Scale-Aware Fast R-CNN for Pedestrian Detection

In this paper, we consider the problem of pedestrian detection in natural scenes. Intuitively, instances of pedestrians with different spatial scales may exhibit dramatically different features. Thus, large variance in instance scales, which results in undesirable large intracategory variance in fea...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	IEEE transactions on multimedia Ročník 20; číslo 4; s. 985 - 996
Hlavní autori:	Li, Jianan, Liang, Xiaodan, Shen, Shengmei, Xu, Tingfa, Feng, Jiashi, Yan, Shuicheng
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	IEEE 01.04.2018
Predmet:	deep learning Detectors Feature extraction Logic gates Pedestrian detection Proposals Robustness scale-aware Skeleton Training
ISSN:	1520-9210, 1941-0077
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Abstract	In this paper, we consider the problem of pedestrian detection in natural scenes. Intuitively, instances of pedestrians with different spatial scales may exhibit dramatically different features. Thus, large variance in instance scales, which results in undesirable large intracategory variance in features, may severely hurt the performance of modern object instance detection methods. We argue that this issue can be substantially alleviated by the divide-and-conquer philosophy. Taking pedestrian detection as an example, we illustrate how we can leverage this philosophy to develop a Scale-Aware Fast R-CNN (SAF R-CNN) framework. The model introduces multiple built-in subnetworks which detect pedestrians with scales from disjoint ranges. Outputs from all of the subnetworks are then adaptively combined to generate the final detection results that are shown to be robust to large variance in instance scales, via a gate function defined over the sizes of object proposals. Extensive evaluations on several challenging pedestrian detection datasets well demonstrate the effectiveness of the proposed SAF R-CNN. Particularly, our method achieves state-of-the-art performance on Caltech [P. Dollar, C. Wojek, B. Schiele, and P. Perona, "Pedestrian detection: An evaluation of the state of the art," IEEE Trans. Pattern Anal. Mach. Intell. , vol. 34, no. 4, pp. 743-761, Apr. 2012], and obtains competitive results on INRIA [N. Dalal and B. Triggs, "Histograms of oriented gradients for human detection," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. , 2005, pp. 886-893], ETH [A. Ess, B. Leibe, and L. V. Gool, "Depth and appearance for mobile scene analysis," in Proc. Int. Conf. Comput. Vis ., 2007, pp. 1-8], and KITTI [A. Geiger, P. Lenz, and R. Urtasun, "Are we ready for autonomous driving? The KITTI vision benchmark suite," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit ., 2012, pp. 3354-3361].
AbstractList	In this paper, we consider the problem of pedestrian detection in natural scenes. Intuitively, instances of pedestrians with different spatial scales may exhibit dramatically different features. Thus, large variance in instance scales, which results in undesirable large intracategory variance in features, may severely hurt the performance of modern object instance detection methods. We argue that this issue can be substantially alleviated by the divide-and-conquer philosophy. Taking pedestrian detection as an example, we illustrate how we can leverage this philosophy to develop a Scale-Aware Fast R-CNN (SAF R-CNN) framework. The model introduces multiple built-in subnetworks which detect pedestrians with scales from disjoint ranges. Outputs from all of the subnetworks are then adaptively combined to generate the final detection results that are shown to be robust to large variance in instance scales, via a gate function defined over the sizes of object proposals. Extensive evaluations on several challenging pedestrian detection datasets well demonstrate the effectiveness of the proposed SAF R-CNN. Particularly, our method achieves state-of-the-art performance on Caltech [P. Dollar, C. Wojek, B. Schiele, and P. Perona, "Pedestrian detection: An evaluation of the state of the art," IEEE Trans. Pattern Anal. Mach. Intell. , vol. 34, no. 4, pp. 743-761, Apr. 2012], and obtains competitive results on INRIA [N. Dalal and B. Triggs, "Histograms of oriented gradients for human detection," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. , 2005, pp. 886-893], ETH [A. Ess, B. Leibe, and L. V. Gool, "Depth and appearance for mobile scene analysis," in Proc. Int. Conf. Comput. Vis ., 2007, pp. 1-8], and KITTI [A. Geiger, P. Lenz, and R. Urtasun, "Are we ready for autonomous driving? The KITTI vision benchmark suite," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit ., 2012, pp. 3354-3361].
Author	Yan, Shuicheng Xu, Tingfa Feng, Jiashi Liang, Xiaodan Li, Jianan Shen, Shengmei
Author_xml	– sequence: 1 givenname: Jianan orcidid: 0000-0002-1479-1099 surname: Li fullname: Li, Jianan email: 20090964@bit.edu.cn organization: School of Optical Engineering, Beijing Institute of Technology, Beijing, China – sequence: 2 givenname: Xiaodan surname: Liang fullname: Liang, Xiaodan email: xdliang328@gmail.com organization: Carnegie Mellon University, Pittsburgh, USA – sequence: 3 givenname: Shengmei surname: Shen fullname: Shen, Shengmei email: shengmei.shen@sg.panasonic.com organization: Panasonic R&D Center Singapore, Singapore – sequence: 4 givenname: Tingfa orcidid: 0000-0002-1479-1099 surname: Xu fullname: Xu, Tingfa email: 15210538723@163.com organization: School of Optical Engineering, Beijing Institute of Technology, Beijing, China – sequence: 5 givenname: Jiashi surname: Feng fullname: Feng, Jiashi email: jshfeng@gmail.com organization: Department of Electrical and Computer Engineering, National University of Singapore, Singapore – sequence: 6 givenname: Shuicheng surname: Yan fullname: Yan, Shuicheng email: eleyans@nus.edu.sg organization: Department of Electrical and Computer Engineering, National University of Singapore, Singapore
BookMark	eNp9j8FKAzEQhoNUsK3eBS_7AmlnstlNcizVqtBW0XpestkJrNRdSQLi27ulxYMHTzPMP98w34SNur4jxq4RZohg5rvNZiYA1UyowhSgz9gYjUQOoNRo6AsB3AiECzaJ8R0AZQFqzOavzu6JL75soGxlY8pe-HK7zXwfsmdqKKbQ2i67pUQutX13yc693Ue6OtUpe1vd7ZYPfP10_7hcrLkTZZ54UcsSraHGGdRIptZQa-3RKtC1loYsNJqa0utSSGlEIVUxzL3zlGNNkE9ZebzrQh9jIF-5NtnDBynYdl8hVAftatCuDtrVSXsA4Q_4GdoPG77_Q26OSEtEv-saShjy_Ad1cmMN
CODEN	ITMUF8
CitedBy_id	crossref_primary_10_1117_1_JEI_31_6_061812 crossref_primary_10_1109_TVT_2020_2983825 crossref_primary_10_1109_TPAMI_2020_2981890 crossref_primary_10_1155_2018_7328074 crossref_primary_10_1109_ACCESS_2019_2928879 crossref_primary_10_1109_TIM_2022_3230459 crossref_primary_10_1109_TMM_2018_2834873 crossref_primary_10_1109_TMM_2020_2981237 crossref_primary_10_1109_ACCESS_2021_3115963 crossref_primary_10_1109_TMM_2021_3140025 crossref_primary_10_1109_TCSVT_2018_2883558 crossref_primary_10_1109_TCSVT_2019_2913114 crossref_primary_10_1109_TMM_2021_3116430 crossref_primary_10_1109_TPAMI_2023_3290594 crossref_primary_10_1109_TPAMI_2019_2910514 crossref_primary_10_1109_TMM_2023_3272471 crossref_primary_10_1109_ACCESS_2019_2896201 crossref_primary_10_1109_TCSVT_2023_3306870 crossref_primary_10_1109_TIM_2024_3428635 crossref_primary_10_1088_1361_6501_adfe09 crossref_primary_10_1109_TNNLS_2020_3004819 crossref_primary_10_1109_TIM_2021_3054627 crossref_primary_10_17163_ings_n27_2022_08 crossref_primary_10_1109_TITS_2020_3043250 crossref_primary_10_1109_TIP_2020_3038347 crossref_primary_10_1109_TMM_2020_2990070 crossref_primary_10_1109_TII_2023_3316182 crossref_primary_10_1109_TIP_2021_3049948 crossref_primary_10_1109_ACCESS_2020_2972055 crossref_primary_10_1109_JIOT_2022_3162295 crossref_primary_10_1109_TITS_2019_2948398 crossref_primary_10_1007_s11042_024_18879_5 crossref_primary_10_1109_TNNLS_2021_3080276 crossref_primary_10_1109_TCSVT_2019_2950526 crossref_primary_10_1109_ACCESS_2019_2904712 crossref_primary_10_1109_TITS_2018_2869087 crossref_primary_10_1007_s00530_019_00628_6 crossref_primary_10_1007_s11042_023_14721_6 crossref_primary_10_20965_jaciii_2018_p1056 crossref_primary_10_1117_1_JEI_31_4_043018 crossref_primary_10_1109_ACCESS_2020_3022517 crossref_primary_10_1109_TITS_2022_3171250 crossref_primary_10_1109_TCSVT_2021_3060162 crossref_primary_10_1109_TITS_2023_3307167 crossref_primary_10_1109_LSP_2022_3215920 crossref_primary_10_1109_TMM_2019_2929005 crossref_primary_10_1109_TGRS_2022_3155634 crossref_primary_10_1109_TIP_2019_2944306 crossref_primary_10_1109_TITS_2019_2933581 crossref_primary_10_1109_JOE_2020_3039037 crossref_primary_10_1007_s11771_020_4448_1 crossref_primary_10_1109_ACCESS_2024_3406968 crossref_primary_10_1109_TIP_2020_3029901 crossref_primary_10_1109_TPAMI_2019_2897684 crossref_primary_10_1109_MCE_2021_3116440 crossref_primary_10_1007_s00530_025_01967_3 crossref_primary_10_1109_ACCESS_2020_2995321 crossref_primary_10_1109_ACCESS_2020_3012558 crossref_primary_10_1109_TMC_2024_3452101 crossref_primary_10_1016_j_ijleo_2022_170334 crossref_primary_10_1109_ACCESS_2019_2900369 crossref_primary_10_1007_s00521_021_06265_3 crossref_primary_10_1049_cvi2_12159 crossref_primary_10_1109_TMM_2024_3350926 crossref_primary_10_1186_s13640_019_0441_8 crossref_primary_10_1109_ACCESS_2025_3561279 crossref_primary_10_1109_LSP_2020_3033462 crossref_primary_10_1007_s11432_020_2969_8 crossref_primary_10_1117_1_JEI_34_3_033046 crossref_primary_10_1109_TII_2024_3353845 crossref_primary_10_1109_ACCESS_2025_3599213 crossref_primary_10_1364_AO_503039 crossref_primary_10_1007_s40192_021_00240_5 crossref_primary_10_3390_app9112335 crossref_primary_10_1007_s13735_022_00239_4 crossref_primary_10_1109_ACCESS_2025_3543164 crossref_primary_10_1109_TITS_2024_3495814 crossref_primary_10_1108_IR_09_2020_0186 crossref_primary_10_1109_TITS_2019_2904836 crossref_primary_10_1109_TCSVT_2021_3079897 crossref_primary_10_1109_TMM_2022_3160589 crossref_primary_10_1109_TPAMI_2020_3012414 crossref_primary_10_1155_2022_6106853 crossref_primary_10_1155_2023_5349965 crossref_primary_10_1007_s00521_019_04424_1 crossref_primary_10_1109_LGRS_2024_3440045 crossref_primary_10_2478_amns_2023_2_00449 crossref_primary_10_1186_s13640_019_0456_1 crossref_primary_10_1088_1361_6501_adcf41 crossref_primary_10_1109_TCSVT_2020_3000223 crossref_primary_10_1109_TMM_2021_3088303 crossref_primary_10_1109_ACCESS_2018_2872497 crossref_primary_10_1109_ACCESS_2021_3063028 crossref_primary_10_1080_10095020_2025_2542964 crossref_primary_10_1109_TITS_2019_2963700 crossref_primary_10_1109_TMM_2024_3381377 crossref_primary_10_1631_FITEE_2000567 crossref_primary_10_1109_ACCESS_2022_3175303 crossref_primary_10_1109_ACCESS_2019_2927036 crossref_primary_10_1109_LSP_2020_2995102 crossref_primary_10_1109_TMM_2024_3401549 crossref_primary_10_1109_TCOMM_2020_3027027 crossref_primary_10_1109_ACCESS_2019_2924443 crossref_primary_10_1016_j_ins_2020_05_009 crossref_primary_10_1109_ACCESS_2023_3244981 crossref_primary_10_1002_tee_23696 crossref_primary_10_1109_JSEN_2023_3242082 crossref_primary_10_1109_TIP_2019_2957927 crossref_primary_10_1109_TGRS_2024_3457155 crossref_primary_10_1109_TITS_2022_3142445 crossref_primary_10_1088_1361_6501_ad9bd9 crossref_primary_10_1109_TMM_2019_2929949 crossref_primary_10_3389_fnbot_2018_00064 crossref_primary_10_1109_TBIOM_2024_3487545 crossref_primary_10_1109_TCDS_2019_2920364 crossref_primary_10_1007_s11554_022_01203_5 crossref_primary_10_1155_2021_7978644 crossref_primary_10_1109_TITS_2024_3390576 crossref_primary_10_1109_ACCESS_2020_2999694 crossref_primary_10_1109_TITS_2022_3210186 crossref_primary_10_1109_JPHOT_2019_2922270 crossref_primary_10_1109_TIE_2019_2945295 crossref_primary_10_1109_ACCESS_2024_3362636 crossref_primary_10_1109_ACCESS_2022_3201139 crossref_primary_10_1109_TMM_2019_2916104 crossref_primary_10_1109_TITS_2019_2923752 crossref_primary_10_1109_TIP_2020_3038371 crossref_primary_10_1109_TMM_2019_2922127 crossref_primary_10_1109_TGRS_2021_3059450 crossref_primary_10_1109_TIP_2020_3040854 crossref_primary_10_1109_TMM_2021_3078141 crossref_primary_10_1088_1742_6596_2252_1_012050 crossref_primary_10_3389_fpls_2025_1604514 crossref_primary_10_1109_TII_2020_3024578 crossref_primary_10_1016_j_eswa_2021_115295 crossref_primary_10_1109_ACCESS_2019_2899105 crossref_primary_10_1109_TIP_2019_2942686 crossref_primary_10_1109_TVT_2020_3043203 crossref_primary_10_1007_s11042_018_6866_8 crossref_primary_10_1145_3434398 crossref_primary_10_1007_s12145_025_01818_9 crossref_primary_10_1109_TMM_2021_3058546 crossref_primary_10_1155_2018_3518959 crossref_primary_10_1109_TIP_2020_3039574 crossref_primary_10_1155_2021_5590895 crossref_primary_10_1109_TCSVT_2023_3245613 crossref_primary_10_1109_ACCESS_2018_2869976 crossref_primary_10_1109_ACCESS_2023_3293120 crossref_primary_10_1109_TIFS_2019_2916592 crossref_primary_10_1109_TITS_2019_2942045 crossref_primary_10_1007_s11263_021_01461_z crossref_primary_10_1109_TMM_2020_3020691 crossref_primary_10_1007_s11042_023_15845_5 crossref_primary_10_1109_TIP_2022_3189803 crossref_primary_10_1007_s10586_023_04164_x crossref_primary_10_1109_TMM_2022_3149129 crossref_primary_10_1145_3307599_3307605 crossref_primary_10_1109_TMM_2019_2951461 crossref_primary_10_1109_TMM_2023_3251100 crossref_primary_10_1109_ACCESS_2021_3063294 crossref_primary_10_1109_TIP_2019_2938877 crossref_primary_10_3389_fnbot_2022_881021 crossref_primary_10_1109_TPAMI_2021_3076733 crossref_primary_10_1109_TCSVT_2021_3076466 crossref_primary_10_1109_TCSVT_2019_2924912 crossref_primary_10_1007_s11045_021_00764_1 crossref_primary_10_1109_TMM_2022_3178871 crossref_primary_10_1007_s11704_018_7153_6 crossref_primary_10_1117_1_JEI_33_2_023052 crossref_primary_10_1155_2022_2748862 crossref_primary_10_1109_TIP_2020_2966371 crossref_primary_10_1109_ACCESS_2019_2895376 crossref_primary_10_1088_1361_6501_abfdde crossref_primary_10_1109_ACCESS_2023_3343383 crossref_primary_10_1109_ACCESS_2020_2986476 crossref_primary_10_1007_s10462_023_10630_0 crossref_primary_10_1016_j_inffus_2018_11_017 crossref_primary_10_1016_j_infrared_2018_11_007 crossref_primary_10_1109_TITS_2020_3034239 crossref_primary_10_1109_JIOT_2024_3362851 crossref_primary_10_1109_ACCESS_2022_3150988 crossref_primary_10_1109_TDSC_2019_2923653 crossref_primary_10_1145_3498340 crossref_primary_10_1109_TMM_2021_3075566
Cites_doi	10.1007/s11263-013-0620-5 10.1109/CVPR.2007.383157 10.1109/ICCV.2013.10 10.1109/ICCV.2013.257 10.1109/CVPR.2014.126 10.1109/IVS.2015.7225711 10.1109/TPAMI.2011.155 10.1109/ICCV.2013.322 10.1109/ICCV.2003.1238422 10.1109/TMM.2016.2642789 10.1145/2647868.2654889 10.1109/CVPR.2014.81 10.1109/TCYB.2013.2255271 10.1109/TMM.2016.2602060 10.1109/CVPR.2005.177 10.1145/3065386 10.1109/ICCV.2015.169 10.1109/CVPR.2013.235 10.1109/CVPR.2015.7299143 10.1109/CVPR.2015.7299034 10.1109/TPAMI.2013.124 10.1109/ICCV.2009.5459207 10.1007/978-3-319-16181-5_47 10.1109/CVPR.2012.6248074 10.1109/CVPR.2016.91 10.1109/CVPR.2016.141 10.1109/TPAMI.2009.167 10.1007/978-3-642-23678-5_55 10.1109/TMM.2015.2476660 10.1109/CVPR.2014.49 10.1109/TCYB.2016.2593940 10.1109/ICCV.2007.4409092 10.1109/TPAMI.2016.2577031 10.1109/ICCV.2015.384 10.1007/s11263-016-0890-9 10.1007/978-3-319-10584-0_26 10.1016/j.procs.2016.05.455 10.1109/TPAMI.2014.2300479 10.1109/CVPR.2012.6248017 10.1109/CVPR.2016.147 10.1007/978-3-319-10593-2_36 10.1109/TMM.2014.2321534 10.1109/CVPR.2013.390 10.1023/B:VISI.0000013087.49260.fb 10.1007/978-3-642-15561-1_18 10.1109/TMM.2015.2476655 10.1109/CVPR.2015.7298784 10.1109/CVPR.2013.465 10.1007/978-3-319-10602-1_26 10.1109/ICCV.2015.221 10.1109/CVPR.2014.27 10.5244/C.23.91
ContentType	Journal Article
DBID	97E RIA RIE AAYXX CITATION
DOI	10.1109/TMM.2017.2759508
DatabaseName	IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef
DatabaseTitle	CrossRef
DatabaseTitleList
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	996
ExternalDocumentID	10_1109_TMM_2017_2759508 8060595
Genre	orig-research
GrantInformation_xml	– fundername: China Scholarship Council grantid: 201506030045
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
ID	FETCH-LOGICAL-c263t-5b461a9edc9181e9b80b88f1a708b849ea0d8ed6f86244925475b84fcfe31be03
IEDL.DBID	RIE
ISICitedReferencesCount	577
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000427623000017&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	Sat Nov 29 02:04:04 EST 2025 Tue Nov 18 22:41:41 EST 2025 Wed Aug 27 02:52:11 EDT 2025
IsPeerReviewed	true
IsScholarly	true
Issue	4
Language	English
License	https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c263t-5b461a9edc9181e9b80b88f1a708b849ea0d8ed6f86244925475b84fcfe31be03
ORCID	0000-0002-1479-1099
PageCount	12
ParticipantIDs	crossref_citationtrail_10_1109_TMM_2017_2759508 crossref_primary_10_1109_TMM_2017_2759508 ieee_primary_8060595
PublicationCentury	2000
PublicationDate	2018-04-01
PublicationDateYYYYMMDD	2018-04-01
PublicationDate_xml	– month: 04 year: 2018 text: 2018-04-01 day: 01
PublicationDecade	2010
PublicationTitle	IEEE transactions on multimedia
PublicationTitleAbbrev	TMM
PublicationYear	2018
Publisher	IEEE
Publisher_xml	– name: IEEE
References	zhang (ref58) 0 ref57 ref13 ref12 ref59 ref15 ref14 ref53 ref52 ref55 ref11 ref54 ref10 ref17 ref16 ref19 ref18 hariharan (ref20) 0 ref51 ref50 ouyang (ref33) 0 ref46 nam (ref31) 0 ref48 ref47 ref41 ref44 simonyan (ref45) 2014 he (ref21) 0 chen (ref7) 0 ref49 ref8 ref9 ref4 ref3 ref6 ref5 ref40 ref35 ref34 nam (ref32) 0 ref37 ref36 ref30 ref2 ref1 ref39 ref38 ribeiro (ref42) 2016 ref24 ref23 ref26 ref25 ref64 ref63 ref22 xu (ref56) 2014 liu (ref28) 0 ref27 ref29 sermanet (ref43) 2013 ref60 ref62 ref61
References_xml	– start-page: 443 year: 0 ident: ref58 article-title: Is faster R-CNN doing well for pedestrian detection publication-title: Proc Eur Conf Comput Vis – ident: ref49 doi: 10.1007/s11263-013-0620-5 – ident: ref38 doi: 10.1109/CVPR.2007.383157 – start-page: 1 year: 0 ident: ref31 article-title: Pedestrian detection system based on stereo vision for mobile robot publication-title: Proc – ident: ref55 doi: 10.1109/ICCV.2013.10 – start-page: 424 year: 0 ident: ref7 article-title: 3D object proposals for accurate object class detection publication-title: Proc 28th Int Conf Neural Inform Process Syst – start-page: 346 year: 0 ident: ref21 article-title: Spatial pyramid pooling in deep convolutional networks for visual recognition publication-title: Proc Eur Conf Comput Vis – year: 2016 ident: ref42 article-title: A real-time pedestrian detector using deep learning for human-aware navigation – ident: ref34 doi: 10.1109/ICCV.2013.257 – ident: ref61 doi: 10.1109/CVPR.2014.126 – ident: ref19 doi: 10.1109/IVS.2015.7225711 – ident: ref11 doi: 10.1109/TPAMI.2011.155 – ident: ref30 doi: 10.1109/ICCV.2013.322 – ident: ref51 doi: 10.1109/ICCV.2003.1238422 – ident: ref26 doi: 10.1109/TMM.2016.2642789 – ident: ref24 doi: 10.1145/2647868.2654889 – start-page: 21 year: 0 ident: ref28 article-title: SSD: Single shot multibox detector publication-title: Proc Eur Conf Comput Vis – start-page: 459 year: 0 ident: ref20 article-title: Discriminative decorrelation for clustering and classification publication-title: Proc Eur Conf Comput Vis – ident: ref16 doi: 10.1109/CVPR.2014.81 – ident: ref29 doi: 10.1109/TCYB.2013.2255271 – ident: ref23 doi: 10.1109/TMM.2016.2602060 – ident: ref8 doi: 10.1109/CVPR.2005.177 – ident: ref25 doi: 10.1145/3065386 – ident: ref15 doi: 10.1109/ICCV.2015.169 – ident: ref6 doi: 10.1109/CVPR.2013.235 – ident: ref48 doi: 10.1109/CVPR.2015.7299143 – ident: ref22 doi: 10.1109/CVPR.2015.7299034 – ident: ref53 doi: 10.1109/TPAMI.2013.124 – ident: ref54 doi: 10.1109/ICCV.2009.5459207 – ident: ref3 doi: 10.1007/978-3-319-16181-5_47 – ident: ref14 doi: 10.1109/CVPR.2012.6248074 – ident: ref40 doi: 10.1109/CVPR.2016.91 – ident: ref59 doi: 10.1109/CVPR.2016.141 – ident: ref13 doi: 10.1109/TPAMI.2009.167 – start-page: 3258 year: 0 ident: ref33 article-title: A discriminative deep model for pedestrian detection with occlusion handling publication-title: Proc IEEE Conf Comput Vis Pattern Recogn – ident: ref39 doi: 10.1007/978-3-642-23678-5_55 – ident: ref46 doi: 10.1109/TMM.2015.2476660 – ident: ref1 doi: 10.1109/CVPR.2014.49 – ident: ref18 doi: 10.1109/TCYB.2016.2593940 – ident: ref12 doi: 10.1109/ICCV.2007.4409092 – ident: ref41 doi: 10.1109/TPAMI.2016.2577031 – ident: ref62 doi: 10.1109/ICCV.2015.384 – ident: ref35 doi: 10.1007/s11263-016-0890-9 – ident: ref17 doi: 10.1007/978-3-319-10584-0_26 – ident: ref4 doi: 10.1016/j.procs.2016.05.455 – ident: ref9 doi: 10.1109/TPAMI.2014.2300479 – ident: ref2 doi: 10.1109/CVPR.2012.6248017 – ident: ref5 doi: 10.1109/CVPR.2016.147 – year: 2014 ident: ref45 article-title: Very deep convolutional networks for large-scale image recognition – start-page: 424 year: 0 ident: ref32 article-title: Local decorrelation for improved pedestrian detection publication-title: Proc 27th Int Conf Neural Inf Process Syst – ident: ref36 doi: 10.1007/978-3-319-10593-2_36 – ident: ref63 doi: 10.1109/TMM.2014.2321534 – year: 2013 ident: ref43 article-title: Overfeat: Integrated recognition, localization and detection using convolutional networks – ident: ref57 doi: 10.1109/CVPR.2013.390 – ident: ref50 doi: 10.1023/B:VISI.0000013087.49260.fb – ident: ref37 doi: 10.1007/978-3-642-15561-1_18 – ident: ref52 doi: 10.1109/TMM.2015.2476655 – ident: ref60 doi: 10.1109/CVPR.2015.7298784 – ident: ref44 doi: 10.1109/CVPR.2013.465 – ident: ref64 doi: 10.1007/978-3-319-10602-1_26 – ident: ref47 doi: 10.1109/ICCV.2015.221 – ident: ref27 doi: 10.1109/CVPR.2014.27 – ident: ref10 doi: 10.5244/C.23.91 – year: 2014 ident: ref56 article-title: Scale-invariant convolutional neural networks
SSID	ssj0014507
Score	2.6704466
Snippet	In this paper, we consider the problem of pedestrian detection in natural scenes. Intuitively, instances of pedestrians with different spatial scales may...
SourceID	crossref ieee
SourceType	Enrichment Source Index Database Publisher
StartPage	985
SubjectTerms	deep learning Detectors Feature extraction Logic gates Pedestrian detection Proposals Robustness scale-aware Skeleton Training
Title	Scale-Aware Fast R-CNN for Pedestrian Detection
URI	https://ieeexplore.ieee.org/document/8060595
Volume	20
WOSCitedRecordID	wos000427623000017&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/eLvHCXMwlV1LS8QwEB508aAH1yeuL3rwIhg3tWkex0VdPGgRX3greUxBkCpr1b9vku0WBRG8lTAJ4UvLTDrzzQdwwJXxTlUyolPhCHPMEOM0J5XIhMhFJfPIcn24FEUhHx_V9RwcdVwYRIzFZ3gcHmMu373Y9_CrbCipD75VPg_zQvApV6vLGLA8UqO9O6JE-XvMLCVJ1fDu6irUcInjE5EH0dMfLuibpkp0KeP-_zazAstt6JiMpme9CnNYr0F_JsuQtF_pGix96zG4DsNbfwpIRp96gslYvzXJDTktisQHq8k1Ooy6HXVyhk0syqo34H58fnd6QVqVBGJPeNaQ3DCeaoXOKu-tURlJjZRVqgWVRjKFmjqJjleBChJaETKR-_HKVpilBmm2Cb36pcYtSJgWuWY8c456S79WqjmzFrlRxii0AxjOgCtt20I8KFk8l_EqQVXpoS4D1GUL9QAOuxmv0_YZf9iuB5Q7uxbg7d-Hd2DRT5bTIppd6DWTd9yDBfvRPL1N9uO78QVeCLR4
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3fb9MwED6VgQQ8MOiG6DZGHnhBmhunsWP7ceqoitZGFZSpb5F_XCQklKE2g38f202rIiEk3iLrYlmfY905d999AO8LZbxTlYzoTDjCHDPEOF2QWuRCcFFLHlmudzNRlnK1UoseXO25MIgYi89wGB5jLt_d24fwqyyV1Affij-Cx5yxEd2ytfY5A8YjOdo7JEqUv8nskpJUpcv5PFRxieFI8CB7-ocTOlBViU5lcvx_y3kJL7rgMbne7vYr6GHTh-OdMEPSndM-PD_oMngC6Re_D0iuf-k1JhO9aZPPZFyWiQ9XkwU6jModTXKDbSzLak7h6-TjcjwlnU4CsaMibwk3rMi0QmeV99eojKRGyjrTgkojmUJNnURX1IEMEpoRMsH9eG1rzDODNH8NR819g28gYVpwzYrcOeot_VyZLpi1WBhljEI7gHQHXGW7JuJBy-J7FS8TVFUe6ipAXXVQD-DD_o0f2wYa_7A9CSjv7TqAz_4-_A6eTpfzWTX7VN6ewzM_kdyW1FzAUbt-wLfwxP5sv23Wl_E7-Q3x47e_
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=Scale-aware+Fast+R-CNN+for+Pedestrian+Detection&rft.jtitle=IEEE+transactions+on+multimedia&rft.au=Li%2C+Jianan&rft.au=Liang%2C+Xiaodan&rft.au=Shen%2C+ShengMei&rft.au=Xu%2C+Tingfa&rft.date=2018-04-01&rft.issn=1520-9210&rft.eissn=1941-0077&rft.spage=1&rft.epage=1&rft_id=info:doi/10.1109%2FTMM.2017.2759508&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TMM_2017_2759508
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