2D and 3D object detection algorithms from images: A Survey
Object detection is a crucial branch of computer vision that aims to locate and classify objects in images. Using deep convolutional neural networks (CNNs) as the primary framework for object detection can efficiently extract features, which is closer to real-time performance than the traditional mo...
Uložené v:
| Vydané v: | Array (New York) Ročník 19; s. 100305 |
|---|---|
| Hlavní autori: | , , , |
| Médium: | Journal Article |
| Jazyk: | English |
| Vydavateľské údaje: |
Elsevier Inc
01.09.2023
Elsevier |
| Predmet: | |
| ISSN: | 2590-0056, 2590-0056 |
| On-line prístup: | Získať plný text |
| Tagy: |
Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
|
| Abstract | Object detection is a crucial branch of computer vision that aims to locate and classify objects in images. Using deep convolutional neural networks (CNNs) as the primary framework for object detection can efficiently extract features, which is closer to real-time performance than the traditional model that extracts features manually. In recent years, the rise of Transformer with powerful self-attention mechanisms has further enhanced performance to a new level. However, when it comes to specific vision tasks in the real world, it is necessary to obtain 3D information about the spatial coordinates, orientation, and velocity of objects, which makes research on object detection in 3D scenes more active. Although LiDAR-based 3D object detection algorithms have excellent performance, they are difficult to popularize in practical applications due to their high price. Hence, we summarize the development process, different frameworks, contributions, advantages, disadvantages, and development trends of image-based 2D and 3D object detection algorithms in recent years to help more researchers better understand this field. Besides, representative datasets，evaluation metrics，related techniques and applications are introduced, and some valuable research directions are discussed. |
|---|---|
| AbstractList | Object detection is a crucial branch of computer vision that aims to locate and classify objects in images. Using deep convolutional neural networks (CNNs) as the primary framework for object detection can efficiently extract features, which is closer to real-time performance than the traditional model that extracts features manually. In recent years, the rise of Transformer with powerful self-attention mechanisms has further enhanced performance to a new level. However, when it comes to specific vision tasks in the real world, it is necessary to obtain 3D information about the spatial coordinates, orientation, and velocity of objects, which makes research on object detection in 3D scenes more active. Although LiDAR-based 3D object detection algorithms have excellent performance, they are difficult to popularize in practical applications due to their high price. Hence, we summarize the development process, different frameworks, contributions, advantages, disadvantages, and development trends of image-based 2D and 3D object detection algorithms in recent years to help more researchers better understand this field. Besides, representative datasets，evaluation metrics，related techniques and applications are introduced, and some valuable research directions are discussed. |
| ArticleNumber | 100305 |
| Author | Chen, Wei Tian, Zijian Zhang, Fan Li, Yan |
| Author_xml | – sequence: 1 givenname: Wei surname: Chen fullname: Chen, Wei email: chenwdavior@163.com organization: School of Mechanical, Electrical & Information Engineering, China University of Mining and Technology (Beijing), Beijing, 100083, China – sequence: 2 givenname: Yan surname: Li fullname: Li, Yan email: 18600873522@163.com organization: School of Mechanical, Electrical & Information Engineering, China University of Mining and Technology (Beijing), Beijing, 100083, China – sequence: 3 givenname: Zijian surname: Tian fullname: Tian, Zijian email: Tianzj0726@126.com organization: School of Mechanical, Electrical & Information Engineering, China University of Mining and Technology (Beijing), Beijing, 100083, China – sequence: 4 givenname: Fan surname: Zhang fullname: Zhang, Fan email: zf@cumtb.edu.cn organization: School of Mechanical, Electrical & Information Engineering, China University of Mining and Technology (Beijing), Beijing, 100083, China |
| BookMark | eNqFkMtKLDEQhoMoeH0CN3mBGSvXnj4HF-IdBBfqOlQnlTHNTEfSrTBvb48jIi509RcF30_Vt8-2u9wRY8cCpgKEPWmnWAquphKkGjegwGyxPWlqmAAYu_1t3mVHfd8CgDRCCDPbY__lBccucHXBc9OSH3igYYyUO46LeS5peF72PJa85GmJc-r_8TP-8FreaHXIdiIuejr6zAP2dHX5eH4zubu_vj0_u5t4LfQwwVmMdVMFHbWNFmoljbRaaxssNrGqIZIKGEVTaZrVVaUbMIGs9lA31IBWB-x20xsytu6ljHeUlcuY3Mcil7nDMiS_IGdkpWYoNSkibUEgWJTKkK8CoGzqsUttunzJfV8ofvUJcGudrnUfOt1ap9voHKn6B-XTgGtJQ8G0-IM93bA0KnpLVFzvE3WeQiqj6PGH9Cv_DrJSkXE |
| CitedBy_id | crossref_primary_10_1109_LSP_2024_3402338 crossref_primary_10_1016_j_array_2025_100469 crossref_primary_10_3390_s24144526 crossref_primary_10_1007_s13349_025_00921_1 crossref_primary_10_3390_s25185884 crossref_primary_10_1016_j_engappai_2025_111113 crossref_primary_10_1016_j_sna_2024_116082 crossref_primary_10_3390_s24217007 crossref_primary_10_1109_ACCESS_2025_3599358 crossref_primary_10_1007_s00170_024_13874_4 crossref_primary_10_1016_j_marpetgeo_2024_106965 crossref_primary_10_1016_j_procs_2024_10_282 crossref_primary_10_3390_jmse11091658 crossref_primary_10_32604_cmc_2024_046501 crossref_primary_10_1080_17483107_2025_2530674 crossref_primary_10_1109_ACCESS_2024_3386826 crossref_primary_10_1016_j_eswa_2025_129652 crossref_primary_10_1016_j_patcog_2025_112347 crossref_primary_10_1109_ACCESS_2024_3514673 crossref_primary_10_3390_agriengineering6020065 crossref_primary_10_3390_app14010249 crossref_primary_10_1109_OJVT_2025_3542213 crossref_primary_10_1057_s41599_025_04503_w crossref_primary_10_1109_JSEN_2024_3392918 crossref_primary_10_1109_ACCESS_2024_3484933 crossref_primary_10_1016_j_nexres_2025_100424 crossref_primary_10_1016_j_eswa_2023_122212 crossref_primary_10_1371_journal_pone_0315384 crossref_primary_10_3390_s25175264 crossref_primary_10_1109_ACCESS_2024_3431244 |
| Cites_doi | 10.1007/s11263-013-0620-5 10.1016/j.neunet.2021.12.003 10.1109/TIP.2020.3002345 10.1109/TPAMI.2015.2389824 10.1023/B:VISI.0000029664.99615.94 10.1007/s11263-009-0275-4 10.1109/TPAMI.2017.2706685 10.1109/CVPR46437.2021.00219 10.1109/ICRA40945.2020.9196660 10.1016/j.eswa.2022.116793 10.1109/CVPR.2019.00507 10.1109/ICSP56322.2022.9965335 10.1109/CVPR.2019.00720 10.1109/TPAMI.2016.2577031 10.1007/978-3-319-46448-0_2 10.1109/CVPR.2005.177 |
| ContentType | Journal Article |
| Copyright | 2023 |
| Copyright_xml | – notice: 2023 |
| DBID | 6I. AAFTH AAYXX CITATION DOA |
| DOI | 10.1016/j.array.2023.100305 |
| DatabaseName | ScienceDirect Open Access Titles Elsevier:ScienceDirect:Open Access CrossRef DOAJ Directory of Open Access Journals |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| 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 | Computer Science |
| EISSN | 2590-0056 |
| ExternalDocumentID | oai_doaj_org_article_52738a24e3ee4601a06a235ec7d0a2b9 10_1016_j_array_2023_100305 S2590005623000309 |
| GroupedDBID | 0SF 6I. AAEDW AAFTH AALRI AAXUO AEXQZ AITUG ALMA_UNASSIGNED_HOLDINGS AMRAJ EBS EJD FDB GROUPED_DOAJ M41 M~E NCXOZ OK1 ROL 0R~ AAYWO AAYXX ACVFH ADCNI ADVLN AEUPX AFJKZ AFPUW AIGII AKBMS AKYEP APXCP CITATION |
| ID | FETCH-LOGICAL-c414t-a8ff9b7d4f46f609325264446d6abf790fe3daf1b74e89774b05de64c09beb043 |
| IEDL.DBID | DOA |
| ISICitedReferencesCount | 35 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001043834800001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 2590-0056 |
| IngestDate | Fri Oct 03 12:44:09 EDT 2025 Tue Nov 18 22:34:37 EST 2025 Thu Nov 20 00:39:06 EST 2025 Fri Aug 04 01:17:46 EDT 2023 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | 3D Transformer Image Object detection CNNs |
| Language | English |
| License | This is an open access article under the CC BY license. |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c414t-a8ff9b7d4f46f609325264446d6abf790fe3daf1b74e89774b05de64c09beb043 |
| OpenAccessLink | https://doaj.org/article/52738a24e3ee4601a06a235ec7d0a2b9 |
| ParticipantIDs | doaj_primary_oai_doaj_org_article_52738a24e3ee4601a06a235ec7d0a2b9 crossref_primary_10_1016_j_array_2023_100305 crossref_citationtrail_10_1016_j_array_2023_100305 elsevier_sciencedirect_doi_10_1016_j_array_2023_100305 |
| PublicationCentury | 2000 |
| PublicationDate | September 2023 2023-09-00 2023-09-01 |
| PublicationDateYYYYMMDD | 2023-09-01 |
| PublicationDate_xml | – month: 09 year: 2023 text: September 2023 |
| PublicationDecade | 2020 |
| PublicationTitle | Array (New York) |
| PublicationYear | 2023 |
| Publisher | Elsevier Inc Elsevier |
| Publisher_xml | – name: Elsevier Inc – name: Elsevier |
| References | Qian, Garg, Wang, You, Belongie, Hariharan (bib102) 2020 Liu, Anguelov, Erhan, Szegedy, Reed, Fu (bib13) 2016 Philion, Kar, Fidler (bib174) 2020 Sun, Chen, Xie, Zhang, Jiang, Zhou (bib85) 2020 He, Zhang, Ren, Sun (bib5) 2016 Li, Liang, Wei, Xu, Feng, Yan (bib134) 2017 Shi, Rajkumar (bib129) 2020 Wang, Wang, Dang, Liu, Hu, Yu (bib54) 2022 Liu, Wang, Liu (bib92) 2021 Inoue, Furuta, Yamasaki, Aizawa (bib127) 2018 Liu, Huang, Wang (bib176) 2017 Hasan, Liao, Li, Akram, Shao (bib157) 2022 Yu, Chang, Lv, Xu, Cui, Ji (bib117) 2021 He, Gkioxari, Dollár, Girshick, Mask (bib24) 2017 Chen, Chen, Liu, Wang, Jia (bib122) 2021 Lin, Dollár, Girshick, He, Hariharan, Belongie (bib8) 2017 Yang, Li, Jiang, Gong, Yuan, Zhao (bib121) 2022 Qin, Wang, Lu (bib71) 2019; 33 Chen, Yang, Zhang, Meng, Pan, Sun (bib113) 2019 He, Zhang, Ren, Sun (bib21) 2015; 37 Zhang, Ye, Zhang, Liu, Zhang, Tian (bib161) 2022 Hwang, Benz, Kim (bib159) 2022 Peng, Zhu, Wang, Ma (bib87) 2022 Wang, Zhang, Yang, Sun (bib62) 2022; 36 Liu, Jiang, Zhu, xu (bib162) 2023 Jeong, Park, Kwak (bib33) 2017 Dooley, Wei, Goldstein, Dickerson (bib148) 2022 Simonelli, Bulò, Porzi, Lopez-Antequera, Kontschieder (bib70) 2019 Wang, Min, Ge, Li, Li, Yang (bib108) 2022 Xu, Sun, Yang, Miao, Yang, H2Fa (bib128) 2022 Brazil, Liu (bib74) 2019 Krizhevsky, Sutskever, Hinton (bib4) 2012; 25 Chang, Wang, Yang, Yu, Yu, Xia (bib179) 2022 Redmon, Divvala, Girshick, Farhadi (bib12) 2016 Li, Bao, Ge, Yang, Sun, Li (bib107) 2022 Dai, Jiang, Wu, Bao, Wang, Liu (bib123) 2021 Gilroy, Mullins, Jones, Parsi, Glavin (bib156) 2022 Li, Mao, Girshick, He (bib66) 2022 Shamsolmoali, Zareapoor, Granger, Chanussot, Yang (bib164) 2022 Zhu, Chen, Shen, Savvides (bib49) 2020 Ren, He, Girshick, Sun, Faster (bib23) 2017; 39 Lowe (bib3) 2004; 60 Cai, Vasconcelos (bib25) 2018 Pon, Ku, Li, Waslander (bib99) 2020 Mao, Yang, Dally (bib173) 2019 Roh, Shin, Shin, Kim (bib59) 2021 Chen, Li, Sakaridis, Dai, Gool (bib124) 2018 Cen, Yun, Cai, Wang, Liu (bib182) 2021 Xu, Zhang, Ye, Tan, Yang, Wen (bib101) 2020; 34 Chopra, Khurana (bib20) 2023 Wang, Bashir, Khan, Ullah, Wang, Song (bib163) 2022; 197 Zhou, Zhuo, Krähenbühl (bib45) 2019 Yang, Chen, Tian, Tao, Zhu, Zhang (bib110) 2022 Luo, Dai, Shao, Ding (bib76) 2021 Long, Deng, Wang, Zhang, Dang, Gao (bib30) 2020 Wang, Xie, Li, Fan, Song, Liang (bib64) 2022; vol. 8 Yan, Nie, Cai, Han, Xu, Yang (bib80) 2022 Park, Xu, Yang, Keutzer, Kitani, Tomizuka (bib111) 2022 Deng, Dong, Socher, Li, Kai, Li (bib137) 2009 Najibi, Samangouei, Chellappa, Davis (bib177) 2017 Tian, Shen, Chen, He (bib46) 2019 Chen, Huang, Liu, Yu, Jia (bib90) 2023; 45 Garg, Wang, Hariharan, Weinberger, Chao (bib100) 2020 Zheng, Fu, Zhao (bib34) 2018 Huang, Huang, Zheng, Du (bib105) 2021 Wang, Shrivastava, Gupta (bib133) 2017 Chandio, Gui, Kumar, Ullah, Ranjbarzadeh, Roy (bib37) 2022 Deng, Qi, Najibi, Funkhouser, Zhou, Anguelov (bib175) 2021 Girshick, Fast (bib22) 2015 Chang, Chen (bib88) 2018 Shen, Liao, Nie, Zheng, Zhao (bib81) 2022 Uijlings, van de Sande, Gevers, Smeulders (bib19) 2013; 104 Dosovitskiy, Beyer, Kolesnikov, Weissenborn, Zhai, Unterthiner (bib17) 2020 Fu, Liu, Ranga, Tyagi, Berg (bib32) 2017 You, Wang, Chao, Garg, Pleiss, Hariharan (bib97) 2019 Bochkovskiy, Wang, Liao (bib9) 2020 Law, Teng, Russakovsky, Deng (bib42) 2019 Carion, Massa, Synnaeve, Usunier, Kirillov, Zagoruyko (bib11) 2020; 2020 Muhammad, Romaissa, Oussalah (bib152) 2023 Wang, Yin, Kong, Jiang, Li, Shen (bib95) 2020; 34 Huang, Wang, Lv, Bai, Long, Deng (bib31) 2021 Dosovitskiy, Ros, Codevilla, López, Koltun (bib144) 2017 Dalal, Triggs (bib2) 2005; 1 Girshick, Donahue, Darrell, Malik (bib18) 2014 Wang, Chao, Garg, Hariharan, Weinberger (bib93) 2018 Wang, Yuan, Zhang, Feng (bib119) 2019 Liu, Wu, Tóth (bib77) 2020 Li, Liu, Bai, Lin, Ling (bib169) 2022; 60 Duan, Bai, Xie, Qi, Huang, Tian (bib44) 2019 Man, Weng, Sivakumar, O'Toole, Kitani (bib131) 2021 Wang, Bochkovskiy, Liao (bib28) 2022 Manhardt, Kehl, Gaidon (bib69) 2019 Wang, Li, Wu, Xu, Shen, Yang (bib149) 2023 Li, Ge, Yu, Yang, Wang, Shi (bib106) 2022 Gao, Zheng, Wang, Dai, Li (bib56) 2021 Liang, Wang, Tang, Hu, Ling (bib114) 2021 Xu, Wang, Lv, Chang, Cui, Deng (bib15) 2022 Wang, Yang, Hu, Liang, Urtasun (bib103) 2021 Lu, Ma, Yang, Zhang, Liu, Chu (bib73) 2021 Fang, Huber, Damer (bib154) 2023 Kumar, Brazil, Liu (bib75) 2021 Li, Du, Zhang, Wen, Luo, Wu (bib126) 2020 Everingham, Van Gool, Williams, Winn, Zisserman (bib136) 2010 Bai, Zhang, Ding, Ghanem (bib135) 2018 Lin, Pei, Chen, Zhang, Lu (bib158) 2022 Kong, Li, Wang (bib155) 2023 Guo, Shi, Wang, Li (bib91) 2021 Sun, Cao, Yang, Kitani (bib60) 2021 Zhang, Li, Wang, Lu (bib170) 2020 Liu, Chen, Wang (bib167) 2022 Lin, Maire, Belongie, Hays, Perona, Ramanan (bib138) 2014 Ge, Liu, Wang, Li, Sun (bib51) 2021 Zheng, Gao, Wang, Li, Dong (bib55) 2020 Li, Ouyang, Sheng, Zeng, Wang (bib68) 2019 Dwivedi, Kumar, Chopra, Kothari, Singh (bib153) 2023 Li, Ku, Waslander (bib98) 2020 Zou, Wu, Zhou, Huang (bib52) 2022 Dai, Chang, Savva, Halber, Funkhouser, Nießner (bib145) 2017 Chen, Wang, Yang, Zhang, Cheng, Sun (bib10) 2021 Zhang, Lu, Zhou (bib78) 2021 Ye, Wang, Zhou, Lei, Fan, Qin (bib166) 2023 Philion, Fidler (bib104) 2020 Sun, Kretzschmar, Dotiwalla, Chouard, Patnaik, Tsui (bib141) 2020 Rashwan, Kalra, Poupart (bib43) 2019 Law, Deng (bib41) 2018 Hinton, Vinyals, Dean (bib118) 2015 Joseph, Khan, Khan, Balasubramanian (bib180) 2021 Dai, Li, He, Sun (bib14) 2016 Yi, Wu, Metaxas (bib36) 2019 Qin, Wang, Lu (bib84) 2019 Yang, Wang (bib35) 2019 Zhu, He, Savvides (bib47) 2019 Zhu, Su, Lu, Li, Wang, Dai (bib58) 2020 Liu, Lin, Cao, Hu, Wei, Zhang (bib6) 2021 Guo, Han, Wang, Zhang, Yang, Wu (bib116) 2020 Liu, Li, Zhang, Yang, Qi, Su (bib61) 2022 Ghiasi, Lin, Le (bib115) 2019 Weng, Man, Cheng, Park, O'Toole, Kitani (bib143) 2020 Lin, Sun, Liu, Bian, Cen, Zhou (bib168) 2022 Li, Li, Jiang, Weng, Geng, Li (bib53) 2022 Zong, Jiang, Song, Xue, Su, Li (bib112) 2023 Wang, Zhu, Pang, Lin (bib79) 2021 Liu, Anguelov, Erhan, Szegedy, Reed, Fu (bib178) 2016 Nie, Anwer, Cholakkal, Khan, Pang, Shao (bib40) 2019 Chen, Kundu, Zhu, Ma, Fidler, Urtasun (bib82) 2018; 40 Beal, Kim, Tzeng, Park, Zhai, Kislyuk (bib63) 2020 Piland, Czajka, Sweet (bib151) 2023 Bai, Xia (bib172) 2022; 1 Qiu, Li, Wu, Cui, Song, Wang (bib50) 2021 Guo, Han, Wang, Wu, Chen, Xu (bib120) 2021 Krasin, Duerig, Alldrin, Veit, Abu-El-Haija, Belongie (bib139) 2016 Yan, Wan, Zhang (bib165) 2022; 2023 Redmon, Farhadi (bib26) 2017 Song, Lichtenberg, Xiao, Sun (bib146) 2015 Wu, Zhao, Zhang (bib16) 2021 Silberman, Hoiem, Kohli, Fergus (bib147) 2012 Shuvo (bib171) 2023 Chen, Liu, Shen, Jia (bib89) 2020 Peng, Pan, Liu, Sun (bib86) 2020 Ansari, Meraz, Chakraborty, Javed (bib132) 2022 Kong, Sun, Liu, Jiang, Li, Shi (bib48) 2020; 29 Zhu, Pang, Yang, Shi, Lin (bib125) 2019 Ye, Du, Shi, Li, Tan, Feng (bib96) 2020 Gupta, Narayan, Joseph, Khan, Khan, Shah (bib181) 2022 Zheng, Li, Hong, Petersson, Barnes (bib183) 2022 Geiger, Lenz, Urtasun (bib140) 2012 Shi, Ye, Chen, Chen, Chen, Kim (bib72) 2021 Li, Wang, Li, Xie, Sima, Lu (bib109) 2022 Wang, Xie, Li, Fan, Song, Liang (bib7) 2021 Jocher (bib29) 2020 Lin, Goyal, Girshick, He, Dollár (bib38) 2017 Zhang, Wen, Bian, Lei, Li (bib39) 2018 Boyd, Tinsley, Bowyer, Czajka (bib150) 2021 Li, Chen, Shen (bib83) 2019 Lienhart, Maydt (bib1) 2002 Redmon, Farhadi (bib27) 2018 Ma, Wang, Li, Zhang, Ouyang, Fan (bib94) 2019 Vora, Dutta, Jain, Karthik, Gandhi (bib160) 2023 Najibi, Lai, Kundu, Lu, Rathod, Funkhouser (bib130) 2020 Caesar, Bankiti, Lang, Vora, Liong, Xu (bib142) 2020 Chen, Kundu, Zhang, Ma, Fidler, Urtasun (bib67) 2016 Dai, Chen, Yang, Zhang, Yuan, Zhang (bib57) 2021 Liu, Hu, Lin, Yao, Xie, Wei (bib65) 2021 Lu (10.1016/j.array.2023.100305_bib73) 2021 Long (10.1016/j.array.2023.100305_bib30) 2020 Yang (10.1016/j.array.2023.100305_bib121) 2022 Uijlings (10.1016/j.array.2023.100305_bib19) 2013; 104 Song (10.1016/j.array.2023.100305_bib146) 2015 Dosovitskiy (10.1016/j.array.2023.100305_bib144) 2017 Gao (10.1016/j.array.2023.100305_bib56) 2021 Philion (10.1016/j.array.2023.100305_bib174) 2020 Li (10.1016/j.array.2023.100305_bib68) 2019 Tian (10.1016/j.array.2023.100305_bib46) 2019 Redmon (10.1016/j.array.2023.100305_bib26) 2017 Dooley (10.1016/j.array.2023.100305_bib148) 2022 Li (10.1016/j.array.2023.100305_bib134) 2017 Chen (10.1016/j.array.2023.100305_bib67) 2016 Shi (10.1016/j.array.2023.100305_bib72) 2021 Liu (10.1016/j.array.2023.100305_bib162) 2023 Liu (10.1016/j.array.2023.100305_bib178) 2016 Chen (10.1016/j.array.2023.100305_bib82) 2018; 40 Yu (10.1016/j.array.2023.100305_bib117) 2021 Shen (10.1016/j.array.2023.100305_bib81) 2022 Peng (10.1016/j.array.2023.100305_bib86) 2020 Li (10.1016/j.array.2023.100305_bib126) 2020 Fang (10.1016/j.array.2023.100305_bib154) 2023 Huang (10.1016/j.array.2023.100305_bib31) 2021 Weng (10.1016/j.array.2023.100305_bib143) 2020 Law (10.1016/j.array.2023.100305_bib41) 2018 Philion (10.1016/j.array.2023.100305_bib104) 2020 Yan (10.1016/j.array.2023.100305_bib80) 2022 Chopra (10.1016/j.array.2023.100305_bib20) 2023 Kumar (10.1016/j.array.2023.100305_bib75) 2021 Zhang (10.1016/j.array.2023.100305_bib78) 2021 Xu (10.1016/j.array.2023.100305_bib128) 2022 Lienhart (10.1016/j.array.2023.100305_bib1) 2002 Deng (10.1016/j.array.2023.100305_bib137) 2009 Li (10.1016/j.array.2023.100305_bib98) 2020 Li (10.1016/j.array.2023.100305_bib109) 2022 Dwivedi (10.1016/j.array.2023.100305_bib153) 2023 Lowe (10.1016/j.array.2023.100305_bib3) 2004; 60 He (10.1016/j.array.2023.100305_bib5) 2016 Zhu (10.1016/j.array.2023.100305_bib58) 2020 Liu (10.1016/j.array.2023.100305_bib92) 2021 Li (10.1016/j.array.2023.100305_bib106) 2022 Boyd (10.1016/j.array.2023.100305_bib150) 2021 Zhu (10.1016/j.array.2023.100305_bib125) 2019 Zhang (10.1016/j.array.2023.100305_bib161) 2022 Ansari (10.1016/j.array.2023.100305_bib132) 2022 Li (10.1016/j.array.2023.100305_bib107) 2022 Zhang (10.1016/j.array.2023.100305_bib39) 2018 Ma (10.1016/j.array.2023.100305_bib94) 2019 Guo (10.1016/j.array.2023.100305_bib120) 2021 Dai (10.1016/j.array.2023.100305_bib123) 2021 Caesar (10.1016/j.array.2023.100305_bib142) 2020 Girshick (10.1016/j.array.2023.100305_bib18) 2014 Li (10.1016/j.array.2023.100305_bib83) 2019 Li (10.1016/j.array.2023.100305_bib169) 2022; 60 Jocher (10.1016/j.array.2023.100305_bib29) 2020 Chen (10.1016/j.array.2023.100305_bib124) 2018 Wang (10.1016/j.array.2023.100305_bib133) 2017 Shi (10.1016/j.array.2023.100305_bib129) 2020 Zhang (10.1016/j.array.2023.100305_bib170) 2020 Qiu (10.1016/j.array.2023.100305_bib50) 2021 Rashwan (10.1016/j.array.2023.100305_bib43) 2019 Geiger (10.1016/j.array.2023.100305_bib140) 2012 Liu (10.1016/j.array.2023.100305_bib167) 2022 Luo (10.1016/j.array.2023.100305_bib76) 2021 Wang (10.1016/j.array.2023.100305_bib28) 2022 Guo (10.1016/j.array.2023.100305_bib91) 2021 Nie (10.1016/j.array.2023.100305_bib40) 2019 Inoue (10.1016/j.array.2023.100305_bib127) 2018 Sun (10.1016/j.array.2023.100305_bib141) 2020 Girshick (10.1016/j.array.2023.100305_bib22) 2015 Hwang (10.1016/j.array.2023.100305_bib159) 2022 Zou (10.1016/j.array.2023.100305_bib52) 2022 Roh (10.1016/j.array.2023.100305_bib59) 2021 Shuvo (10.1016/j.array.2023.100305_bib171) 2023 Cai (10.1016/j.array.2023.100305_bib25) 2018 Joseph (10.1016/j.array.2023.100305_bib180) 2021 Ye (10.1016/j.array.2023.100305_bib166) 2023 Qin (10.1016/j.array.2023.100305_bib84) 2019 Garg (10.1016/j.array.2023.100305_bib100) 2020 Li (10.1016/j.array.2023.100305_bib53) 2022 Liu (10.1016/j.array.2023.100305_bib65) 2021 Zheng (10.1016/j.array.2023.100305_bib55) 2020 Yan (10.1016/j.array.2023.100305_bib165) 2022; 2023 Wang (10.1016/j.array.2023.100305_bib64) 2022; vol. 8 Beal (10.1016/j.array.2023.100305_bib63) 2020 Dosovitskiy (10.1016/j.array.2023.100305_bib17) 2020 Dalal (10.1016/j.array.2023.100305_bib2) 2005; 1 Guo (10.1016/j.array.2023.100305_bib116) 2020 Yi (10.1016/j.array.2023.100305_bib36) 2019 Chen (10.1016/j.array.2023.100305_bib113) 2019 Liu (10.1016/j.array.2023.100305_bib77) 2020 Sun (10.1016/j.array.2023.100305_bib85) 2020 Dai (10.1016/j.array.2023.100305_bib14) 2016 Krasin (10.1016/j.array.2023.100305_bib139) 2016 Liu (10.1016/j.array.2023.100305_bib6) 2021 Lin (10.1016/j.array.2023.100305_bib138) 2014 Kong (10.1016/j.array.2023.100305_bib155) 2023 Bai (10.1016/j.array.2023.100305_bib172) 2022; 1 Law (10.1016/j.array.2023.100305_bib42) 2019 Carion (10.1016/j.array.2023.100305_bib11) 2020; 2020 Hinton (10.1016/j.array.2023.100305_bib118) 2015 Wang (10.1016/j.array.2023.100305_bib62) 2022; 36 Wang (10.1016/j.array.2023.100305_bib149) 2023 Najibi (10.1016/j.array.2023.100305_bib130) 2020 Chen (10.1016/j.array.2023.100305_bib122) 2021 Man (10.1016/j.array.2023.100305_bib131) 2021 Lin (10.1016/j.array.2023.100305_bib8) 2017 Wang (10.1016/j.array.2023.100305_bib119) 2019 Everingham (10.1016/j.array.2023.100305_bib136) 2010 Ghiasi (10.1016/j.array.2023.100305_bib115) 2019 Wang (10.1016/j.array.2023.100305_bib7) 2021 Mao (10.1016/j.array.2023.100305_bib173) 2019 Bai (10.1016/j.array.2023.100305_bib135) 2018 Dai (10.1016/j.array.2023.100305_bib57) 2021 Li (10.1016/j.array.2023.100305_bib66) 2022 Dai (10.1016/j.array.2023.100305_bib145) 2017 Chen (10.1016/j.array.2023.100305_bib10) 2021 Zhu (10.1016/j.array.2023.100305_bib49) 2020 Ren (10.1016/j.array.2023.100305_bib23) 2017; 39 Redmon (10.1016/j.array.2023.100305_bib27) 2018 Wu (10.1016/j.array.2023.100305_bib16) 2021 Lin (10.1016/j.array.2023.100305_bib168) 2022 Redmon (10.1016/j.array.2023.100305_bib12) 2016 Park (10.1016/j.array.2023.100305_bib111) 2022 Piland (10.1016/j.array.2023.100305_bib151) 2023 You (10.1016/j.array.2023.100305_bib97) 2019 Deng (10.1016/j.array.2023.100305_bib175) 2021 Liang (10.1016/j.array.2023.100305_bib114) 2021 Sun (10.1016/j.array.2023.100305_bib60) 2021 Wang (10.1016/j.array.2023.100305_bib93) 2018 He (10.1016/j.array.2023.100305_bib24) 2017 Liu (10.1016/j.array.2023.100305_bib13) 2016 Wang (10.1016/j.array.2023.100305_bib79) 2021 Zhu (10.1016/j.array.2023.100305_bib47) 2019 Yang (10.1016/j.array.2023.100305_bib110) 2022 Hasan (10.1016/j.array.2023.100305_bib157) 2022 Wang (10.1016/j.array.2023.100305_bib103) 2021 Jeong (10.1016/j.array.2023.100305_bib33) 2017 Zheng (10.1016/j.array.2023.100305_bib34) 2018 Wang (10.1016/j.array.2023.100305_bib95) 2020; 34 Silberman (10.1016/j.array.2023.100305_bib147) 2012 Gupta (10.1016/j.array.2023.100305_bib181) 2022 Xu (10.1016/j.array.2023.100305_bib15) 2022 Chen (10.1016/j.array.2023.100305_bib90) 2023; 45 Liu (10.1016/j.array.2023.100305_bib176) 2017 Cen (10.1016/j.array.2023.100305_bib182) 2021 Bochkovskiy (10.1016/j.array.2023.100305_bib9) 2020 Chandio (10.1016/j.array.2023.100305_bib37) 2022 Liu (10.1016/j.array.2023.100305_bib61) 2022 Pon (10.1016/j.array.2023.100305_bib99) 2020 Chang (10.1016/j.array.2023.100305_bib88) 2018 Vora (10.1016/j.array.2023.100305_bib160) 2023 Yang (10.1016/j.array.2023.100305_bib35) 2019 Qian (10.1016/j.array.2023.100305_bib102) 2020 Ge (10.1016/j.array.2023.100305_bib51) 2021 Najibi (10.1016/j.array.2023.100305_bib177) 2017 He (10.1016/j.array.2023.100305_bib21) 2015; 37 Gilroy (10.1016/j.array.2023.100305_bib156) 2022 Huang (10.1016/j.array.2023.100305_bib105) 2021 Shamsolmoali (10.1016/j.array.2023.100305_bib164) 2022 Simonelli (10.1016/j.array.2023.100305_bib70) 2019 Manhardt (10.1016/j.array.2023.100305_bib69) 2019 Xu (10.1016/j.array.2023.100305_bib101) 2020; 34 Kong (10.1016/j.array.2023.100305_bib48) 2020; 29 Zheng (10.1016/j.array.2023.100305_bib183) 2022 Wang (10.1016/j.array.2023.100305_bib163) 2022; 197 Fu (10.1016/j.array.2023.100305_bib32) 2017 Ye (10.1016/j.array.2023.100305_bib96) 2020 Chang (10.1016/j.array.2023.100305_bib179) 2022 Muhammad (10.1016/j.array.2023.100305_bib152) 2023 Qin (10.1016/j.array.2023.100305_bib71) 2019; 33 Duan (10.1016/j.array.2023.100305_bib44) 2019 Lin (10.1016/j.array.2023.100305_bib158) 2022 Lin (10.1016/j.array.2023.100305_bib38) 2017 Brazil (10.1016/j.array.2023.100305_bib74) 2019 Wang (10.1016/j.array.2023.100305_bib108) 2022 Zong (10.1016/j.array.2023.100305_bib112) 2023 Wang (10.1016/j.array.2023.100305_bib54) 2022 Zhou (10.1016/j.array.2023.100305_bib45) 2019 Peng (10.1016/j.array.2023.100305_bib87) 2022 Chen (10.1016/j.array.2023.100305_bib89) 2020 Krizhevsky (10.1016/j.array.2023.100305_bib4) 2012; 25 |
| References_xml | – volume: 2020 start-page: 213 year: 2020 end-page: 229 ident: bib11 article-title: End-to-End object detection with transformers publication-title: Computer Vision – ECCV – start-page: 11402 year: 2020 end-page: 11411 ident: bib116 article-title: Hit-detector: hierarchical trinity architecture search for object detection publication-title: 2020 IEEE/CVF conference on computer vision and pattern recognition (CVPR) – start-page: 2968 year: 2021 end-page: 2977 ident: bib57 article-title: Dynamic DETR: end-to-end object detection with dynamic attention publication-title: 2021 IEEE/CVF international conference on computer vision (ICCV) – start-page: 1 year: 2022 ident: bib158 article-title: Pedestrian detection by exemplar-guided contrastive learning publication-title: IEEE Trans Image Process – start-page: 567 year: 2015 end-page: 576 ident: bib146 article-title: A RGB-D scene understanding benchmark suite publication-title: 2015 IEEE conference on computer vision and pattern recognition (CVPR) – year: 2021 ident: bib150 article-title: CYBORG: blending human saliency into the loss improves deep learning – year: 2021 ident: bib65 article-title: Swin transformer V2: scaling up capacity and resolution – start-page: 225 year: 2022 end-page: 234 ident: bib87 article-title: SIDE: center-based stereo 3D detector with structure-aware instance depth estimation publication-title: 2022 IEEE/CVF winter conference on applications of computer vision (WACV) – volume: vol. 8 start-page: 1 year: 2022 end-page: 10 ident: bib64 publication-title: PVT v2: improved baselines with pyramid vision transformer – year: 2020 ident: bib100 article-title: Wasserstein distances for stereo disparity estimation – start-page: 8383 year: 2020 end-page: 8389 ident: bib99 article-title: Object-centric stereo matching for 3D object detection publication-title: 2020 IEEE International Conference on Robotics and Automation (ICRA) – start-page: 746 year: 2012 end-page: 760 ident: bib147 article-title: Indoor segmentation and support inference from RGBD images publication-title: Computer vision – ECCV 2012 – year: 2023 ident: bib155 article-title: Enhancing general face forgery detection via vision transformer with low-rank adaptation – start-page: 3339 year: 2018 end-page: 3348 ident: bib124 article-title: Domain adaptive faster R-CNN for object detection in the wild publication-title: 2018 IEEE/CVF conference on computer vision and pattern recognition – start-page: 4885 year: 2017 end-page: 4894 ident: bib177 article-title: SSH: single stage headless face detector publication-title: 2017 IEEE international conference on computer vision (ICCV) – start-page: 913 year: 2021 end-page: 922 ident: bib79 article-title: FCOS3D: fully convolutional one-stage monocular 3D object detection publication-title: IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)2021 – start-page: 1 year: 2022 end-page: 18 ident: bib109 article-title: BEVFormer: learning bird’s-eye-view representation from multi-camera images via spatiotemporal transformers – start-page: 573 year: 2019 end-page: 582 ident: bib173 article-title: A delay metric for video object detection: what average precision fails to tell publication-title: 2019 IEEE/CVF international conference on computer vision (ICCV) – start-page: 58 year: 2023 end-page: 73 ident: bib20 article-title: Support vector machine – start-page: 3091 year: 2021 end-page: 3101 ident: bib73 article-title: Geometry uncertainty projection network for monocular 3D object detection publication-title: 2021 IEEE/CVF international conference on computer vision (ICCV) – year: 2021 ident: bib175 article-title: Revisiting 3D object detection from an egocentric perspective – volume: 40 start-page: 1259 year: 2018 end-page: 1272 ident: bib82 article-title: 3D object proposals using stereo imagery for accurate object class detection publication-title: IEEE Trans Pattern Anal Mach Intell – start-page: 4928 year: 2019 end-page: 4937 ident: bib119 article-title: Distilling object detectors with fine-grained feature imitation publication-title: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) – start-page: 4203 year: 2018 end-page: 4212 ident: bib39 article-title: Single-shot refinement neural network for object detection publication-title: 2018 IEEE/CVF conference on computer vision and pattern recognition – year: 2020 ident: bib143 article-title: All-in-one drive: a large-scale comprehensive perception dataset with high-density long-range point clouds – year: 2017 ident: bib33 article-title: Enhancement of SSD by concatenating feature maps for object detection – start-page: 11618 year: 2020 end-page: 11628 ident: bib142 article-title: nuScenes: a multimodal dataset for autonomous driving publication-title: 2020 IEEE/CVF conference on computer vision and pattern recognition (CVPR) – year: 2022 ident: bib37 article-title: Precise single-stage detector – start-page: 13012 year: 2020 end-page: 13021 ident: bib86 article-title: IDA-3D: instance-depth-aware 3D object detection from stereo vision for autonomous driving publication-title: 2020 IEEE/CVF conference on computer vision and pattern recognition (CVPR) – start-page: 5001 year: 2018 end-page: 5009 ident: bib127 article-title: Cross-domain weakly-supervised object detection through progressive domain adaptation publication-title: IEEE/CVF conference on computer vision and pattern Recognition2018 – volume: 104 start-page: 154 year: 2013 end-page: 171 ident: bib19 article-title: Selective search for object recognition publication-title: Int J Comput Vis – start-page: 2025 year: 2019 end-page: 2028 ident: bib43 article-title: Matrix nets: a new deep architecture for object detection publication-title: 2019 IEEE/CVF international conference on computer vision workshop (ICCVW) – year: 2023 ident: bib112 article-title: Temporal enhanced training of multi-view 3D object detector via historical object prediction – year: 2022 ident: bib15 article-title: PP-YOLOE: an evolved version of YOLO – start-page: 3133 year: 2021 end-page: 3143 ident: bib91 article-title: LIGA-stereo: learning LiDAR geometry aware representations for stereo-based 3D detector publication-title: 2021 IEEE/CVF international conference on computer vision (ICCV) – start-page: 3288 year: 2021 end-page: 3297 ident: bib78 article-title: Objects are different: flexible monocular 3D object detection publication-title: 2021 IEEE/CVF conference on computer vision and pattern recognition (CVPR) – start-page: 25 year: 2022 end-page: 36 ident: bib168 article-title: Attention guided network for salient object detection in optical remote sensing images publication-title: Artificial Neural Networks and Machine Learning – ICANN – start-page: 2999 year: 2017 end-page: 3007 ident: bib38 article-title: Focal loss for dense object detection publication-title: 2017 IEEE international conference on computer vision (ICCV) – start-page: 7029 year: 2019 end-page: 7038 ident: bib115 article-title: NAS-FPN: learning scalable feature pyramid architecture for object detection publication-title: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) – start-page: 8969 year: 2021 end-page: 8979 ident: bib75 article-title: GrooMeD-NMS: grouped mathematically differentiable NMS for monocular 3D object detection publication-title: 2021 IEEE/CVF conference on computer vision and pattern recognition (CVPR) – start-page: 2766 year: 2019 end-page: 2770 ident: bib35 article-title: Feature fusion and enhancement for single shot multibox detector. 2019 Chinese automation congress – start-page: I year: 2002 ident: bib1 article-title: An extended set of Haar-like features for rapid object detection publication-title: Proceedings international conference on image processing – start-page: 17122 year: 2022 end-page: 17131 ident: bib80 article-title: ONCE-3DLanes: building monocular 3D lane detection publication-title: 2022 IEEE/CVF conference on computer vision and pattern recognition (CVPR) – year: 2021 ident: bib51 article-title: YOLOX: exceeding YOLO series in 2021 – start-page: 526 year: 2022 end-page: 543 ident: bib179 article-title: RFLA: Gaussian receptive field based label assignment for tiny object detection – start-page: 15152 year: 2021 end-page: 15161 ident: bib72 article-title: Geometry-based distance decomposition for monocular 3D object detection publication-title: IEEE/CVF international conference on computer vision (ICCV)2021 – start-page: 840 year: 2019 end-page: 849 ident: bib47 article-title: Feature selective anchor-free module for single-shot object detection publication-title: 2019 IEEE/CVF conference on computer vision and pattern recognition (CVPR) – year: 2022 ident: bib54 article-title: PP-YOLOE-R: an efficient anchor-free rotated object detector – year: 2021 ident: bib105 article-title: BEVDet: high-performance multi-camera 3D object detection in bird-eye-view – start-page: 1019 year: 2019 end-page: 1028 ident: bib68 article-title: An efficient 3D object detection framework for autonomous driving publication-title: 2019 IEEE/CVF conference on computer vision and pattern recognition (CVPR) – year: 2022 ident: bib167 article-title: LSNet: extremely light-weight siamese network for change detection in remote sensing image – year: 2018 ident: bib93 article-title: Pseudo-LiDAR from visual depth estimation: bridging the gap in 3D object detection for autonomous driving – volume: 37 start-page: 1904 year: 2015 end-page: 1916 ident: bib21 article-title: Spatial pyramid pooling in deep convolutional networks for visual recognition publication-title: IEEE Trans Pattern Anal Mach Intell – year: 2021 ident: bib117 article-title: PP-PicoDet: a better real-time object detector on mobile devices – year: 2023 ident: bib154 article-title: SynthASpoof: developing face presentation attack detection based on privacy-friendly synthetic data – start-page: 850 year: 2019 end-page: 859 ident: bib45 article-title: Bottom-up object detection by grouping extreme and center points publication-title: 2019 IEEE/CVF conference on computer vision and pattern recognition (CVPR) – year: 2019 ident: bib113 article-title: DetNAS: neural architecture search on object detection – volume: 33 start-page: 8851 year: 2019 end-page: 8858 ident: bib71 article-title: MonoGRNet: a geometric reasoning network for monocular 3D object localization publication-title: Proc AAAI Conf Artif Intell – start-page: 4339 year: 2021 end-page: 4348 ident: bib122 article-title: Deep structured instance graph for distilling object detectors publication-title: IEEE/CVF international conference on computer vision (ICCV)2021 – start-page: 9536 year: 2019 end-page: 9545 ident: bib40 article-title: Enriched feature guided refinement network for object detection publication-title: 2019 IEEE/CVF international conference on computer vision (ICCV) – start-page: 248 year: 2009 end-page: 255 ident: bib137 article-title: ImageNet: a large-scale hierarchical image database publication-title: 2009 IEEE conference on computer vision and pattern recognition – volume: 36 start-page: 2567 year: 2022 end-page: 2575 ident: bib62 article-title: Anchor DETR: query design for transformer-based detector publication-title: Proc AAAI Conf Artif Intell – year: 2023 ident: bib171 article-title: An automated end-to-end deep learning-based framework for lung cancer diagnosis by detecting and classifying the lung nodules – start-page: 779 year: 2016 end-page: 788 ident: bib12 article-title: You only look once: unified, real-time object detection publication-title: 2016 IEEE conference on computer vision and pattern recognition (CVPR) – start-page: 4633 year: 2022 end-page: 4642 ident: bib121 article-title: Focal and global knowledge distillation for detectors publication-title: 2022 IEEE/CVF conference on computer vision and pattern recognition (CVPR) – year: 2018 ident: bib27 article-title: YOLOv3: an incremental improvement – start-page: 7636 year: 2019 end-page: 7644 ident: bib83 article-title: Stereo R-CNN based 3D object detection for autonomous driving publication-title: 2019 IEEE/CVF conference on computer vision and pattern recognition (CVPR) – year: 2021 ident: bib59 article-title: Sparse DETR: efficient end-to-end object detection with learnable sparsity – start-page: 9286 year: 2019 end-page: 9295 ident: bib74 article-title: M3D-RPN: monocular 3D region proposal network for object detection publication-title: 2019 IEEE/CVF international conference on computer vision (ICCV) – year: 2016 ident: bib14 article-title: Object detection via region-based fully convolutional networks – start-page: 5880 year: 2020 end-page: 5889 ident: bib102 article-title: End-to-End pseudo-LiDAR for image-based 3D object detection publication-title: 2020 IEEE/CVF conference on computer vision and pattern recognition (CVPR) – volume: 60 start-page: 1 year: 2022 end-page: 12 ident: bib169 article-title: Lightweight salient object detection in optical remote sensing images via feature correlation publication-title: IEEE Trans Geosci Rem Sens – start-page: 869 year: 2021 end-page: 878 ident: bib182 article-title: Open-set 3D object detection publication-title: International Conference on 3D Vision – year: 2019 ident: bib97 article-title: Pseudo-LiDAR++: accurate depth for 3D object detection in autonomous driving – start-page: 6517 year: 2017 end-page: 6525 ident: bib26 article-title: YOLO9000: better, faster, stronger. 2017 IEEE conference on computer vision and pattern recognition (CVPR) – start-page: 3601 year: 2021 end-page: 3610 ident: bib56 article-title: Fast convergence of DETR with spatially modulated Co-attention publication-title: 2021 IEEE/CVF international conference on computer vision (ICCV) – year: 2022 ident: bib106 article-title: BEVDepth: acquisition of reliable depth for multi-view 3D object detection – start-page: 2154 year: 2021 end-page: 2164 ident: bib120 article-title: Distilling object detectors via decoupled features publication-title: 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) – start-page: 3591 year: 2021 end-page: 3600 ident: bib60 article-title: Rethinking transformer-based set prediction for object detection publication-title: 2021 IEEE/CVF international conference on computer vision (ICCV) – year: 2023 ident: bib153 article-title: An efficient ensemble explainable AI (XAI) approach for morphed face detection – start-page: 11910 year: 2020 end-page: 11919 ident: bib130 article-title: DOPS: learning to detect 3D objects and predict their 3D shapes publication-title: 2020 IEEE/CVF conference on computer vision and pattern recognition (CVPR) – start-page: 6154 year: 2018 end-page: 6162 ident: bib25 article-title: Cascade R-CNN: delving into high quality object detection publication-title: 2018 IEEE/CVF conference on computer vision and pattern recognition – start-page: 7838 year: 2021 end-page: 7847 ident: bib123 article-title: General instance distillation for object detection publication-title: 2021 IEEE/CVF conference on computer vision and pattern recognition (CVPR) – year: 2022 ident: bib161 article-title: Feature calibration network for occluded pedestrian detection – volume: 45 start-page: 4416 year: 2023 end-page: 4429 ident: bib90 article-title: DSGN++: exploiting visual-spatial relation for stereo-based 3D detectors publication-title: IEEE Trans Pattern Anal Mach Intell – start-page: 110 year: 2023 end-page: 119 ident: bib160 article-title: Bringing generalization to deep multi-view pedestrian detection – start-page: 195 year: 2022 end-page: 211 ident: bib81 article-title: PanoFormer: panorama transformer for indoor 360$$^{\circ }$$ depth estimation – year: 2017 ident: bib176 article-title: Receptive field block net for accurate and Fast object detection – start-page: 9992 year: 2021 end-page: 10002 ident: bib6 article-title: Swin transformer: hierarchical vision transformer using shifted windows publication-title: 2021 IEEE/CVF international conference on computer vision (ICCV) – year: 2016 ident: bib139 article-title: OpenImages: a public dataset for large-scale multi-label and multi-class image classification – year: 2023 ident: bib152 article-title: Domain generalization via ensemble stacking for face presentation attack detection – start-page: 936 year: 2017 end-page: 944 ident: bib8 article-title: Feature pyramid networks for object detection publication-title: 2017 IEEE conference on computer vision and pattern recognition (CVPR) – start-page: 1708 year: 2020 end-page: 1716 ident: bib129 article-title: Point-GNN: graph neural network for 3D object detection in a point cloud publication-title: 2020 IEEE/CVF conference on computer vision and pattern recognition (CVPR) – year: 2020 ident: bib85 article-title: Disp R-CNN: stereo 3D object detection via shape prior guided instance disparity estimation – year: 2022 ident: bib148 article-title: Robustness disparities in face detection – volume: 2023 start-page: 75 year: 2022 end-page: 92 ident: bib165 article-title: Fully transformer network for change detection of remote sensing images publication-title: Computer Vision – ACCV – volume: 39 start-page: 1137 year: 2017 end-page: 1149 ident: bib23 article-title: Towards real-time object detection with region proposal networks publication-title: IEEE Trans Pattern Anal Mach Intell – start-page: 770 year: 2016 end-page: 778 ident: bib5 article-title: Deep residual learning for image recognition publication-title: 2016 IEEE conference on computer vision and pattern recognition (CVPR) – start-page: 580 year: 2014 end-page: 587 ident: bib18 article-title: Rich feature hierarchies for accurate object detection and semantic segmentation publication-title: 2014 IEEE conference on computer vision and pattern recognition – volume: 34 start-page: 12257 year: 2020 end-page: 12264 ident: bib95 article-title: Task-aware monocular depth estimation for 3D object detection publication-title: Proc AAAI Conf Artif Intell – start-page: 765 year: 2018 end-page: 781 ident: bib41 article-title: CornerNet: detecting objects as paired keypoints publication-title: Computer vision – ECCV 2018 – year: 2022 ident: bib111 article-title: Time will tell: new outlooks and A baseline for temporal multi-view 3D object detection – year: 2022 ident: bib164 article-title: Enhanced single-shot detector for small object detection in remote sensing images – year: 2017 ident: bib32 article-title: Dssd : deconvolutional single shot detector – year: 2017 ident: bib133 article-title: A-Fast-RCNN: hard positive generation via adversary for object detection – start-page: 1951 year: 2017 end-page: 1959 ident: bib134 article-title: Perceptual generative adversarial networks for small object detection publication-title: 2017 IEEE conference on computer vision and pattern recognition (CVPR) – year: 2020 ident: bib30 article-title: PP-YOLO: an effective and efficient implementation of object detector – year: 2022 ident: bib52 article-title: YOLOX-PAI: an improved YOLOX version by PAI – start-page: 481 year: 2020 end-page: 497 ident: bib126 article-title: Spatial attention pyramid network for unsupervised domain adaptation publication-title: Computer vision – ECCV 2020 – start-page: 7607 year: 2019 end-page: 7615 ident: bib84 article-title: Triangulation learning network: from monocular to stereo 3D object detection publication-title: 2019 IEEE/CVF conference on computer vision and pattern recognition (CVPR) – year: 2020 ident: bib58 article-title: Deformable DETR: deformable transformers for end-to-end object detection – start-page: 280 year: 2022 end-page: 296 ident: bib66 article-title: Exploring Plain vision transformer backbones for object detection – year: 2023 ident: bib151 article-title: Improving model's focus improves performance of deep learning-based synthetic face detectors – start-page: 17 year: 2020 end-page: 34 ident: bib96 article-title: Monocular 3D object detection via feature domain adaptation – start-page: 21 year: 2016 end-page: 37 ident: bib13 article-title: SSD: single shot MultiBox detector publication-title: Computer Vision – ECCV 2016 – year: 2020 ident: bib17 article-title: An image is worth 16x16 words: transformers for image recognition at scale – year: 2022 ident: bib159 article-title: Booster-SHOT: boosting stacked homography transformations for multiview pedestrian detection with attention – start-page: 14309 year: 2022 end-page: 14319 ident: bib128 article-title: Holistic and hierarchical feature alignment for cross-domain weakly supervised object detection publication-title: 2022 IEEE/CVF conference on computer vision and pattern recognition (CVPR) – start-page: 1160 year: 2020 end-page: 1164 ident: bib170 article-title: A novel and efficient tumor detection framework for pancreatic cancer via CT images publication-title: 42nd annual international conference of the IEEE engineering in medicine & biology society – start-page: 419 year: 2022 end-page: 432 ident: bib132 article-title: Angle-based feature learning in GNN for 3D object detection using point cloud – year: 2023 ident: bib149 article-title: EfficientFace: an efficient deep network with feature enhancement for accurate face detection – start-page: 3960 year: 2022 end-page: 3969 ident: bib183 article-title: Towards open-set object detection and Discovery publication-title: 2022 IEEE/CVF conference on computer vision and pattern recognition workshops (CVPRW) – volume: 25 year: 2012 ident: bib4 article-title: ImageNet classification with deep convolutional neural networks publication-title: Neural Information Processing Systems – year: 2022 ident: bib108 article-title: STS: surround-view temporal stereo for multi-view 3D detection – volume: 34 start-page: 12557 year: 2020 end-page: 12564 ident: bib101 article-title: ZoomNet: Part-aware adaptive zooming neural network for 3D object detection publication-title: Proc AAAI Conf Artif Intell – start-page: 3743 year: 2021 end-page: 3752 ident: bib131 article-title: Multi-echo LiDAR for 3D object detection publication-title: 2021 IEEE/CVF international conference on computer vision (ICCV) – year: 2020 ident: bib55 article-title: End-to-End object detection with adaptive clustering transformer – start-page: 3354 year: 2012 end-page: 3361 ident: bib140 article-title: Are we ready for autonomous driving? The KITTI vision benchmark suite publication-title: 2012 IEEE conference on computer vision and pattern recognition – start-page: 3175 year: 2021 end-page: 3184 ident: bib50 article-title: CrossDet: crossline representation for object detection publication-title: 2021 IEEE/CVF international conference on computer vision (ICCV) – year: 2019 ident: bib36 article-title: ASSD: attentive single shot multibox detector – year: 2020 ident: bib98 article-title: Confidence guided stereo 3D object detection with split depth estimation – start-page: 3383 year: 2021 end-page: 3390 ident: bib103 article-title: PLUMENet: efficient 3D object detection from stereo images publication-title: 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) – start-page: 210 year: 2018 end-page: 226 ident: bib135 publication-title: SOD-MTGAN: Small Object Detection via Multi-Task Generative Adversarial Network: 15th European Conference – start-page: 13018 year: 2021 end-page: 13024 ident: bib92 article-title: YOLOStereo3D: a step back to 2D for efficient stereo 3D detection publication-title: IEEE International Conference on Robotics and Automation (ICRA)2021 – start-page: 9225 year: 2022 end-page: 9234 ident: bib181 article-title: OW-DETR: open-world detection transformer publication-title: 2022 IEEE/CVF conference on computer vision and pattern recognition (CVPR) – volume: 1 start-page: 886 year: 2005 end-page: 893 ident: bib2 article-title: Histograms of oriented gradients for human detection publication-title: IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05)2005 – start-page: 5410 year: 2018 end-page: 5418 ident: bib88 article-title: Pyramid stereo matching network publication-title: 2018 IEEE/CVF conference on computer vision and pattern recognition – year: 2017 ident: bib144 article-title: CARLA: an open urban driving simulator – start-page: 14052 year: 2020 end-page: 14061 ident: bib174 article-title: Learning to evaluate perception models using planner-centric metrics publication-title: 2020 IEEE/CVF conference on computer vision and pattern recognition (CVPR) – year: 2021 ident: bib31 article-title: PP-YOLOv2: a practical object detector – start-page: 687 year: 2019 end-page: 696 ident: bib125 article-title: Adapting object detectors via selective cross-domain alignment publication-title: 2019 IEEE/CVF conference on computer vision and pattern recognition (CVPR) – start-page: 2432 year: 2017 end-page: 2443 ident: bib145 article-title: ScanNet: richly-annotated 3D reconstructions of indoor scenes publication-title: 2017 IEEE conference on computer vision and pattern recognition (CVPR) – start-page: 9626 year: 2019 end-page: 9635 ident: bib46 article-title: FCOS: fully convolutional one-stage object detection – start-page: 5826 year: 2021 end-page: 5836 ident: bib180 article-title: Towards open world object detection publication-title: 2021 IEEE/CVF conference on computer vision and pattern recognition (CVPR) – year: 2019 ident: bib42 article-title: CornerNet-lite: efficient keypoint based object detection – start-page: 6141 year: 2021 end-page: 6150 ident: bib76 article-title: M3DSSD: monocular 3D single stage object detector publication-title: 2021 IEEE/CVF conference on computer vision and pattern recognition (CVPR) – start-page: 21 year: 2016 end-page: 37 ident: bib178 article-title: SSD: single shot MultiBox detector publication-title: Computer vision – ECCV 2016 – start-page: 91 year: 2020 end-page: 107 ident: bib49 article-title: Soft anchor-point object detection – volume: 1 start-page: 411 year: 2022 end-page: 415 ident: bib172 article-title: An end-to-end framework for universal lesion detection with missing annotations publication-title: 2022 16th IEEE International Conference on Signal Processing (ICSP) – start-page: 303 year: 2010 end-page: 338 ident: bib136 article-title: The pascal visual object classes (VOC) challenge publication-title: Int J Comput Vis – start-page: 1440 year: 2015 end-page: 1448 ident: bib22 article-title: IEEE international conference on computer vision (ICCV)2015 – start-page: 6850 year: 2019 end-page: 6859 ident: bib94 article-title: Accurate monocular 3D object detection via color-embedded 3D reconstruction for autonomous driving – start-page: 2980 year: 2017 end-page: 2988 ident: bib24 article-title: IEEE international conference on computer vision (ICCV)2017 – year: 2015 ident: bib118 article-title: Distilling the knowledge in a neural network – start-page: 740 year: 2014 end-page: 755 ident: bib138 article-title: Microsoft COCO: common objects in context publication-title: Computer vision – ECCV 2014 – year: 2023 ident: bib162 article-title: VLPD: context-aware pedestrian detection via vision-language semantic self-supervision – start-page: 10190 year: 2021 end-page: 10198 ident: bib114 article-title: OPANAS: one-shot path aggregation network architecture search for object detection publication-title: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)2021 – year: 2022 ident: bib156 article-title: The impact of partial occlusion on pedestrian detectability – volume: 29 start-page: 7389 year: 2020 end-page: 7398 ident: bib48 article-title: FoveaBox: beyound anchor-based object detection publication-title: IEEE Trans Image Process – year: 2020 ident: bib63 article-title: Toward transformer-based object detection – year: 2022 ident: bib28 article-title: YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors – year: 2022 ident: bib107 article-title: BEVStereo: enhancing depth estimation in multi-view 3D object detection with dynamic temporal stereo – volume: 60 start-page: 91 year: 2004 end-page: 110 ident: bib3 article-title: Distinctive image features from scale-invariant keypoints publication-title: Int J Comput Vis – start-page: 4289 year: 2020 end-page: 4298 ident: bib77 article-title: SMOKE: single-stage monocular 3D object detection via keypoint estimation publication-title: IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)2020 – year: 2022 ident: bib53 article-title: YOLOv6: a single-stage object detection framework for industrial applications – year: 2021 ident: bib16 article-title: Not all attention is all you need – start-page: 12533 year: 2020 end-page: 12542 ident: bib89 article-title: DSGN: deep stereo geometry network for 3D object detection publication-title: 2020 IEEE/CVF conference on computer vision and pattern recognition (CVPR) – volume: 197 year: 2022 ident: bib163 article-title: Remote sensing image super-resolution and object detection: benchmark and state of the art publication-title: Expert Syst Appl – start-page: 2064 year: 2019 end-page: 2073 ident: bib69 article-title: ROI-10D: monocular lifting of 2D detection to 6D pose and metric shape publication-title: 2019 IEEE/CVF conference on computer vision and pattern recognition (CVPR) – year: 2023 ident: bib166 article-title: Adjacent-level feature cross-fusion with 3D CNN for remote sensing image change detection – start-page: 548 year: 2021 end-page: 558 ident: bib7 article-title: Pyramid vision transformer: a versatile backbone for dense prediction without convolutions – year: 2022 ident: bib61 article-title: DAB-DETR: dynamic anchor boxes are better queries for DETR – start-page: 1991 year: 2019 end-page: 1999 ident: bib70 article-title: Disentangling monocular 3D object detection publication-title: IEEE/CVF International Conference on Computer Vision (ICCV)2019 – start-page: 6568 year: 2019 end-page: 6577 ident: bib44 article-title: CenterNet: keypoint triplets for object detection publication-title: 2019 IEEE/CVF international conference on computer vision (ICCV) – start-page: 2147 year: 2016 end-page: 2156 ident: bib67 article-title: Monocular 3D object detection for autonomous driving publication-title: 2016 IEEE conference on computer vision and pattern recognition (CVPR) – year: 2021 ident: bib10 article-title: You only look one-level feature – year: 2020 ident: bib104 article-title: Lift, splat, shoot: encoding images from arbitrary camera rigs by implicitly unprojecting to 3D – year: 2020 ident: bib29 publication-title: YOLOv5 – year: 2022 ident: bib157 article-title: Pedestrian detection: domain generalization, CNNs, transformers and beyond – year: 2020 ident: bib9 article-title: YOLOv4: optimal speed and accuracy of object detection – start-page: 141 year: 2018 ident: bib34 article-title: Extend the shallow part of single shot multibox detector via convolutional neural network – start-page: 2443 year: 2020 end-page: 2451 ident: bib141 article-title: Scalability in perception for autonomous driving: Waymo open dataset publication-title: 2020 IEEE/CVF conference on computer vision and pattern recognition (CVPR) – year: 2022 ident: bib110 article-title: BEVFormer v2: adapting modern image backbones to bird's-eye-view recognition via perspective supervision – year: 2020 ident: 10.1016/j.array.2023.100305_bib104 – start-page: 13018 year: 2021 ident: 10.1016/j.array.2023.100305_bib92 article-title: YOLOStereo3D: a step back to 2D for efficient stereo 3D detection publication-title: IEEE International Conference on Robotics and Automation (ICRA)2021 – year: 2020 ident: 10.1016/j.array.2023.100305_bib63 – start-page: 6517 year: 2017 ident: 10.1016/j.array.2023.100305_bib26 – volume: 36 start-page: 2567 year: 2022 ident: 10.1016/j.array.2023.100305_bib62 article-title: Anchor DETR: query design for transformer-based detector publication-title: Proc AAAI Conf Artif Intell – year: 2017 ident: 10.1016/j.array.2023.100305_bib133 – start-page: 1 year: 2022 ident: 10.1016/j.array.2023.100305_bib158 article-title: Pedestrian detection by exemplar-guided contrastive learning publication-title: IEEE Trans Image Process – start-page: 9626 year: 2019 ident: 10.1016/j.array.2023.100305_bib46 – start-page: 8969 year: 2021 ident: 10.1016/j.array.2023.100305_bib75 article-title: GrooMeD-NMS: grouped mathematically differentiable NMS for monocular 3D object detection – year: 2023 ident: 10.1016/j.array.2023.100305_bib171 – volume: 104 start-page: 154 issue: 2 year: 2013 ident: 10.1016/j.array.2023.100305_bib19 article-title: Selective search for object recognition publication-title: Int J Comput Vis doi: 10.1007/s11263-013-0620-5 – start-page: 17 year: 2020 ident: 10.1016/j.array.2023.100305_bib96 – start-page: 4885 year: 2017 ident: 10.1016/j.array.2023.100305_bib177 article-title: SSH: single stage headless face detector – year: 2019 ident: 10.1016/j.array.2023.100305_bib36 – start-page: 25 year: 2022 ident: 10.1016/j.array.2023.100305_bib168 article-title: Attention guided network for salient object detection in optical remote sensing images publication-title: Artificial Neural Networks and Machine Learning – ICANN doi: 10.1016/j.neunet.2021.12.003 – volume: 33 start-page: 8851 year: 2019 ident: 10.1016/j.array.2023.100305_bib71 article-title: MonoGRNet: a geometric reasoning network for monocular 3D object localization publication-title: Proc AAAI Conf Artif Intell – volume: 29 start-page: 7389 year: 2020 ident: 10.1016/j.array.2023.100305_bib48 article-title: FoveaBox: beyound anchor-based object detection publication-title: IEEE Trans Image Process doi: 10.1109/TIP.2020.3002345 – start-page: 12533 year: 2020 ident: 10.1016/j.array.2023.100305_bib89 article-title: DSGN: deep stereo geometry network for 3D object detection – year: 2020 ident: 10.1016/j.array.2023.100305_bib85 – year: 2023 ident: 10.1016/j.array.2023.100305_bib151 – year: 2021 ident: 10.1016/j.array.2023.100305_bib59 – year: 2022 ident: 10.1016/j.array.2023.100305_bib37 – start-page: 5410 year: 2018 ident: 10.1016/j.array.2023.100305_bib88 article-title: Pyramid stereo matching network – volume: 34 start-page: 12557 year: 2020 ident: 10.1016/j.array.2023.100305_bib101 article-title: ZoomNet: Part-aware adaptive zooming neural network for 3D object detection publication-title: Proc AAAI Conf Artif Intell – year: 2020 ident: 10.1016/j.array.2023.100305_bib29 publication-title: YOLOv5 – start-page: 7607 year: 2019 ident: 10.1016/j.array.2023.100305_bib84 article-title: Triangulation learning network: from monocular to stereo 3D object detection – start-page: 779 year: 2016 ident: 10.1016/j.array.2023.100305_bib12 article-title: You only look once: unified, real-time object detection – year: 2018 ident: 10.1016/j.array.2023.100305_bib93 – year: 2022 ident: 10.1016/j.array.2023.100305_bib110 – year: 2023 ident: 10.1016/j.array.2023.100305_bib112 – year: 2022 ident: 10.1016/j.array.2023.100305_bib15 – start-page: 840 year: 2019 ident: 10.1016/j.array.2023.100305_bib47 article-title: Feature selective anchor-free module for single-shot object detection – start-page: 9225 year: 2022 ident: 10.1016/j.array.2023.100305_bib181 article-title: OW-DETR: open-world detection transformer – year: 2021 ident: 10.1016/j.array.2023.100305_bib117 – start-page: 573 year: 2019 ident: 10.1016/j.array.2023.100305_bib173 article-title: A delay metric for video object detection: what average precision fails to tell – year: 2017 ident: 10.1016/j.array.2023.100305_bib33 – start-page: 4203 year: 2018 ident: 10.1016/j.array.2023.100305_bib39 article-title: Single-shot refinement neural network for object detection – start-page: 280 year: 2022 ident: 10.1016/j.array.2023.100305_bib66 – start-page: 17122 year: 2022 ident: 10.1016/j.array.2023.100305_bib80 article-title: ONCE-3DLanes: building monocular 3D lane detection – volume: 37 start-page: 1904 issue: 9 year: 2015 ident: 10.1016/j.array.2023.100305_bib21 article-title: Spatial pyramid pooling in deep convolutional networks for visual recognition publication-title: IEEE Trans Pattern Anal Mach Intell doi: 10.1109/TPAMI.2015.2389824 – start-page: 9992 year: 2021 ident: 10.1016/j.array.2023.100305_bib6 article-title: Swin transformer: hierarchical vision transformer using shifted windows – volume: 2023 start-page: 75 year: 2022 ident: 10.1016/j.array.2023.100305_bib165 article-title: Fully transformer network for change detection of remote sensing images publication-title: Computer Vision – ACCV – start-page: 936 year: 2017 ident: 10.1016/j.array.2023.100305_bib8 article-title: Feature pyramid networks for object detection – start-page: 13012 year: 2020 ident: 10.1016/j.array.2023.100305_bib86 article-title: IDA-3D: instance-depth-aware 3D object detection from stereo vision for autonomous driving – start-page: 91 year: 2020 ident: 10.1016/j.array.2023.100305_bib49 – start-page: 5880 year: 2020 ident: 10.1016/j.array.2023.100305_bib102 article-title: End-to-End pseudo-LiDAR for image-based 3D object detection – start-page: 3383 year: 2021 ident: 10.1016/j.array.2023.100305_bib103 article-title: PLUMENet: efficient 3D object detection from stereo images publication-title: 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) – volume: 60 start-page: 91 issue: 2 year: 2004 ident: 10.1016/j.array.2023.100305_bib3 article-title: Distinctive image features from scale-invariant keypoints publication-title: Int J Comput Vis doi: 10.1023/B:VISI.0000029664.99615.94 – start-page: I year: 2002 ident: 10.1016/j.array.2023.100305_bib1 article-title: An extended set of Haar-like features for rapid object detection – start-page: 2766 year: 2019 ident: 10.1016/j.array.2023.100305_bib35 – year: 2022 ident: 10.1016/j.array.2023.100305_bib157 – year: 2022 ident: 10.1016/j.array.2023.100305_bib108 – start-page: 110 year: 2023 ident: 10.1016/j.array.2023.100305_bib160 – start-page: 11618 year: 2020 ident: 10.1016/j.array.2023.100305_bib142 article-title: nuScenes: a multimodal dataset for autonomous driving – year: 2021 ident: 10.1016/j.array.2023.100305_bib10 – start-page: 4339 year: 2021 ident: 10.1016/j.array.2023.100305_bib122 article-title: Deep structured instance graph for distilling object detectors – start-page: 14052 year: 2020 ident: 10.1016/j.array.2023.100305_bib174 article-title: Learning to evaluate perception models using planner-centric metrics – start-page: 5826 year: 2021 ident: 10.1016/j.array.2023.100305_bib180 article-title: Towards open world object detection – start-page: 3960 year: 2022 ident: 10.1016/j.array.2023.100305_bib183 article-title: Towards open-set object detection and Discovery – start-page: 15152 year: 2021 ident: 10.1016/j.array.2023.100305_bib72 article-title: Geometry-based distance decomposition for monocular 3D object detection – start-page: 1160 year: 2020 ident: 10.1016/j.array.2023.100305_bib170 article-title: A novel and efficient tumor detection framework for pancreatic cancer via CT images – year: 2021 ident: 10.1016/j.array.2023.100305_bib175 – year: 2020 ident: 10.1016/j.array.2023.100305_bib100 – year: 2022 ident: 10.1016/j.array.2023.100305_bib111 – year: 2021 ident: 10.1016/j.array.2023.100305_bib16 – year: 2019 ident: 10.1016/j.array.2023.100305_bib113 – start-page: 303 year: 2010 ident: 10.1016/j.array.2023.100305_bib136 article-title: The pascal visual object classes (VOC) challenge publication-title: Int J Comput Vis doi: 10.1007/s11263-009-0275-4 – start-page: 2968 year: 2021 ident: 10.1016/j.array.2023.100305_bib57 article-title: Dynamic DETR: end-to-end object detection with dynamic attention – year: 2021 ident: 10.1016/j.array.2023.100305_bib65 – volume: 40 start-page: 1259 issue: 5 year: 2018 ident: 10.1016/j.array.2023.100305_bib82 article-title: 3D object proposals using stereo imagery for accurate object class detection publication-title: IEEE Trans Pattern Anal Mach Intell doi: 10.1109/TPAMI.2017.2706685 – year: 2023 ident: 10.1016/j.array.2023.100305_bib153 – year: 2017 ident: 10.1016/j.array.2023.100305_bib176 – start-page: 687 year: 2019 ident: 10.1016/j.array.2023.100305_bib125 article-title: Adapting object detectors via selective cross-domain alignment – start-page: 419 year: 2022 ident: 10.1016/j.array.2023.100305_bib132 – start-page: 3354 year: 2012 ident: 10.1016/j.array.2023.100305_bib140 article-title: Are we ready for autonomous driving? The KITTI vision benchmark suite – year: 2022 ident: 10.1016/j.array.2023.100305_bib161 – start-page: 913 year: 2021 ident: 10.1016/j.array.2023.100305_bib79 article-title: FCOS3D: fully convolutional one-stage monocular 3D object detection publication-title: IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)2021 – year: 2022 ident: 10.1016/j.array.2023.100305_bib107 – year: 2020 ident: 10.1016/j.array.2023.100305_bib98 – year: 2022 ident: 10.1016/j.array.2023.100305_bib148 – year: 2017 ident: 10.1016/j.array.2023.100305_bib32 – start-page: 195 year: 2022 ident: 10.1016/j.array.2023.100305_bib81 – start-page: 3339 year: 2018 ident: 10.1016/j.array.2023.100305_bib124 article-title: Domain adaptive faster R-CNN for object detection in the wild – start-page: 2980 year: 2017 ident: 10.1016/j.array.2023.100305_bib24 – volume: 60 start-page: 1 year: 2022 ident: 10.1016/j.array.2023.100305_bib169 article-title: Lightweight salient object detection in optical remote sensing images via feature correlation publication-title: IEEE Trans Geosci Rem Sens – year: 2020 ident: 10.1016/j.array.2023.100305_bib9 – start-page: 3288 year: 2021 ident: 10.1016/j.array.2023.100305_bib78 article-title: Objects are different: flexible monocular 3D object detection – year: 2020 ident: 10.1016/j.array.2023.100305_bib143 – year: 2021 ident: 10.1016/j.array.2023.100305_bib51 – start-page: 6850 year: 2019 ident: 10.1016/j.array.2023.100305_bib94 – start-page: 3743 year: 2021 ident: 10.1016/j.array.2023.100305_bib131 article-title: Multi-echo LiDAR for 3D object detection – start-page: 580 year: 2014 ident: 10.1016/j.array.2023.100305_bib18 article-title: Rich feature hierarchies for accurate object detection and semantic segmentation – year: 2022 ident: 10.1016/j.array.2023.100305_bib54 – start-page: 7838 year: 2021 ident: 10.1016/j.array.2023.100305_bib123 article-title: General instance distillation for object detection – volume: 34 start-page: 12257 year: 2020 ident: 10.1016/j.array.2023.100305_bib95 article-title: Task-aware monocular depth estimation for 3D object detection publication-title: Proc AAAI Conf Artif Intell – year: 2022 ident: 10.1016/j.array.2023.100305_bib28 – start-page: 2154 year: 2021 ident: 10.1016/j.array.2023.100305_bib120 article-title: Distilling object detectors via decoupled features publication-title: 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) doi: 10.1109/CVPR46437.2021.00219 – year: 2023 ident: 10.1016/j.array.2023.100305_bib155 – start-page: 14309 year: 2022 ident: 10.1016/j.array.2023.100305_bib128 article-title: Holistic and hierarchical feature alignment for cross-domain weakly supervised object detection – year: 2019 ident: 10.1016/j.array.2023.100305_bib42 – year: 2020 ident: 10.1016/j.array.2023.100305_bib30 – start-page: 6141 year: 2021 ident: 10.1016/j.array.2023.100305_bib76 article-title: M3DSSD: monocular 3D single stage object detector – year: 2022 ident: 10.1016/j.array.2023.100305_bib106 – start-page: 526 year: 2022 ident: 10.1016/j.array.2023.100305_bib179 – start-page: 3175 year: 2021 ident: 10.1016/j.array.2023.100305_bib50 article-title: CrossDet: crossline representation for object detection – start-page: 8383 year: 2020 ident: 10.1016/j.array.2023.100305_bib99 article-title: Object-centric stereo matching for 3D object detection publication-title: 2020 IEEE International Conference on Robotics and Automation (ICRA) doi: 10.1109/ICRA40945.2020.9196660 – year: 2021 ident: 10.1016/j.array.2023.100305_bib150 – volume: 197 year: 2022 ident: 10.1016/j.array.2023.100305_bib163 article-title: Remote sensing image super-resolution and object detection: benchmark and state of the art publication-title: Expert Syst Appl doi: 10.1016/j.eswa.2022.116793 – year: 2022 ident: 10.1016/j.array.2023.100305_bib167 – start-page: 740 year: 2014 ident: 10.1016/j.array.2023.100305_bib138 article-title: Microsoft COCO: common objects in context – year: 2022 ident: 10.1016/j.array.2023.100305_bib159 – year: 2023 ident: 10.1016/j.array.2023.100305_bib152 – start-page: 9286 year: 2019 ident: 10.1016/j.array.2023.100305_bib74 article-title: M3D-RPN: monocular 3D region proposal network for object detection – start-page: 1708 year: 2020 ident: 10.1016/j.array.2023.100305_bib129 article-title: Point-GNN: graph neural network for 3D object detection in a point cloud – year: 2016 ident: 10.1016/j.array.2023.100305_bib14 – year: 2017 ident: 10.1016/j.array.2023.100305_bib144 – start-page: 2432 year: 2017 ident: 10.1016/j.array.2023.100305_bib145 article-title: ScanNet: richly-annotated 3D reconstructions of indoor scenes – start-page: 869 issue: 3DV year: 2021 ident: 10.1016/j.array.2023.100305_bib182 article-title: Open-set 3D object detection publication-title: International Conference on 3D Vision – start-page: 1951 year: 2017 ident: 10.1016/j.array.2023.100305_bib134 article-title: Perceptual generative adversarial networks for small object detection – start-page: 9536 year: 2019 ident: 10.1016/j.array.2023.100305_bib40 article-title: Enriched feature guided refinement network for object detection – volume: 45 start-page: 4416 issue: 4 year: 2023 ident: 10.1016/j.array.2023.100305_bib90 article-title: DSGN++: exploiting visual-spatial relation for stereo-based 3D detectors publication-title: IEEE Trans Pattern Anal Mach Intell – start-page: 248 year: 2009 ident: 10.1016/j.array.2023.100305_bib137 article-title: ImageNet: a large-scale hierarchical image database – start-page: 4633 year: 2022 ident: 10.1016/j.array.2023.100305_bib121 article-title: Focal and global knowledge distillation for detectors – start-page: 4928 year: 2019 ident: 10.1016/j.array.2023.100305_bib119 article-title: Distilling object detectors with fine-grained feature imitation publication-title: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) doi: 10.1109/CVPR.2019.00507 – start-page: 567 year: 2015 ident: 10.1016/j.array.2023.100305_bib146 article-title: A RGB-D scene understanding benchmark suite – start-page: 746 year: 2012 ident: 10.1016/j.array.2023.100305_bib147 article-title: Indoor segmentation and support inference from RGBD images – year: 2023 ident: 10.1016/j.array.2023.100305_bib149 – year: 2022 ident: 10.1016/j.array.2023.100305_bib164 – year: 2022 ident: 10.1016/j.array.2023.100305_bib52 – year: 2020 ident: 10.1016/j.array.2023.100305_bib17 – start-page: 1 year: 2022 ident: 10.1016/j.array.2023.100305_bib109 – start-page: 4289 year: 2020 ident: 10.1016/j.array.2023.100305_bib77 article-title: SMOKE: single-stage monocular 3D object detection via keypoint estimation publication-title: IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)2020 – year: 2023 ident: 10.1016/j.array.2023.100305_bib162 – start-page: 2443 year: 2020 ident: 10.1016/j.array.2023.100305_bib141 article-title: Scalability in perception for autonomous driving: Waymo open dataset – start-page: 765 year: 2018 ident: 10.1016/j.array.2023.100305_bib41 article-title: CornerNet: detecting objects as paired keypoints – start-page: 58 year: 2023 ident: 10.1016/j.array.2023.100305_bib20 – start-page: 1440 year: 2015 ident: 10.1016/j.array.2023.100305_bib22 – start-page: 7636 year: 2019 ident: 10.1016/j.array.2023.100305_bib83 article-title: Stereo R-CNN based 3D object detection for autonomous driving – start-page: 6154 year: 2018 ident: 10.1016/j.array.2023.100305_bib25 article-title: Cascade R-CNN: delving into high quality object detection – start-page: 141 year: 2018 ident: 10.1016/j.array.2023.100305_bib34 – year: 2016 ident: 10.1016/j.array.2023.100305_bib139 – start-page: 850 year: 2019 ident: 10.1016/j.array.2023.100305_bib45 article-title: Bottom-up object detection by grouping extreme and center points – start-page: 10190 year: 2021 ident: 10.1016/j.array.2023.100305_bib114 article-title: OPANAS: one-shot path aggregation network architecture search for object detection publication-title: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)2021 – year: 2023 ident: 10.1016/j.array.2023.100305_bib154 – volume: 1 start-page: 411 year: 2022 ident: 10.1016/j.array.2023.100305_bib172 article-title: An end-to-end framework for universal lesion detection with missing annotations publication-title: 2022 16th IEEE International Conference on Signal Processing (ICSP) doi: 10.1109/ICSP56322.2022.9965335 – start-page: 11402 year: 2020 ident: 10.1016/j.array.2023.100305_bib116 article-title: Hit-detector: hierarchical trinity architecture search for object detection – start-page: 1991 year: 2019 ident: 10.1016/j.array.2023.100305_bib70 article-title: Disentangling monocular 3D object detection publication-title: IEEE/CVF International Conference on Computer Vision (ICCV)2019 – start-page: 3591 year: 2021 ident: 10.1016/j.array.2023.100305_bib60 article-title: Rethinking transformer-based set prediction for object detection – start-page: 21 year: 2016 ident: 10.1016/j.array.2023.100305_bib178 article-title: SSD: single shot MultiBox detector – start-page: 2999 year: 2017 ident: 10.1016/j.array.2023.100305_bib38 article-title: Focal loss for dense object detection – year: 2020 ident: 10.1016/j.array.2023.100305_bib55 – volume: 25 year: 2012 ident: 10.1016/j.array.2023.100305_bib4 article-title: ImageNet classification with deep convolutional neural networks publication-title: Neural Information Processing Systems – year: 2019 ident: 10.1016/j.array.2023.100305_bib97 – start-page: 7029 year: 2019 ident: 10.1016/j.array.2023.100305_bib115 article-title: NAS-FPN: learning scalable feature pyramid architecture for object detection publication-title: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) doi: 10.1109/CVPR.2019.00720 – start-page: 2064 year: 2019 ident: 10.1016/j.array.2023.100305_bib69 article-title: ROI-10D: monocular lifting of 2D detection to 6D pose and metric shape – year: 2023 ident: 10.1016/j.array.2023.100305_bib166 – volume: 39 start-page: 1137 issue: 6 year: 2017 ident: 10.1016/j.array.2023.100305_bib23 article-title: Towards real-time object detection with region proposal networks publication-title: IEEE Trans Pattern Anal Mach Intell doi: 10.1109/TPAMI.2016.2577031 – start-page: 11910 year: 2020 ident: 10.1016/j.array.2023.100305_bib130 article-title: DOPS: learning to detect 3D objects and predict their 3D shapes – start-page: 3133 year: 2021 ident: 10.1016/j.array.2023.100305_bib91 article-title: LIGA-stereo: learning LiDAR geometry aware representations for stereo-based 3D detector – volume: 2020 start-page: 213 year: 2020 ident: 10.1016/j.array.2023.100305_bib11 article-title: End-to-End object detection with transformers publication-title: Computer Vision – ECCV – start-page: 770 year: 2016 ident: 10.1016/j.array.2023.100305_bib5 article-title: Deep residual learning for image recognition – year: 2021 ident: 10.1016/j.array.2023.100305_bib31 – year: 2022 ident: 10.1016/j.array.2023.100305_bib61 – year: 2015 ident: 10.1016/j.array.2023.100305_bib118 – start-page: 21 year: 2016 ident: 10.1016/j.array.2023.100305_bib13 article-title: SSD: single shot MultiBox detector publication-title: Computer Vision – ECCV 2016 doi: 10.1007/978-3-319-46448-0_2 – year: 2018 ident: 10.1016/j.array.2023.100305_bib27 – volume: vol. 8 start-page: 1 year: 2022 ident: 10.1016/j.array.2023.100305_bib64 – start-page: 225 year: 2022 ident: 10.1016/j.array.2023.100305_bib87 article-title: SIDE: center-based stereo 3D detector with structure-aware instance depth estimation – start-page: 1019 year: 2019 ident: 10.1016/j.array.2023.100305_bib68 article-title: An efficient 3D object detection framework for autonomous driving – start-page: 3091 year: 2021 ident: 10.1016/j.array.2023.100305_bib73 article-title: Geometry uncertainty projection network for monocular 3D object detection – start-page: 6568 year: 2019 ident: 10.1016/j.array.2023.100305_bib44 article-title: CenterNet: keypoint triplets for object detection – start-page: 2147 year: 2016 ident: 10.1016/j.array.2023.100305_bib67 article-title: Monocular 3D object detection for autonomous driving – year: 2022 ident: 10.1016/j.array.2023.100305_bib156 – volume: 1 start-page: 886 year: 2005 ident: 10.1016/j.array.2023.100305_bib2 article-title: Histograms of oriented gradients for human detection publication-title: IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05)2005 doi: 10.1109/CVPR.2005.177 – year: 2022 ident: 10.1016/j.array.2023.100305_bib53 – year: 2021 ident: 10.1016/j.array.2023.100305_bib105 – start-page: 548 year: 2021 ident: 10.1016/j.array.2023.100305_bib7 – year: 2020 ident: 10.1016/j.array.2023.100305_bib58 – start-page: 5001 year: 2018 ident: 10.1016/j.array.2023.100305_bib127 article-title: Cross-domain weakly-supervised object detection through progressive domain adaptation – start-page: 481 year: 2020 ident: 10.1016/j.array.2023.100305_bib126 article-title: Spatial attention pyramid network for unsupervised domain adaptation – start-page: 210 year: 2018 ident: 10.1016/j.array.2023.100305_bib135 publication-title: SOD-MTGAN: Small Object Detection via Multi-Task Generative Adversarial Network: 15th European Conference – start-page: 2025 year: 2019 ident: 10.1016/j.array.2023.100305_bib43 article-title: Matrix nets: a new deep architecture for object detection – start-page: 3601 year: 2021 ident: 10.1016/j.array.2023.100305_bib56 article-title: Fast convergence of DETR with spatially modulated Co-attention |
| SSID | ssj0002511158 |
| Score | 2.4816787 |
| SecondaryResourceType | review_article |
| Snippet | Object detection is a crucial branch of computer vision that aims to locate and classify objects in images. Using deep convolutional neural networks (CNNs) as... |
| SourceID | doaj crossref elsevier |
| SourceType | Open Website Enrichment Source Index Database Publisher |
| StartPage | 100305 |
| SubjectTerms | CNNs Object detection Transformer |
| Title | 2D and 3D object detection algorithms from images: A Survey |
| URI | https://dx.doi.org/10.1016/j.array.2023.100305 https://doaj.org/article/52738a24e3ee4601a06a235ec7d0a2b9 |
| Volume | 19 |
| WOSCitedRecordID | wos001043834800001&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: PRVAON databaseName: DOAJ Directory of Open Access Journals customDbUrl: eissn: 2590-0056 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0002511158 issn: 2590-0056 databaseCode: DOA dateStart: 20190101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVHPJ databaseName: ROAD: Directory of Open Access Scholarly Resources customDbUrl: eissn: 2590-0056 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0002511158 issn: 2590-0056 databaseCode: M~E dateStart: 20190101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV05T8MwFLYQYmDhRpRLHhgJpPGRBCaOIgaokDjEFvl4gaKSorQgdeG34-ckVSZYWDJEsR09v_h9jj5_HyEHTDGhtJSBNRoCbtxcJMqmgSu1eVemQjPPzXm6ifv95Pk5vWtZfSEnrJIHrgJ37AXCVMSBAXC3e1ChVBETYGIbqkj7o3sO9bQ2U7gGI3DuenNOB-_x6LSQjeSQJ3epslTTI7QOR5oAQ_O6Vlny6v2t6tSqOFcrZKmGivSsesVVMgfFGllubBho_VWuk9PokqrCUnZJRxp_q1ALE8-wKqgavozc9v_1fUzxIAkdvLv1Y3xCz-j9Z_kF0w3yeNV7uLgOak-EwPAunwQqyfNUx5bnXOYydOhLIKTh0kql8zgNc2BW5V0dc0gQ2-lQWJDchKkGHXK2SeaLUQFbhCohrBWJSWNmHWxz7U1qUc4MVKyBQ4dETUgyUwuGo2_FMGuYYW-Zj2OGccyqOHbI4azRR6WX8fvj5xjr2aModu1vuBTI6hTI_kqBDpHNTGU1bqjwgOtq8Nvo2_8x-g5ZxC4r3tkumZ-Un7BHFszXZDAu931auuvtd-8HusLkDw |
| linkProvider | Directory of Open Access Journals |
| 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=2D+and+3D+object+detection+algorithms+from+images%3A+A+Survey&rft.jtitle=Array+%28New+York%29&rft.au=Chen%2C+Wei&rft.au=Li%2C+Yan&rft.au=Tian%2C+Zijian&rft.au=Zhang%2C+Fan&rft.date=2023-09-01&rft.pub=Elsevier+Inc&rft.issn=2590-0056&rft.eissn=2590-0056&rft.volume=19&rft_id=info:doi/10.1016%2Fj.array.2023.100305&rft.externalDocID=S2590005623000309 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2590-0056&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2590-0056&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2590-0056&client=summon |