHbfNePS8XF34XfQL75cM_ |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LaxsxEB5MUkhzSNokJc6re-ilEMWSvA_paPLApbbxwYXcFkk7gkDZBGeT_P2MtGuTklLoZdnDCJYZaWc-zeMD-IYpt6iEYM5yZKlWllmdS2aqzAhLm8arlmyimM3U7a2e9-B83QuDiLH4DC_Ca8zlV_fuKVyVDTTBEREmR25maSp52621zhmkWWyOJofEmSYks0pKcj1YTKcEBSUhVHrkWvzhhCKryrtfcfQvN7v_92WfYKeLI5NRa_jP0MN6D3ZXHA1Jd2T3YPvNwMF9GIyaluEK2ejFLDGZY4WRuaNOrrCJZVl1clcnJrkkfF4dwK-b68XlmHWUCcxJLRrmDJJ_d6LKvBGVIA-IiswhCyMKr6zx0io5RGMrckroitxlQ8MLk3mf52qYDr_ARn1f4yEkurKBAsKj52nqnLck6SmcIrxDQWGe9WGw0mHpunnigdbidxlxBdclab0MWi87rffh-3rFQztL4x-y-0HLa7lOwX04WZmp7A7bYykDyajiFLgc_X3VV9gaL6aTcvJj9vMYPspQlhJvUU5go1k-4Sl8cM_N3ePyLO6oV1GixoY |
| 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=Attribute-Aware+Pedestrian+Detection+in+a+Crowd&rft.jtitle=IEEE+transactions+on+multimedia&rft.au=Zhang%2C+Jialiang&rft.au=Lin%2C+Lixiang&rft.au=Zhu%2C+Jianke&rft.au=Li%2C+Yang&rft.date=2021&rft.pub=IEEE&rft.issn=1520-9210&rft.volume=23&rft.spage=3085&rft.epage=3097&rft_id=info:doi/10.1109%2FTMM.2020.3020691&rft.externalDocID=9184102 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1520-9210&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1520-9210&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1520-9210&client=summon |