{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T13:20:20Z","timestamp":1753881620212,"version":"3.41.2"},"reference-count":36,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2021,5,5]],"date-time":"2021-05-05T00:00:00Z","timestamp":1620172800000},"content-version":"vor","delay-in-days":124,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Computational Intelligence and Neuroscience"],"published-print":{"date-parts":[[2021,1]]},"abstract":"<jats:p>Face detection remains a challenging problem due to the high variability of scale and occlusion despite the strong representational power of deep convolutional neural networks and their implicit robustness. To handle hard face detection under extreme circumstances especially tiny faces detection, in this paper, we proposed a multiscale Hybrid Pyramid Convolutional Network (HPCNet), which is a one\u2010stage fully convolutional network. Our HPCNet consists of three newly presented modules: firstly, we designed the Hybrid Dilated Convolution (HDC) module to replace the fully connected layers in VGG16, which enlarges receptive field and reduces its loss of local information; secondly, we constructed the Hybrid Feature Pyramid (HFP) to combine semantic information from higher layers together with details from lower layers; and thirdly, to deal with the problem of occlusion and blurring effectively, we introduced Context Information Extractor (CIE) in HPCNet. In addition, we presented an improved Online Hard Example Mining (OHEM) strategy, which can enhance the average precision of face detection by balancing the number of positive and negative samples. Our method has achieved an accuracy of 0.933, 0.924, and 0.848 on the Easy, Medium, and Hard subset of WIDER FACE, respectively, which surpasses most of the advanced algorithms.<\/jats:p>","DOI":"10.1155\/2021\/9963322","type":"journal-article","created":{"date-parts":[[2021,5,5]],"date-time":"2021-05-05T19:29:23Z","timestamp":1620242963000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Hybrid Pyramid Convolutional Network for Multiscale Face Detection"],"prefix":"10.1155","volume":"2021","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8304-5711","authenticated-orcid":false,"given":"Shaoqi","family":"Hou","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9300-3678","authenticated-orcid":false,"given":"Dongdong","family":"Fang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4821-4310","authenticated-orcid":false,"given":"Yixi","family":"Pan","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2699-6630","authenticated-orcid":false,"given":"Ye","family":"Li","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2178-2147","authenticated-orcid":false,"given":"Guangqiang","family":"Yin","sequence":"additional","affiliation":[]}],"member":"311","published-online":{"date-parts":[[2021,5,5]]},"reference":[{"key":"e_1_2_9_1_2","doi-asserted-by":"publisher","DOI":"10.1109\/34.655647"},{"key":"e_1_2_9_2_2","unstructured":"RowleyH. A. BalujaS. andKanadeT. Rotation invariant neural network-based face detection Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition 1998 London UK."},{"key":"e_1_2_9_3_2","unstructured":"KouzaniA. Z. HeF. andSammutK. Commonsense knowledge-based face detection Proceedings of the IEEE International Conference on Intelligent Engineering Systems 1997 London UK."},{"key":"e_1_2_9_4_2","unstructured":"OsunaE. FreundR. andGirosiF. Training support vector machines: an application to face detection Proceedings of the IEEE Computer Society Conference on Computer Vision & Pattern Recognition 2000 London UK."},{"key":"e_1_2_9_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2003.1201822"},{"key":"e_1_2_9_6_2","article-title":"Hmm-based architecture for face identification","volume":"23","author":"Ferdinando S.","year":"1994","journal-title":"Image & Vision Computing"},{"key":"e_1_2_9_7_2","unstructured":"ViolaP.andJonesM. J. Rapid object detection using a boosted cascade of simple features Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition 2001 London UK."},{"key":"e_1_2_9_8_2","unstructured":"PedroF. Girshick andRoss B. Object detection with discriminatively trained part-based models Proceedings of the IEEE Transactions on Pattern Analysis & Machine Intelligence 2010 London UK."},{"key":"e_1_2_9_9_2","unstructured":"LienhartR.andMaydtJ. An extended set of haar-like features for rapid object detection Proceedings of the International Conference on Image Processing 2002 London UK."},{"key":"e_1_2_9_10_2","article-title":"Aggregate channel features for multi-view face detection","volume":"23","author":"Yang B.","year":"2014","journal-title":"CoRR"},{"key":"e_1_2_9_11_2","unstructured":"DalalN.andTriggsB. Histograms of oriented gradients for human detection 2 Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2005) 2005."},{"key":"e_1_2_9_12_2","unstructured":"HadjiI.andWildesR. What Do We Understand about Convolutional Networks? 2018."},{"key":"e_1_2_9_13_2","unstructured":"WuBo AiH. ChangH. andLaoS. Fast rotation invariant multi-view face detection based on real adaboost Proceedings of the Sixth IEEE International Conference on Automatic Face and Gesture Recognition 2004 London UK."},{"key":"e_1_2_9_14_2","doi-asserted-by":"crossref","unstructured":"LiH. LinZ. ShenX. BrandtJ. andGangH. A convolutional neural network cascade for face detection Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2015 London UK.","DOI":"10.1109\/CVPR.2015.7299170"},{"key":"e_1_2_9_15_2","unstructured":"JosephR. DivvalaS. GirshickR. andAliF. You Only Look once: Unified Real-Time Object Detection 2015."},{"key":"e_1_2_9_16_2","article-title":"YOLO9000: better, faster, stronger","volume":"2016","author":"Joseph R.","year":"2016","journal-title":"CoRR"},{"key":"e_1_2_9_17_2","article-title":"Yolov3: an incremental improvement","volume":"2018","author":"Joseph R.","year":"2018","journal-title":"CoRR"},{"key":"e_1_2_9_18_2","article-title":"SSD: single shot multibox detector","volume":"2015","author":"Liu W.","year":"2015","journal-title":"CoRR"},{"key":"e_1_2_9_19_2","article-title":"Dssd: Deconvolutional single shot detector","volume":"2017","author":"Fu C.-Y.","year":"2017","journal-title":"CoRR"},{"key":"e_1_2_9_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/access.2020.2973071"},{"key":"e_1_2_9_21_2","article-title":"Fast r-cnn","volume":"2015","author":"Girshick R.","year":"2015","journal-title":"Computer Science"},{"key":"e_1_2_9_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2577031"},{"key":"e_1_2_9_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/lsp.2016.2603342"},{"key":"e_1_2_9_24_2","unstructured":"DaiJ. LiYi andHeK. R-fcn: Object Detection via Region-Based Fully Convolutional Networks 2016."},{"key":"e_1_2_9_25_2","unstructured":"YangS. XiongY. andTangX. Face Detection through Scale-Friendly Deep Convolutional Networks 2017."},{"key":"e_1_2_9_26_2","article-title":"Feature pyramid networks for object detection","volume":"2016","author":"Lin T.-Yi","year":"2016","journal-title":"CoRR"},{"key":"e_1_2_9_27_2","doi-asserted-by":"crossref","unstructured":"YangS. LuoP. andTangX. Computer vision and pattern recognition (cvpr)-wider face: a face detection benchmark 2016.","DOI":"10.1109\/CVPR.2016.596"},{"key":"e_1_2_9_28_2","article-title":"S3fd: single shot scale-invariant face detector","volume":"2017","author":"Zhang S.","year":"2017","journal-title":"CoRR"},{"key":"e_1_2_9_29_2","article-title":"DSFD: dual shot face detector","volume":"2018","author":"Li J.","year":"2018","journal-title":"CoRR"},{"key":"e_1_2_9_30_2","article-title":"Very deep convolutional networks for large-scale image recognition","volume":"2014","author":"Simonyan K.","year":"2014","journal-title":"Computer Science"},{"key":"e_1_2_9_31_2","article-title":"Pyramid methods in image processing","volume":"29","author":"Adelson E.","year":"1983","journal-title":"RCA Engineering"},{"key":"e_1_2_9_32_2","doi-asserted-by":"crossref","unstructured":"ZhuC. ZhengY. LuuK. andSavvidesM. Cms-rcnn: contextual multi-scale region-based cnn for unconstrained face detection 2016.","DOI":"10.1007\/978-3-319-61657-5_3"},{"key":"e_1_2_9_33_2","doi-asserted-by":"crossref","unstructured":"ShrivastavaA. GuptaA. andGirshickR. Training Region-Based Object Detectors with Online Hard Example Mining 2016.","DOI":"10.1109\/CVPR.2016.89"},{"key":"e_1_2_9_34_2","article-title":"SSH: single stage headless face detector","volume":"2017","author":"Najibi M.","year":"2017","journal-title":"CoRR"},{"key":"e_1_2_9_35_2","doi-asserted-by":"crossref","unstructured":"HuP.andRamananD. Computer vision and pattern recognition (cvpr)-finding tiny faces 2017.","DOI":"10.1109\/CVPR.2017.166"},{"key":"e_1_2_9_36_2","doi-asserted-by":"crossref","unstructured":"YangS. LuoP. andTangX. From facial parts responses to face detection: a deep learning approach 2015.","DOI":"10.1109\/ICCV.2015.419"}],"container-title":["Computational Intelligence and Neuroscience"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/downloads.hindawi.com\/journals\/cin\/2021\/9963322.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/cin\/2021\/9963322.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/2021\/9963322","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,6]],"date-time":"2024-08-06T12:20:03Z","timestamp":1722946803000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1155\/2021\/9963322"}},"subtitle":[],"editor":[{"given":"Nian","family":"Zhang","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2021,1]]},"references-count":36,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,1]]}},"alternative-id":["10.1155\/2021\/9963322"],"URL":"https:\/\/doi.org\/10.1155\/2021\/9963322","archive":["Portico"],"relation":{},"ISSN":["1687-5265","1687-5273"],"issn-type":[{"type":"print","value":"1687-5265"},{"type":"electronic","value":"1687-5273"}],"subject":[],"published":{"date-parts":[[2021,1]]},"assertion":[{"value":"2021-03-14","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-04-13","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-05-05","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"9963322"}}