{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T03:31:03Z","timestamp":1762918263433,"version":"3.37.3"},"reference-count":58,"publisher":"Springer Science and Business Media LLC","issue":"23","license":[{"start":{"date-parts":[[2021,7,7]],"date-time":"2021-07-07T00:00:00Z","timestamp":1625616000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,7,7]],"date-time":"2021-07-07T00:00:00Z","timestamp":1625616000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61873246"],"award-info":[{"award-number":["61873246"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput & Applic"],"published-print":{"date-parts":[[2021,12]]},"DOI":"10.1007\/s00521-021-06265-3","type":"journal-article","created":{"date-parts":[[2021,7,7]],"date-time":"2021-07-07T11:02:52Z","timestamp":1625655772000},"page":"16697-16712","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Learning efficient single stage pedestrian detection by squeeze-and-excitation network"],"prefix":"10.1007","volume":"33","author":[{"given":"Lu","family":"Ding","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0578-8023","authenticated-orcid":false,"given":"Yong","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Robert","family":"Lagani\u00e8re","sequence":"additional","affiliation":[]},{"given":"Xinbin","family":"Luo","sequence":"additional","affiliation":[]},{"given":"Dan","family":"Huang","sequence":"additional","affiliation":[]},{"given":"Huanlong","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,7,7]]},"reference":[{"key":"6265_CR1","doi-asserted-by":"crossref","unstructured":"Angelova A, Krizhevsky A, Vanhoucke V, Ogale A, Ferguson D (2015) Real-time pedestrian detection with deep network cascades. In: Xie X, Jones MW, Tam GKL (eds) Proceedings of the British machine vision conference (BMVC), pp 32.1\u201332.12. BMVA Press","DOI":"10.5244\/C.29.32"},{"key":"6265_CR2","doi-asserted-by":"crossref","unstructured":"Brazil G, Yin X, Liu X (2017) Illuminating pedestrians via simultaneous detection segmentation. arXiv:1706.08564","DOI":"10.1109\/ICCV.2017.530"},{"key":"6265_CR3","doi-asserted-by":"crossref","unstructured":"Bell S, Lawrence Zitnick C, 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":"6265_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, Cham, pp 354\u2013370","DOI":"10.1007\/978-3-319-46493-0_22"},{"key":"6265_CR5","doi-asserted-by":"crossref","unstructured":"Cai Z, Vasconcelos N (2017) Cascade r-CNN: delving into high quality object detection. In: ICCV, pp 4950\u20134959","DOI":"10.1109\/CVPR.2018.00644"},{"key":"6265_CR6","doi-asserted-by":"crossref","unstructured":"Cao Y, Xu J, Lin S, Wei F, Hu H (2019) GCNet: non-local networks meet squeeze-excitation networks and beyond. arXiv:1904.11492","DOI":"10.1109\/ICCVW.2019.00246"},{"key":"6265_CR7","unstructured":"Dai J, Li Y, He K, Sun J (2016) R-FCN, Object detection via region-based fully convolutional networks. In: Advances in neural information processing systems, pp 379\u2013387"},{"key":"6265_CR8","doi-asserted-by":"crossref","unstructured":"Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. In: Proc. IEEE conf.comput. vis. pattern recogn., pp 886\u2013893","DOI":"10.1109\/CVPR.2005.177"},{"key":"6265_CR9","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: Applications of computer vision (WACV), IEEE winter conference on, pp 953-961","DOI":"10.1109\/WACV.2017.111"},{"key":"6265_CR10","doi-asserted-by":"publisher","unstructured":"Dollar P, Wojek C, Schiele B, Perona P (2009) Pedestrian detection: a benchmark. In: IEEE conference on computer vision and pattern recognition, pp 304\u2013311. https:\/\/doi.org\/10.1109\/CVPR.2009.5206631","DOI":"10.1109\/CVPR.2009.5206631"},{"issue":"8","key":"6265_CR11","doi-asserted-by":"publisher","first-page":"1532","DOI":"10.1109\/TPAMI.2014.2300479","volume":"36","author":"P Dollar","year":"2014","unstructured":"Dollar 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":"6265_CR12","doi-asserted-by":"crossref","unstructured":"Ess A, Leibe B, Van Gool L (2007) Depth and appearance for mobile scene analysis. In: IEEE international conference on computer vision (ICCV)","DOI":"10.1109\/ICCV.2007.4409092"},{"key":"6265_CR13","unstructured":"Fu CY, Liu W, Ranga A, Tyagi A, Berg AC (2017) Dssd: deconvolutional single shot detector. arXiv:1701.06659"},{"key":"6265_CR14","doi-asserted-by":"crossref","unstructured":"Geiger A, Lenz P, Urtasun R (2012) Are we ready for autonomous driving? the kitti vision benchmark suite. In: IEEE conference on computer vision and pattern recognition (CVPR)","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"6265_CR15","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: Computer vision and pattern recognition (CVPR)","DOI":"10.1109\/CVPR.2014.81"},{"key":"6265_CR16","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":"6265_CR17","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":"6265_CR18","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":"6265_CR19","doi-asserted-by":"crossref","unstructured":"Hosang J, Omran M, Benenson R, Schiele B (2015) Taking a deeper look at pedestrians. In: IEEE conference on computer vision and pattern recognition CVPR","DOI":"10.1109\/CVPR.2015.7299034"},{"key":"6265_CR20","doi-asserted-by":"crossref","unstructured":"Hu J, Shen L, Sun G (2018) Squeeze-and-excitation networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7132\u20137141","DOI":"10.1109\/CVPR.2018.00745"},{"issue":"6","key":"6265_CR21","doi-asserted-by":"publisher","first-page":"1358","DOI":"10.1109\/TCSVT.2017.2648850","volume":"28","author":"Q Hu","year":"2018","unstructured":"Hu Q, Wang P, Shen C, van den Hengel A, Porikli F (2018) Pushing the limits of deep CNNs for pedestrian detection. IEEE Trans Circuits Syst Video Technol 28(6):1358\u20131368. https:\/\/doi.org\/10.1109\/TCSVT.2017.2648850","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"6265_CR22","unstructured":"Howard AG, Zhu M, Chen B, Kalenichenko D, Wang W, Weyand T, Andreetto M, Adam H (2017) Mobilenets: efficient convolutional neural networks for mobile vision applications. arXiv:1704.04861"},{"key":"6265_CR23","doi-asserted-by":"publisher","first-page":"188","DOI":"10.1016\/j.neucom.2018.09.081","volume":"323","author":"Y Ji","year":"2019","unstructured":"Ji Y, Zhang H, Tseng KK, Chow TW, Wu QJ (2019) Graph model-based salient object detection using objectness and multiple saliency cues. Neurocomputing 323:188\u2013202","journal-title":"Neurocomputing"},{"key":"6265_CR24","unstructured":"Ji Y, Zhang H, Jie Z, Ma L, Wu QMJ (2020) Casnet: a cross-attention Siamese network for video salient object detection. IEEE Trans Neural Netw Learn Syst PP(99), 1-15"},{"key":"6265_CR25","doi-asserted-by":"crossref","unstructured":"Kong T, Sun F, Tan C, Liu H, Huang W (2018) Deep feature pyramid reconfiguration for object detection. In: Proceedings of the European conference on computer vision (ECCV), pp 169\u2013185","DOI":"10.1007\/978-3-030-01228-1_11"},{"key":"6265_CR26","doi-asserted-by":"crossref","unstructured":"Kong T, Yao A, Chen Y, Sun F (2016) Hypernet: towards accurate region proposal generation and joint object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 845\u2013853","DOI":"10.1109\/CVPR.2016.98"},{"key":"6265_CR27","doi-asserted-by":"crossref","unstructured":"Kong T, Sun F, Yao A, Liu H, Lu M, Chen Y (2017) Ron: reverse connection with objectness prior networks for object detection. arXiv:1707.01691","DOI":"10.1109\/CVPR.2017.557"},{"key":"6265_CR28","unstructured":"Lee H, Eum S, Kwon H (2017) Me r-CNN: multi-expert region-based CNN for object detection. arXiv:1704.01069"},{"issue":"4","key":"6265_CR29","doi-asserted-by":"publisher","first-page":"985","DOI":"10.1109\/TMM.2017.2759508","volume":"20","author":"J Li","year":"2017","unstructured":"Li J, Liang X, Shen S, Xu T, Feng J, Yan S (2017) Scale-aware fast R-CNN for pedestrian detection. IEEE Trans Multimed 20(4):985\u2013996. https:\/\/doi.org\/10.1109\/TMM.2017.2759508","journal-title":"IEEE Trans Multimed"},{"key":"6265_CR30","doi-asserted-by":"crossref","unstructured":"Li X, Wang W, Hu X, Yang J (2019) Selective kernel networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 510\u2013519","DOI":"10.1109\/CVPR.2019.00060"},{"key":"6265_CR31","doi-asserted-by":"crossref","unstructured":"Lin YT, Dollar P, Girshick R, He K, Hariharan B, Belongie S (2016) Feature pyramid networks for object detection. arXiv:1612.03144","DOI":"10.1109\/CVPR.2017.106"},{"key":"6265_CR32","doi-asserted-by":"crossref","unstructured":"Lin YT, Goyal P, Girshick R, He K, Dollar P (2017) Focal loss for dense object detection. arXiv:1708.02002","DOI":"10.1109\/ICCV.2017.324"},{"key":"6265_CR33","doi-asserted-by":"crossref","unstructured":"Lin C, Lu J, Wang G, Zhou J (2018) Graininess-aware deep feature learning for pedestrian detection. In: The European conference on computer vision (ECCV)","DOI":"10.1007\/978-3-030-01240-3_45"},{"key":"6265_CR34","unstructured":"Lin M, Chen Q, Yan S (2013) Network in network. arXiv:1312.4400"},{"key":"6265_CR35","doi-asserted-by":"crossref","unstructured":"Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu C-Y, 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":"6265_CR36","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: The European conference on computer vision (ECCV)","DOI":"10.1007\/978-3-030-01264-9_38"},{"key":"6265_CR37","doi-asserted-by":"crossref","unstructured":"Mao J, Xiao T, Jiang Y, Cao Z (2017) What can help pedestrian detection? In: The IEEE conference on computer vision and pattern recognition (CVPR), vol 1, p 3","DOI":"10.1109\/CVPR.2017.639"},{"key":"6265_CR38","unstructured":"Nam W, Dollar P, Han JH (2014) Local decorrelation for improved pedestrian detection. In: Advances in neural information processing systems, pp 424\u2013432"},{"key":"6265_CR39","doi-asserted-by":"crossref","unstructured":"Paisitkriangkrai S, Shen C, den Hengel A (2014) Strengthening the effectiveness of pedestrian detection with spatially pooled features. In: Proc. Eur. conf. comput. vis, pp 546\u2013561","DOI":"10.1007\/978-3-319-10593-2_36"},{"key":"6265_CR40","doi-asserted-by":"publisher","unstructured":"Redmon J, Divvala S, Girshick R, Farhadi A (2016) You only look once: unified, real-time object detection. In: 2016 IEEE conference on computer vision and pattern recognition (CVPR), pp 779\u2013788. https:\/\/doi.org\/10.1109\/CVPR.2016.91","DOI":"10.1109\/CVPR.2016.91"},{"key":"6265_CR41","unstructured":"Ren S, He K, Girshick R, Sun J (2015) Faster r-CNN: towards real-time object detection with region proposal networks. In: Advances in neural information processing systems, pp 91\u201399"},{"issue":"3","key":"6265_CR42","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky O, Deng J, Su H, Krause J, Satheesh S, Ma S, Huang Z, Karpathy A, Khosla A, Bernstein M, Berg AC, Li F-F (2015) ImageNet large scale visual recognition challenge. Int J Comput Vis (IJCV) 115(3):211\u2013252","journal-title":"Int J Comput Vis (IJCV)"},{"key":"6265_CR43","unstructured":"Shrivastava A, Gupta A, Girshick R, Training region-based object detectors with online hard example mining. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 761\u2013769"},{"key":"6265_CR44","doi-asserted-by":"crossref","unstructured":"Shrivastava A, Gupta A (2016) Contextual priming and feedback for faster r-CNN. In: European conference on computer vision. Springer, pp 330\u2013348","DOI":"10.1007\/978-3-319-46448-0_20"},{"key":"6265_CR45","doi-asserted-by":"crossref","unstructured":"Shen Z, Liu Z, Li J, Jiang YG, Chen Y, Xue X (2017) Dsod: learning deeply supervised object detectors from scratch. In: The IEEE international conference on computer vision (ICCV), vol 3, p 7","DOI":"10.1109\/ICCV.2017.212"},{"key":"6265_CR46","unstructured":"Simonyan K, Zisserman A (2015) Very deep convolutional networks for large scale image recognition. In: ICLR"},{"key":"6265_CR47","doi-asserted-by":"crossref","unstructured":"Tian Y, Luo P, Wang X, Tang X (2015) Pedestrian detection aided by deep learning semantic tasks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5079\u20135087","DOI":"10.1109\/CVPR.2015.7299143"},{"key":"6265_CR48","doi-asserted-by":"publisher","unstructured":"Tian Y, Luo P, Wang X, Tang X (2015) Pedestrian detection aided by deep learning semantic tasks. In: 2015 IEEE conference on computer vision and pattern recognition (CVPR), pp 5079\u20135087. https:\/\/doi.org\/10.1109\/CVPR.2015.7299143","DOI":"10.1109\/CVPR.2015.7299143"},{"key":"6265_CR49","doi-asserted-by":"crossref","unstructured":"Verbickas R, Laganiere R, Laroche D, Zhu C, Xu X, Ors A (2017) SqueezeMap: fast pedestrian detection on a low-power automotive processor using efficient convolutional neural networks. In: CVPR workshops, pp 463\u2013471","DOI":"10.1109\/CVPRW.2017.62"},{"key":"6265_CR50","doi-asserted-by":"crossref","unstructured":"Wang X, Shrivastava A, Gupta A (2017) A-fast-rCNN: hard positive generation via adversary for object detection. arXiv:1704.03414","DOI":"10.1109\/CVPR.2017.324"},{"key":"6265_CR51","doi-asserted-by":"crossref","unstructured":"Wang X, Xiao T, Jiang Y, Shao S, Sun J, Shen C (2017) Repulsion loss: detecting pedestrians in a crowd. arXiv:1711.07752","DOI":"10.1109\/CVPR.2018.00811"},{"key":"6265_CR52","unstructured":"Yonglong T, Ping L, Xiaogang W, Tang X (2015) Deep learning strong parts for pedestrian detection. In: Proceedings of the IEEE international conference on computer vision, pp 1904\u20131912"},{"key":"6265_CR53","doi-asserted-by":"publisher","first-page":"835","DOI":"10.1016\/j.ins.2020.09.003","volume":"546","author":"J Yuzhu","year":"2021","unstructured":"Yuzhu J, Haijun Z, Zhao Z, Ming L (2021) CNN-based encoder-decoder networks for salient object detection: a comprehensive review and recent advances. Inf Sci 546:835\u2013857","journal-title":"Inf Sci"},{"key":"6265_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: ECCV","DOI":"10.1007\/978-3-319-46475-6_28"},{"key":"6265_CR55","doi-asserted-by":"crossref","unstructured":"Zhang S, Benenson R, Schiele B (2017) Citypersons: a diverse dataset for pedestrian detection. arXiv:1702.05693","DOI":"10.1109\/CVPR.2017.474"},{"key":"6265_CR56","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":"6265_CR57","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: The European conference on computer vision (ECCV)","DOI":"10.1007\/978-3-030-01219-9_39"},{"key":"6265_CR58","doi-asserted-by":"crossref","unstructured":"Zhou C, Yuan J (2018) Bi-box regression for pedestrian detection and occlusion estimation. In: The European conference on computer vision (ECCV)","DOI":"10.1007\/978-3-030-01246-5_9"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-021-06265-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-021-06265-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-021-06265-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,11,3]],"date-time":"2021-11-03T18:16:37Z","timestamp":1635963397000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-021-06265-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,7]]},"references-count":58,"journal-issue":{"issue":"23","published-print":{"date-parts":[[2021,12]]}},"alternative-id":["6265"],"URL":"https:\/\/doi.org\/10.1007\/s00521-021-06265-3","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"type":"print","value":"0941-0643"},{"type":"electronic","value":"1433-3058"}],"subject":[],"published":{"date-parts":[[2021,7,7]]},"assertion":[{"value":"19 August 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 June 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 July 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}