{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,31]],"date-time":"2025-03-31T02:52:13Z","timestamp":1743389533921,"version":"3.30.1"},"reference-count":62,"publisher":"Tech Science Press","issue":"2","license":[{"start":{"date-parts":[[2022,5,24]],"date-time":"2022-05-24T00:00:00Z","timestamp":1653350400000},"content-version":"vor","delay-in-days":508,"URL":"https:\/\/doi.org\/10.32604\/TSP-CROSSMARKPOLICY"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.32604\/csse.2021.017016","type":"journal-article","created":{"date-parts":[[2021,4,25]],"date-time":"2021-04-25T10:28:43Z","timestamp":1619346523000},"page":"165-182","update-policy":"https:\/\/doi.org\/10.32604\/tsp-crossmarkpolicy","source":"Crossref","is-referenced-by-count":35,"title":["Deep Learning for Object Detection: A Survey"],"prefix":"10.32604","volume":"38","author":[{"given":"Jun","family":"Wang","sequence":"first","affiliation":[]},{"given":"Tingjuan","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Yong","family":"Cheng","sequence":"additional","affiliation":[]},{"given":"Najla","family":"Al-Nabhan","sequence":"additional","affiliation":[]}],"member":"17807","reference":[{"key":"ref1","series-title":"Proc. of the IEEE Int. Conf. on Computer Vision","first-page":"89","article-title":"Ensemble of exemplar-svms for object detection aeyond","author":"Malisiewicz","year":"2011"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","article-title":"The pascal visual object classes (voc) challenge","volume":"88","author":"Everingham","year":"2010","journal-title":"International Journal of Computer Vision"},{"key":"ref3","first-page":"205","article-title":"Visual object detection and tracking using analytical learning approach of validity level","volume":"25","author":"Lee","year":"2019","journal-title":"Intelligent Automation & Soft Computing"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","article-title":"Distinctive image features from scale-invariant keypoints","volume":"60","author":"Lowe","year":"2004","journal-title":"International Journal of Computer Vision"},{"key":"ref5","series-title":"Proc. of the IEEE Int. Conf. on Computer Vision","first-page":"1440","article-title":"Fast r-cnn","author":"Girshick","year":"2015"},{"key":"ref6","series-title":"Proc. of the IEEE Computer Society Conf. on Computer Vision and Pattern Recognition","first-page":"1491","article-title":"Fast human detection using a cascade of histograms of oriented gradients","author":"Zhu","year":"2006"},{"key":"ref7","series-title":"Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition","first-page":"1","article-title":"Classification using intersection kernel support vector machines is efficient","author":"Maji","year":"2008"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"98","DOI":"10.1007\/s11263-014-0733-5","article-title":"The pascal visual object classes challenge: A retrospective","volume":"111","author":"Everingham","year":"2015","journal-title":"International Journal of Computer Vision"},{"key":"ref9","series-title":"Proc. of the European Conf. on Computer Vision","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"Lin","year":"2014"},{"key":"ref10","series-title":"Proc. of the IEEE Int. Conf. on Computer Vision","first-page":"1879","article-title":"Segmentation as selective search for object recognition","author":"Van de Sande","year":"2011"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"154","DOI":"10.1007\/s11263-013-0620-5","article-title":"Selective search for object recognition","volume":"104","author":"Uijlings","year":"2013","journal-title":"International Journal of Computer Vision"},{"key":"ref12","series-title":"Proc. of the IEEE Computer Society Conf. on Computer Vision and Pattern Recognition","first-page":"3241","article-title":"Constrained parametric min-cuts for automatic object segmentation","author":"Carreira","year":"2010"},{"key":"ref13","series-title":"Proc. the IEEE Conf. on Computer Vision and Pattern Recognition","first-page":"328","article-title":"Multiscale combinatorial grouping","author":"Arbel\u00e1ez","year":"2014"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"2189","DOI":"10.1109\/TPAMI.2012.28","article-title":"Measuring the objectness of image windows","volume":"34","author":"Alexe","year":"2012","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"ref15","series-title":"Proc. the IEEE Conf. on Computer Vision and Pattern Recognition","first-page":"3286","article-title":"BING: Binarized normed gradients for objectness estimation at 300fps","author":"Cheng","year":"2014"},{"key":"ref16","series-title":"Proc. of the European Conf. on Computer Vision","first-page":"391","article-title":"Edge boxes: Locating object proposals from edges","author":"Zitnick","year":"2014"},{"key":"ref17","unstructured":"C.Szegedy, S.Reed, D.Erhan, D.Anguelov and S.Ioffe, \u201cScalable, high-quality object detection,\u201d in arXiv preprint arXiv, 1412.1441, 2014."},{"key":"ref18","series-title":"Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition","first-page":"2147","article-title":"Scalable object detection using deep neural networks","author":"Erhan","year":"2014"},{"key":"ref19","series-title":"Proc. of the IEEE Int. Conf. on Computer Vision","first-page":"2479","article-title":"Deepbox: Learning objectness with convolutional networks","author":"Kuo","year":"2015"},{"key":"ref20","doi-asserted-by":"crossref","unstructured":"S.Gidaris and N.Komodakis, \u201cAttend refine repeat: Active box proposal generation via in-out localization,\u201d in arXiv preprint arXiv, 1606.04446, 2016.","DOI":"10.5244\/C.30.90"},{"key":"ref21","unstructured":"H.Li, Y.Liu, W.Ouyang and X.Wang, \u201cZoom out-and-in network with recursive training for object proposal,\u201d in arXiv preprint arXiv, 1702.05711, 2017."},{"key":"ref22","series-title":"Proc. of the AAAI Conf. on Artificial Intelligence","article-title":"R-fcn++: Towards accurate region-based fully convolutional networks for object detection","author":"Li","year":"2018"},{"key":"ref23","first-page":"769","article-title":"Ott messages modeling and classification based on recurrent neural networks","volume":"63","author":"Yang","year":"2020","journal-title":"Computers, Materials & Continua"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"944","DOI":"10.1109\/TMM.2016.2642789","article-title":"Attentive contexts for object detection","volume":"19","author":"Li","year":"2017","journal-title":"IEEE Transactions on Multimedia"},{"key":"ref25","doi-asserted-by":"crossref","first-page":"1627","DOI":"10.1109\/TPAMI.2009.167","article-title":"Object detection with discriminatively trained part-based models","volume":"32","author":"Felzenszwalb","year":"2010","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"ref26","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s11263-011-0439-x","article-title":"Discriminative models for multi-class object layout","volume":"95","author":"Desai","year":"2011","journal-title":"International Journal of Computer Vision"},{"key":"ref27","doi-asserted-by":"crossref","first-page":"3210","DOI":"10.1109\/TIP.2017.2694224","article-title":"Learning multilayer channel features for pedestrian detection","volume":"26","author":"Cao","year":"2017","journal-title":"IEEE Transactions on Image Processing"},{"key":"ref28","doi-asserted-by":"crossref","first-page":"113","DOI":"10.32604\/jai.2020.010137","article-title":"Impolite pedestrian detection by using enhanced YOLOv3-Tiny","volume":"2","author":"Wang","year":"2020","journal-title":"Journal on Artificial Intelligence"},{"key":"ref29","doi-asserted-by":"crossref","first-page":"1358","DOI":"10.1109\/TCSVT.2017.2648850","article-title":"Pushing the limits of deep cnns for pedestrian detection","volume":"28","author":"Hu","year":"2018","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"ref30","series-title":"Proc. of the IEEE Computer Society Conf. on Computer Vision and Pattern Recognition","first-page":"886","article-title":"Histograms of oriented gradients for human detection","author":"Dalal","year":"2005"},{"key":"ref31","series-title":"Proc. of the European Conf. on Computer Vision","first-page":"443","article-title":"Is faster R-CNN doing well for pedestrian detection?","author":"Zhang","year":"2016"},{"key":"ref32","series-title":"Proc. of the IEEE conf. on Computer Vision and Pattern Recognition","first-page":"304","article-title":"Pedestrian detection: A benchmark","author":"Doll\u00e1r","year":"2009"},{"key":"ref33","doi-asserted-by":"crossref","first-page":"743","DOI":"10.1109\/TPAMI.2011.155","article-title":"Pedestrian detection: An evaluation of the state of the art","volume":"34","author":"Dollar","year":"2012","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"ref34","series-title":"Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition","first-page":"5079","article-title":"Pedestrian detection aided by deep learning semantic tasks","author":"Tian","year":"2015"},{"key":"ref35","series-title":"Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition","first-page":"5363","article-title":"Learning cross-modal deep representations for robust pedestrian detection","author":"Xu","year":"2017"},{"key":"ref36","series-title":"Proc. of the IEEE Int. Conf. on Computer Vision","first-page":"1904","article-title":"Deep learning strong parts for pedestrian detection","author":"Tian","year":"2015"},{"key":"ref37","doi-asserted-by":"crossref","first-page":"1874","DOI":"10.1109\/TPAMI.2017.2738645","article-title":"Jointly learning deep features, deformable parts, occlusion and classification for pedestrian detection","volume":"40","author":"Ouyang","year":"2018","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"ref38","series-title":"Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition","first-page":"6995","article-title":"Occluded pedestrian detection through guided attention in cnns","author":"Zhang","year":"2018"},{"key":"ref39","series-title":"Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition","first-page":"5325","article-title":"A convolutional neural network cascade for face detection","author":"Li","year":"2015"},{"key":"ref40","doi-asserted-by":"crossref","first-page":"1499","DOI":"10.1109\/LSP.2016.2603342","article-title":"Joint face detection and alignment using multitask cascaded convolutional networks","volume":"23","author":"Zhang","year":"2016","journal-title":"IEEE Signal Processing Letters"},{"key":"ref41","series-title":"Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition","first-page":"6186","article-title":"Scale-aware face detection","author":"Hao","year":"2017"},{"key":"ref42","series-title":"Proc. of the IEEE conf. on Computer Vision and Pattern Recognition","first-page":"2295","article-title":"Real-time rotation-invariant face detection with progressive calibration networks","author":"Shi","year":"2018"},{"key":"ref43","series-title":"Proc. of the European Conf. on Computer Vision","first-page":"122","article-title":"Supervised transformer network for efficient face detection","author":"Chen","year":"2016"},{"key":"ref44","doi-asserted-by":"crossref","first-page":"1845","DOI":"10.1109\/TPAMI.2017.2738644","article-title":"Faceness-net: Face detection through deep facial part responses","volume":"40","author":"Yang","year":"2018","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"ref45","series-title":"Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition","first-page":"951","article-title":"Finding tiny faces","author":"Hu","year":"2017"},{"key":"ref46","unstructured":"S.Yang, Y.Xiong, C. C.Loy and X.Tang, \u201cFace detection through scale-friendly deep convolutional networks,\u201d in arXiv preprint arXiv, 1706.02863, 2017."},{"key":"ref47","series-title":"Proc. of the IEEE Int. Conf. on Computer Vision","first-page":"4875","article-title":"Ssh: Single stage headless face detector","author":"Najibi","year":"2017"},{"key":"ref48","series-title":"Proc. of the IEEE Int. Conf. on Computer Vision","first-page":"192","article-title":"S3fd: Single shot scale-invariant face detector","author":"Zhang","year":"2017"},{"key":"ref49","series-title":"Proc. of the IEEE Int. Conf. on Biometrics Theory, Applications and Systems","first-page":"1","article-title":"Pushing the limits of unconstrained face detection: a challenge dataset and baseline results","author":"Nada","year":"2018"},{"key":"ref50","unstructured":"M. K.Yucel, Y. C.Bilge, O.Oguz, N.Ikizler-Cinbis, P.Duygulu et al., \u201cWildest faces: Face detection and recognition in violent settings,\u201d in arXiv preprint arXiv, 1805.07566, 2018."},{"key":"ref51","series-title":"Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition","first-page":"951","article-title":"Finding tiny faces","author":"Hu","year":"2017"},{"key":"ref52","series-title":"Proc. of the Int. ACM SIGACCESS Conf. on Computers and Accessibility","first-page":"305","article-title":"A camera phone based currency reader for the visually impaired","author":"Liu","year":"2008"},{"key":"ref53","series-title":"Proc. of the IEEE Int. Conf. on Document Analysis and Recognition","first-page":"257","article-title":"Improved text-detection methods for a camera-based text reading system for blind persons","author":"Ezaki","year":"2005"},{"key":"ref54","series-title":"Proc. of the IEEE Int. Conf. on Pattern Recognition","first-page":"3288","article-title":"Convolutional neural networks applied to house numbers digit classification","author":"Sermanet","year":"2012"},{"key":"ref55","series-title":"Proc. of the IEEE IAPR Int. Conf. on Document Analysis and Recognition","first-page":"844","article-title":"Attention-based extraction of structured information from street view imagery","author":"Wojna","year":"2017"},{"key":"ref56","doi-asserted-by":"crossref","first-page":"2233","DOI":"10.32604\/cmc.2020.09471","article-title":"A Modified Method for Scene Text Detection by ResNet","volume":"65","author":"Niu","year":"2020","journal-title":"Computers, Materials &Continua"},{"key":"ref57","doi-asserted-by":"crossref","first-page":"1251","DOI":"10.32604\/iasc.2020.012775","article-title":"Text detection and classification from low quality natural images","volume":"26","author":"Yasmeen","year":"2020","journal-title":"Intelligent Automation & Soft Computing"},{"key":"ref58","series-title":"Proc. of the IEEE Int. Conf. on Computer Vision","first-page":"5000","article-title":"Self-organized text detection with minimal post-processing via border learning","author":"Wu","year":"2017"},{"key":"ref59","series-title":"Proc. of the European Conf. on Computer Vision","first-page":"355","article-title":"Accurate scene text detection through border semantics awareness and bootstrapping","author":"Xue","year":"2018"},{"key":"ref60","series-title":"Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition","first-page":"7553","article-title":"Multi-oriented scene text detection via corner localization and region segmentation","author":"Lyu","year":"2018"},{"key":"ref61","series-title":"Proc. of the IEEE Int. Joint Conf. on Neural Networks","first-page":"1","article-title":"Detection of traffic signs in real-world images: The German Traffic Sign Detection Benchmark","author":"Houben","year":"2013"},{"key":"ref62","series-title":"Proc. of the IEEE conf. on Computer Vision and Pattern Recognition","first-page":"2110","article-title":"Traffic-sign detection and classification in the wild","author":"Zhu","year":"2016"}],"container-title":["Computer Systems Science and Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.techscience.com\/ueditor\/files\/csse\/TSP_CSSE_38-2\/TSP_CSSE_17016\/TSP_CSSE_17016.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,6]],"date-time":"2024-12-06T21:48:31Z","timestamp":1733521711000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.techscience.com\/csse\/v38n2\/42344"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":62,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2021]]}},"URL":"https:\/\/doi.org\/10.32604\/csse.2021.017016","relation":{},"ISSN":["0267-6192"],"issn-type":[{"type":"print","value":"0267-6192"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"2021-01-18","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-02-19","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-04-23","order":2,"name":"published","label":"Published Online","group":{"name":"publication_history","label":"Publication History"}}]}}