{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,21]],"date-time":"2026-03-21T03:32:49Z","timestamp":1774063969902,"version":"3.50.1"},"reference-count":60,"publisher":"Springer Science and Business Media LLC","issue":"9","license":[{"start":{"date-parts":[[2022,1,14]],"date-time":"2022-01-14T00:00:00Z","timestamp":1642118400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,14]],"date-time":"2022-01-14T00:00:00Z","timestamp":1642118400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2022,7]]},"DOI":"10.1007\/s10489-021-02798-1","type":"journal-article","created":{"date-parts":[[2022,1,14]],"date-time":"2022-01-14T14:04:41Z","timestamp":1642169081000},"page":"10430-10447","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":29,"title":["R-SSD: refined single shot multibox detector for pedestrian detection"],"prefix":"10.1007","volume":"52","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3065-6903","authenticated-orcid":false,"given":"Chaoqi","family":"Yan","sequence":"first","affiliation":[]},{"given":"Hong","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Xuliang","family":"Li","sequence":"additional","affiliation":[]},{"given":"Ding","family":"Yuan","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,1,14]]},"reference":[{"key":"2798_CR1","doi-asserted-by":"crossref","unstructured":"Bell S, Zitnick CL, Bala K, Girshick R (2016) Inside-outside net: Detecting objects in context with skip pooling and recurrent neural networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2874\u20132883","DOI":"10.1109\/CVPR.2016.314"},{"key":"2798_CR2","doi-asserted-by":"crossref","unstructured":"Bi HB, Lu D, Zhu HH, Yang LN, Guan HP (2020) Sta-net: spatial-temporal attention network for video salient object detection. Appl Intell:1\u201310","DOI":"10.1109\/TCDS.2021.3078824"},{"key":"2798_CR3","unstructured":"Bochkovskiy A, Wang CY, Liao HYM (2020) Yolov4: Optimal speed and accuracy of object detection. arXiv:2004.10934"},{"key":"2798_CR4","doi-asserted-by":"crossref","unstructured":"Cai Z, Fan Q, Feris RS, Vasconcelos N (2016) A unified multi-scale deep convolutional neural network for fast object detection. In: European conference on computer vision. Springer, pp 354\u2013370","DOI":"10.1007\/978-3-319-46493-0_22"},{"issue":"6","key":"2798_CR5","doi-asserted-by":"publisher","first-page":"1371","DOI":"10.1587\/transinf.2019EDP7285","volume":"103","author":"C Chen","year":"2020","unstructured":"Chen C, Xiao H, Liu Y, Zhang M (2020) Dual-task integrated network for fast pedestrian detection in crowded scenes. IEICE Trans Inf Syst 103(6):1371\u20131379","journal-title":"IEICE Trans Inf Syst"},{"key":"2798_CR6","doi-asserted-by":"crossref","unstructured":"Cordts M, Omran M, Ramos S, Rehfeld T, Enzweiler M, Benenson R, Franke U, Roth S, Schiele B (2016) The cityscapes dataset for semantic urban scene understanding. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3213\u20133223","DOI":"10.1109\/CVPR.2016.350"},{"key":"2798_CR7","doi-asserted-by":"crossref","unstructured":"Costea AD, Nedevschi S (2016) Semantic channels for fast pedestrian detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 2360\u20132368","DOI":"10.1109\/CVPR.2016.259"},{"key":"2798_CR8","unstructured":"Dai J, Li Y, He K, Sun J (2016) R-fcn: Object detection via region-based fully convolutional networks. arXiv:1605.06409"},{"key":"2798_CR9","doi-asserted-by":"crossref","unstructured":"Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. In: 2005 IEEE Computer society conference on computer vision and pattern recognition (CVPR\u201905), vol 1. IEEE, pp 886\u2013893","DOI":"10.1109\/CVPR.2005.177"},{"key":"2798_CR10","doi-asserted-by":"crossref","unstructured":"Deng J, Dong W, Socher R, Li LJ, Li K, Fei-Fei L (2009) Imagenet: a large-scale hierarchical image database. In: 2009 IEEE Conference on computer vision and pattern recognition. IEEE, pp 248\u2013255","DOI":"10.1109\/CVPR.2009.5206848"},{"issue":"8","key":"2798_CR11","doi-asserted-by":"publisher","first-page":"1532","DOI":"10.1109\/TPAMI.2014.2300479","volume":"36","author":"P Doll\u00e1r","year":"2014","unstructured":"Doll\u00e1r P, Appel R, Belongie S, Perona P (2014) Fast feature pyramids for object detection. IEEE Trans Pattern Anal Mach Intell 36(8):1532\u20131545","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2798_CR12","doi-asserted-by":"crossref","unstructured":"Doll\u00e1r P, Tu Z, Perona P, Belongie S (2009) Integral channel features","DOI":"10.5244\/C.23.91"},{"issue":"4","key":"2798_CR13","doi-asserted-by":"publisher","first-page":"743","DOI":"10.1109\/TPAMI.2011.155","volume":"34","author":"P Dollar","year":"2011","unstructured":"Dollar P, Wojek C, Schiele B, Perona P (2011) Pedestrian detection: an evaluation of the state of the art. IEEE Trans Pattern Anal Mach Intell 34(4):743\u2013761","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2798_CR14","doi-asserted-by":"crossref","unstructured":"Du X, El-Khamy M, Lee J, Davis L (2017) Fused dnn: a deep neural network fusion approach to fast and robust pedestrian detection. In: 2017 IEEE Winter conference on applications of computer vision (WACV). IEEE, pp 953\u2013961","DOI":"10.1109\/WACV.2017.111"},{"key":"2798_CR15","unstructured":"Du X, El-Khamy M, Morariu VI, Lee J, Davis L (2018) Fused deep neural networks for efficient pedestrian detection. arXiv:1805.08688"},{"issue":"2","key":"2798_CR16","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham M, Van Gool L, Williams CK, Winn J, Zisserman A (2010) The pascal visual object classes (voc) challenge. Int J Comput Vis 88(2):303\u2013338","journal-title":"Int J Comput Vis"},{"key":"2798_CR17","doi-asserted-by":"crossref","unstructured":"Felzenszwalb P, McAllester D, Ramanan D (2008) A discriminatively trained, multiscale, deformable part model. In: 2008 IEEE Conference on Computer Vision and Pattern Recognition. IEEE, pp 1\u20138","DOI":"10.1109\/CVPR.2008.4587597"},{"issue":"9","key":"2798_CR18","doi-asserted-by":"publisher","first-page":"1627","DOI":"10.1109\/TPAMI.2009.167","volume":"32","author":"PF Felzenszwalb","year":"2009","unstructured":"Felzenszwalb PF, Girshick R, McAllester D, Ramanan D (2009) Object detection with discriminatively trained part-based models. IEEE Trans Pattern Anal Mach Intell 32(9):1627\u20131645","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2798_CR19","unstructured":"Fu CY, Liu W, Ranga A, Tyagi A, Berg AC (2017) Dssd: Deconvolutional single shot detector. arXiv:1701.06659"},{"key":"2798_CR20","doi-asserted-by":"crossref","unstructured":"Gidaris S, Komodakis N (2015) Object detection via a multi-region and semantic segmentation-aware cnn model. In: Proceedings of the IEEE international conference on computer vision, pp 1134\u20131142","DOI":"10.1109\/ICCV.2015.135"},{"key":"2798_CR21","doi-asserted-by":"crossref","unstructured":"Girshick R (2015) Fast r-cnn. In: Proceedings of the IEEE international conference on computer vision, pp 1440\u20131448","DOI":"10.1109\/ICCV.2015.169"},{"key":"2798_CR22","doi-asserted-by":"crossref","unstructured":"Girshick R, Donahue J, Darrell T, Malik J (2014) Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 580\u2013587","DOI":"10.1109\/CVPR.2014.81"},{"key":"2798_CR23","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"2798_CR24","doi-asserted-by":"crossref","unstructured":"Huang G, Liu Z, Van Der Maaten L, Weinberger KQ (2017) Densely connected convolutional networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4700\u20134708","DOI":"10.1109\/CVPR.2017.243"},{"key":"2798_CR25","unstructured":"Li Z, Zhou F (2017) Fssd: feature fusion single shot multibox detector. arXiv:1712.00960"},{"key":"2798_CR26","doi-asserted-by":"crossref","unstructured":"Lin C, Lu J, Wang G, Zhou J (2018) Graininess-aware deep feature learning for pedestrian detection. In: Proceedings of the European Conference on Computer Vision (ECCV), pp 732\u2013747","DOI":"10.1007\/978-3-030-01240-3_45"},{"key":"2798_CR27","doi-asserted-by":"crossref","unstructured":"Lin Z, Hua G, Davis LS (2009) Multiple instance ffeature for robust part-based object detection. In: 2009 IEEE Conference on computer vision and pattern recognition. IEEE, pp 405\u2013412","DOI":"10.1109\/CVPR.2009.5206858"},{"key":"2798_CR28","doi-asserted-by":"crossref","unstructured":"Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu CY, Berg AC (2016) Ssd: Single shot multibox detector. In: European conference on computer vision. Springer, pp 21\u201337","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"2798_CR29","doi-asserted-by":"crossref","unstructured":"Liu W, Liao S, Hu W, Liang X, Chen X (2018) Learning efficient single-stage pedestrian detectors by asymptotic localization fitting. In: Proceedings of the European Conference on Computer Vision (ECCV), pp 618\u2013634","DOI":"10.1007\/978-3-030-01264-9_38"},{"key":"2798_CR30","doi-asserted-by":"crossref","unstructured":"Liu W, Liao S, Ren W, Hu W, Yu Y (2019) High-level semantic feature detection: a new perspective for pedestrian detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 5187\u20135196","DOI":"10.1109\/CVPR.2019.00533"},{"issue":"4","key":"2798_CR31","doi-asserted-by":"publisher","first-page":"349","DOI":"10.1109\/34.917571","volume":"23","author":"A Mohan","year":"2001","unstructured":"Mohan A, Papageorgiou C, Poggio T (2001) Example-based object detection in images by components. IEEE Trans Pattern Anal Mach Intell 23(4):349\u2013361","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2798_CR32","first-page":"424","volume":"27","author":"W Nam","year":"2014","unstructured":"Nam W, Doll\u00e1r P, Han JH (2014) Local decorrelation for improved pedestrian detection. Adv Neural Inf Process Syst 27:424\u2013432","journal-title":"Adv Neural Inf Process Syst"},{"issue":"8","key":"2798_CR33","doi-asserted-by":"publisher","first-page":"1874","DOI":"10.1109\/TPAMI.2017.2738645","volume":"40","author":"W Ouyang","year":"2017","unstructured":"Ouyang W, Zhou H, Li H, Li Q, Yan J, Wang X (2017) Jointly learning deep features, deformable parts, occlusion and classification for pedestrian detection. IEEE Trans Pattern Anal Mach Intell 40 (8):1874\u20131887","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2798_CR34","doi-asserted-by":"crossref","unstructured":"Pang Y, Xie J, Khan MH, Anwer RM, Khan FS, Shao L (2019) Mask-guided attention network for occluded pedestrian detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp 4967\u20134975","DOI":"10.1109\/ICCV.2019.00507"},{"key":"2798_CR35","doi-asserted-by":"crossref","unstructured":"Redmon J, Divvala S, Girshick R, Farhadi A (2016) You only look once: Unified, real-time object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 779\u2013788","DOI":"10.1109\/CVPR.2016.91"},{"key":"2798_CR36","unstructured":"Redmon J, Farhadi A (2018) Yolov3: An incremental improvement. arXiv:1804.02767"},{"key":"2798_CR37","unstructured":"Ren S, He K, Girshick R, Sun J (2015) Faster r-cnn: Towards real-time object detection with region proposal networks. arXiv:1506.01497"},{"key":"2798_CR38","doi-asserted-by":"crossref","unstructured":"Ren X, Ramanan D (2013) Histograms of sparse codes for object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3246\u20133253","DOI":"10.1109\/CVPR.2013.417"},{"key":"2798_CR39","doi-asserted-by":"crossref","unstructured":"Saeidi M, Ahmadi A (2020) High-performance and deep pedestrian detection based on estimation of different parts. J Supercomput:1\u201336","DOI":"10.1007\/s11227-020-03345-4"},{"key":"2798_CR40","unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556"},{"key":"2798_CR41","doi-asserted-by":"crossref","unstructured":"Song T, Sun L, Xie D, Sun H, Pu S (2018) Small-scale pedestrian detection based on topological line localization and temporal feature aggregation. In: Proceedings of the European Conference on Computer Vision (ECCV), pp 536\u2013551","DOI":"10.1007\/978-3-030-01234-2_33"},{"key":"2798_CR42","doi-asserted-by":"crossref","unstructured":"Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2015) Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 1\u20139","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"2798_CR43","unstructured":"Szegedy C, Reed S, Erhan D, Anguelov D, Ioffe S (2014) Scalable, high-quality object detection. arXiv:1412.1441"},{"key":"2798_CR44","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.neucom.2019.12.110","volume":"389","author":"FB Tesema","year":"2020","unstructured":"Tesema FB, Wu H, Chen M, Lin J, Zhu W, Huang K (2020) Hybrid channel based pedestrian detection. Neurocomputing 389:1\u20138","journal-title":"Neurocomputing"},{"issue":"2","key":"2798_CR45","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1023\/B:VISI.0000013087.49260.fb","volume":"57","author":"P Viola","year":"2004","unstructured":"Viola P, Jones MJ (2004) Robust real-time face detection. Int J Comput Vis 57(2):137\u2013154","journal-title":"Int J Comput Vis"},{"issue":"2","key":"2798_CR46","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1007\/s11263-005-6644-8","volume":"63","author":"P Viola","year":"2005","unstructured":"Viola P, Jones MJ, Snow D (2005) Detecting pedestrians using patterns of motion and appearance. Int J Comput Vis 63(2):153\u2013161","journal-title":"Int J Comput Vis"},{"issue":"6","key":"2798_CR47","doi-asserted-by":"publisher","first-page":"4144","DOI":"10.1109\/TVT.2015.2509465","volume":"65","author":"K Wang","year":"2015","unstructured":"Wang K, Liu Y, Gou C, Wang FY (2015) A multi-view learning approach to foreground detection for traffic surveillance applications. IEEE Trans Veh Technol 65(6):4144\u20134158","journal-title":"IEEE Trans Veh Technol"},{"key":"2798_CR48","doi-asserted-by":"crossref","unstructured":"Wang S, Cheng J, Liu H, Tang M (2018) Pcn: Part and context information for pedestrian detection with cnns. arXiv:1804.04483","DOI":"10.5244\/C.31.34"},{"issue":"2","key":"2798_CR49","doi-asserted-by":"publisher","first-page":"361","DOI":"10.1109\/TPAMI.2013.124","volume":"36","author":"X Wang","year":"2013","unstructured":"Wang X, Wang M, Li W (2013) Scene-specific pedestrian detection for static video surveillance. IEEE Trans Pattern Anal Mach Intell 36(2):361\u2013374","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2798_CR50","doi-asserted-by":"crossref","unstructured":"Wang X, Xiao T, Jiang Y, Shao S, Sun J, Shen C (2018) Repulsion loss: Detecting pedestrians in a crowd. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 7774\u20137783","DOI":"10.1109\/CVPR.2018.00811"},{"key":"2798_CR51","doi-asserted-by":"publisher","first-page":"332","DOI":"10.1016\/j.patcog.2018.10.028","volume":"87","author":"J Xiao","year":"2019","unstructured":"Xiao J, Xie Y, Tillo T, Huang K, Wei Y, Feng J (2019) Ian: the individual aggregation network for person search. Pattern Recogn 87:332\u2013340","journal-title":"Pattern Recogn"},{"issue":"3","key":"2798_CR52","doi-asserted-by":"publisher","first-page":"1200","DOI":"10.1007\/s10489-018-1326-8","volume":"49","author":"H Xie","year":"2019","unstructured":"Xie H, Chen Y, Shin H (2019) Context-aware pedestrian detection especially for small-sized instances with deconvolution integrated faster rcnn (dif r-cnn). Appl Intell 49(3):1200\u20131211","journal-title":"Appl Intell"},{"key":"2798_CR53","doi-asserted-by":"crossref","unstructured":"Xie S, Girshick R, Doll\u00e1r P, Tu Z, He K (2017) Aggregated residual transformations for deep neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 1492\u20131500","DOI":"10.1109\/CVPR.2017.634"},{"key":"2798_CR54","doi-asserted-by":"crossref","unstructured":"Zhang L, Lin L, Liang X, He K (2016) Is faster r-cnn doing well for pedestrian detection?. In: European Conference on Computer Vision. Springer, pp 443\u2013457","DOI":"10.1007\/978-3-319-46475-6_28"},{"key":"2798_CR55","doi-asserted-by":"crossref","unstructured":"Zhang S, Benenson R, Omran M, Hosang J, Schiele B (2016) How far are we from solving pedestrian detection?. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 1259\u20131267","DOI":"10.1109\/CVPR.2016.141"},{"key":"2798_CR56","doi-asserted-by":"crossref","unstructured":"Zhang S, Benenson R, Schiele B (2017) Citypersons: a diverse dataset for pedestrian detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 3213\u20133221","DOI":"10.1109\/CVPR.2017.474"},{"key":"2798_CR57","doi-asserted-by":"crossref","unstructured":"Zhang S, Benenson R, Schiele B, et al. (2015) Filtered channel features for pedestrian detection. In: CVPR, vol 1, p. 4","DOI":"10.1109\/CVPR.2015.7298784"},{"key":"2798_CR58","doi-asserted-by":"crossref","unstructured":"Zhang S, Wen L, Bian X, Lei Z, Li SZ (2018) Occlusion-aware r-cnn: detecting pedestrians in a crowd. In: Proceedings of the European Conference on Computer Vision (ECCV), pp 637\u2013 653","DOI":"10.1007\/978-3-030-01219-9_39"},{"key":"2798_CR59","doi-asserted-by":"crossref","unstructured":"Zhang S, Yang J, Schiele B (2018) Occluded pedestrian detection through guided attention in cnns. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 6995\u20137003","DOI":"10.1109\/CVPR.2018.00731"},{"key":"2798_CR60","doi-asserted-by":"publisher","first-page":"114","DOI":"10.1016\/j.neucom.2019.03.095","volume":"394","author":"W Zhang","year":"2020","unstructured":"Zhang W, Wang K, Liu Y, Lu Y, Wang FY (2020) A parallel vision approach to scene-specific pedestrian detection. Neurocomputing 394:114\u2013126","journal-title":"Neurocomputing"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-021-02798-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-021-02798-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-021-02798-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,20]],"date-time":"2022-06-20T07:41:02Z","timestamp":1655710862000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-021-02798-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1,14]]},"references-count":60,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2022,7]]}},"alternative-id":["2798"],"URL":"https:\/\/doi.org\/10.1007\/s10489-021-02798-1","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"value":"0924-669X","type":"print"},{"value":"1573-7497","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,1,14]]},"assertion":[{"value":"25 August 2021","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 January 2022","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Compliance with Ethical Standards"}},{"value":"None.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"<!--Emphasis Type='Bold' removed-->Competing interests"}}]}}