{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T16:02:24Z","timestamp":1740153744054,"version":"3.37.3"},"reference-count":50,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2021,2,15]],"date-time":"2021-02-15T00:00:00Z","timestamp":1613347200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,2,15]],"date-time":"2021-02-15T00:00:00Z","timestamp":1613347200000},"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":["61371156"],"award-info":[{"award-number":["61371156"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Cogn Comput"],"published-print":{"date-parts":[[2022,5]]},"DOI":"10.1007\/s12559-020-09814-5","type":"journal-article","created":{"date-parts":[[2021,2,18]],"date-time":"2021-02-18T22:01:19Z","timestamp":1613685679000},"page":"1107-1122","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Local Enhancement and Bidirectional Feature Refinement Network for Single-Shot Detector"],"prefix":"10.1007","volume":"14","author":[{"given":"Pengxiang","family":"Ouyang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiaqi","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chaogang","family":"Fan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhao","family":"Niu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5568-0264","authenticated-orcid":false,"given":"Shu","family":"Zhan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,2,15]]},"reference":[{"issue":"6","key":"9814_CR1","first-page":"33","volume":"29","author":"EH Adelson","year":"1984","unstructured":"Adelson EH, Anderson CH, Bergen JR, Burt PJ, Ogden JM. Pyramid methods in image processing. RCA engineer. 1984;29(6):33\u201341.","journal-title":"RCA engineer"},{"key":"9814_CR2","unstructured":"LeCun Y, Bengio Y, et al. Convolutional networks for images, speech, and time series. The Handbook of Brain Theory and Neural Networks. 1995;3361(10):"},{"key":"9814_CR3","doi-asserted-by":"crossref","unstructured":"Girshick R, Donahue J, Darrell T, Malik J. Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proc IEEE Conf Comput Vis Pattern Recognit. 2014. pp. 580\u2013587.","DOI":"10.1109\/CVPR.2014.81"},{"key":"9814_CR4","doi-asserted-by":"crossref","unstructured":"Girshick R. Fast r-cnn. In: Proceedings of the IEEE International Conference on Computer Vision. 2015. pp. 1440\u20131448.","DOI":"10.1109\/ICCV.2015.169"},{"key":"9814_CR5","unstructured":"Ren S, He K, Girshick R, Sun J. Faster r-cnn: Towards real-time object detection with region proposal networks. In: Adv Neural Inf Proces Syst. 2015. pp 91\u201399."},{"key":"9814_CR6","doi-asserted-by":"crossref","unstructured":"Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu CY, Berg AC. Ssd: Single shot multibox detector. In: European Conference on Computer Vision, Springer 2016. pp. 21\u201337.","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"9814_CR7","doi-asserted-by":"crossref","unstructured":"Redmon J, Divvala S, Girshick R, Farhadi A. You only look once: Unified, real-time object detection. In: Proc IEEE Conf Comput Vis Pattern Recognit. 2016. pp. 779\u2013788.","DOI":"10.1109\/CVPR.2016.91"},{"key":"9814_CR8","unstructured":"Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. arXiv preprint 2014.\u00a0arXiv:14091556"},{"key":"9814_CR9","doi-asserted-by":"crossref","unstructured":"Lin TY, Doll\u00e1r P, Girshick R, He K, Hariharan B, Belongie S. Feature pyramid networks for object detection. In: Proc IEEE Conf Comput Vis Pattern Recognit. 2017. pp. 2117\u20132125.","DOI":"10.1109\/CVPR.2017.106"},{"key":"9814_CR10","unstructured":"Fu CY, Liu W, Ranga A, Tyagi A, Berg AC. Dssd: Deconvolutional single shot detector. arXiv preprint 2017.\u00a0arXiv:170106659"},{"key":"9814_CR11","doi-asserted-by":"crossref","unstructured":"Shen Z, Liu Z, Li J, Jiang YG, Chen Y, Xue X. Dsod: Learning deeply supervised object detectors from scratch. In: Proceedings of the IEEE International Conference on Computer Vision. 2017. pp. 1919\u20131927.","DOI":"10.1109\/ICCV.2017.212"},{"key":"9814_CR12","doi-asserted-by":"crossref","unstructured":"Kong T, Sun F, Yao A, Liu H, Lu M, Chen Y. Ron: Reverse connection with objectness prior networks for object detection. In: Proc IEEE Conf Comput Vis Pattern Recognit. 2017. pp. 5936\u20135944.","DOI":"10.1109\/CVPR.2017.557"},{"key":"9814_CR13","doi-asserted-by":"crossref","unstructured":"Woo S, Hwang S, Kweon IS. Stairnet: Top-down semantic aggregation for accurate one shot detection. In: 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), IEEE 2018, pp. 1093\u20131102.","DOI":"10.1109\/WACV.2018.00125"},{"key":"9814_CR14","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In: Proc IEEE Conf Comput Vis Pattern Recognit. 2016. pp. 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"issue":"2","key":"9814_CR15","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. The pascal visual object classes (voc) challenge. Int J Comput Vis. 2010;88(2):303\u201338.","journal-title":"Int J Comput Vis"},{"key":"9814_CR16","doi-asserted-by":"crossref","unstructured":"Lin TY, Maire M, Belongie S, Hays J, Perona P, Ramanan D, Doll\u00e1r P, Zitnick CL.\u00a0 Microsoft coco: Common objects in context. In: European Conference on Computer Vision, Springer 2014. pp. 740\u2013755.","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"9814_CR17","unstructured":"Sermanet P, Eigen D, Zhang X, Mathieu M, Fergus R, LeCun Y. Overfeat: Integrated recognition, localization and detection using convolutional networks. arXiv preprint 2013.\u00a0arXiv:13126229"},{"issue":"2","key":"9814_CR18","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1007\/s11263-013-0620-5","volume":"104","author":"JR Uijlings","year":"2013","unstructured":"Uijlings JR, Van De Sande KE, Gevers T, Smeulders AW. Selective search for object recognition. Int J Comput Vis. 2013;104(2):154\u201371.","journal-title":"Int J Comput Vis"},{"key":"9814_CR19","doi-asserted-by":"crossref","unstructured":"Zitnick CL, Doll\u00e1r P. Edge boxes: Locating object proposals from edges. In: European Conference on Computer Vision, Springer 2014. pp 391\u2013405.","DOI":"10.1007\/978-3-319-10602-1_26"},{"issue":"9","key":"9814_CR20","doi-asserted-by":"publisher","first-page":"1904","DOI":"10.1109\/TPAMI.2015.2389824","volume":"37","author":"K He","year":"2015","unstructured":"He K, Zhang X, Ren S, Sun J. Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans Pattern Anal Mach Intell. 2015;37(9):1904\u201316.","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"9814_CR21","doi-asserted-by":"crossref","unstructured":"Cai Z, Fan Q, Feris RiS, Vasconcelos N. A unified multi-scale deep convolutional neural network for fast object detection. In: European Conference on Computer Vision, Springer 2016. pp. 354\u2013370.","DOI":"10.1007\/978-3-319-46493-0_22"},{"key":"9814_CR22","unstructured":"Shrivastava A, Sukthankar R, Malik J, Gupta A. Beyond skip connections: Top-down modulation for object detection. arXiv preprint 2016.\u00a0arXiv:161206851"},{"key":"9814_CR23","doi-asserted-by":"crossref","unstructured":"Zhang S, Wen L, Bian X, Lei Z, Li SZ. Single-shot refinement neural network for object detection. In: Proc IEEE Conf Comput Vis Pattern Recognit. 2018. pp. 4203\u20134212.","DOI":"10.1109\/CVPR.2018.00442"},{"key":"9814_CR24","unstructured":"Chen X, Yu J, Kong S, Wu Z, Wen L. Dual refinement networks for accurate and fast object detection in real-world scenes. arXiv preprint 2018.\u00a0arXiv:180708638"},{"key":"9814_CR25","doi-asserted-by":"crossref","unstructured":"Zhang Z, Qiao S, Xie C, Shen W, Wang B, Yuille AL. Single-shot object detection with enriched semantics. In: Proc IEEE Conf Comput Vis Pattern Recognit. 2018. pp. 5813\u20135821.","DOI":"10.1109\/CVPR.2018.00609"},{"key":"9814_CR26","doi-asserted-by":"crossref","unstructured":"Kong T, Sun F, Tan C, Liu H, Huang W. Deep feature pyramid reconfiguration for object detection. In: Proceedings of the European Conference on Computer Vision (ECCV). 2018. pp 169\u2013185.","DOI":"10.1007\/978-3-030-01228-1_11"},{"key":"9814_CR27","doi-asserted-by":"crossref","unstructured":"Wang T, Anwer RM, Cholakkal H, Khan FS, Pang Y, Shao L. Learning rich features at high-speed for single-shot object detection. In: Proceedings of the IEEE International Conference on Computer Vision. 2019. pp 1971\u20131980.","DOI":"10.1109\/ICCV.2019.00206"},{"key":"9814_CR28","doi-asserted-by":"crossref","unstructured":"Pang Y, Wang T, Anwer RM, Khan FS, Shao L. Efficient featurized image pyramid network for single shot detector. In: Proc IEEE Conf Comput Vis Pattern Recognit. 2019. pp. 7336\u20137344.","DOI":"10.1109\/CVPR.2019.00751"},{"key":"9814_CR29","doi-asserted-by":"crossref","unstructured":"Wang F, Jiang M, Qian C, Yang S, Li C, Zhang H, Wang X, Tang X. Residual attention network for image classification. In: Proc IEEE Conf Comput Vis Pattern Recognit. 2017. pp. 3156\u20133164.","DOI":"10.1109\/CVPR.2017.683"},{"key":"9814_CR30","doi-asserted-by":"crossref","unstructured":"Hu J, Shen L, Sun G. Squeeze-and-excitation networks. In: Proc IEEE Conf Comput Vis Pattern Recognit. 2018. pp. 7132\u20137141.","DOI":"10.1109\/CVPR.2018.00745"},{"key":"9814_CR31","doi-asserted-by":"crossref","unstructured":"Wang X, Girshick R, Gupta A, He K. Non-local neural networks. In: Proc IEEE Conf Comput Vis Pattern Recognit. 2018. pp. 7794\u20137803.","DOI":"10.1109\/CVPR.2018.00813"},{"key":"9814_CR32","doi-asserted-by":"crossref","unstructured":"Deng J, Dong W, Socher R, Li LJ, Li K, Fei-Fei L. Imagenet: A large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, IEEE 2009. pp. 248\u2013255.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"9814_CR33","doi-asserted-by":"crossref","unstructured":"Jang HD, Woo S, Benz P, Park J, Kweon IS. Propose-and-attend single shot detector. In: The IEEE Winter Conference on Applications of Computer Vision. 2020. pp. 815\u2013824.","DOI":"10.1109\/WACV45572.2020.9093364"},{"key":"9814_CR34","doi-asserted-by":"publisher","first-page":"166","DOI":"10.1016\/j.neucom.2019.08.086","volume":"371","author":"H Zhang","year":"2020","unstructured":"Zhang H, Kang D, He H, Wang FY. Aplnet: Attention-enhanced progressive learning network. Neurocomputing. 2020;371:166\u201376.","journal-title":"Neurocomputing"},{"key":"9814_CR35","doi-asserted-by":"crossref","unstructured":"Li S, Yang L, Huang J, Hua XS, Zhang L. Dynamic anchor feature selection for single-shot object detection. In: Proceedings of the IEEE International Conference on Computer Vision. 2019. pp. 6609\u20136618.","DOI":"10.1109\/ICCV.2019.00671"},{"key":"9814_CR36","doi-asserted-by":"crossref","unstructured":"Xu X, Luo X, Ma L. Context-aware hierarchical feature attention network for multi-scale object detection. In: 2020 IEEE International Conference on Image Processing (ICIP), IEEE 2020. pp. 2011\u20132015.","DOI":"10.1109\/ICIP40778.2020.9190896"},{"key":"9814_CR37","doi-asserted-by":"crossref","unstructured":"Zhu Y, Zhao C, Wang J, Zhao X, Wu Y, Lu H. Couplenet: Coupling global structure with local parts for object detection. In: Proceedings of the IEEE International Conference on Computer Vision. 2017. pp. 4126\u20134134.","DOI":"10.1109\/ICCV.2017.444"},{"key":"9814_CR38","doi-asserted-by":"crossref","unstructured":"Kong T, Yao A, Chen Y, Sun F. Hypernet: Towards accurate region proposal generation and joint object detection. In: Proc IEEE Conf Comput Vis Pattern Recognit. 2016. pp. 845\u2013853.","DOI":"10.1109\/CVPR.2016.98"},{"key":"9814_CR39","doi-asserted-by":"crossref","unstructured":"Bell S, Lawrence\u00a0Zitnick C, Bala K, Girshick R. Inside-outside net: Detecting objects in context with skip pooling and recurrent neural networks. In: Proc IEEE Conf Comput Vis Pattern Recognit. 2016. pp. 2874\u20132883.","DOI":"10.1109\/CVPR.2016.314"},{"key":"9814_CR40","unstructured":"Dai J, Li Y, He K, Sun J. R-fcn: Object detection via region-based fully convolutional networks. In: Adv Neural Inf Proces Syst. 2016. pp. 379\u2013387."},{"key":"9814_CR41","doi-asserted-by":"crossref","unstructured":"Jeong J, Park H, Kwak N. Enhancement of ssd by concatenating feature maps for object detection. arXiv preprint 2017.\u00a0arXiv:170509587","DOI":"10.5244\/C.31.76"},{"key":"9814_CR42","unstructured":"Lee K, Choi J, Jeong J, Kwak N. Residual features and unified prediction network for single stage detection. arXiv preprint 2017.\u00a0arXiv:170705031"},{"key":"9814_CR43","doi-asserted-by":"crossref","unstructured":"Xie S, Liu C, Gao J, Li X, Luo J, Fan B, Chen J, Pu H, Peng Y. Diverse receptive field network with context aggregation for fast object detection. J Vis Commun Image Represent.\u00a02020. pp. 102770.","DOI":"10.1016\/j.jvcir.2020.102770"},{"key":"9814_CR44","doi-asserted-by":"crossref","unstructured":"Liu S, Huang D, et\u00a0al. Receptive field block net for accurate and fast object detection. In: Proceedings of the European Conference on Computer Vision (ECCV). 2018. pp. 385\u2013400.","DOI":"10.1007\/978-3-030-01252-6_24"},{"key":"9814_CR45","doi-asserted-by":"crossref","unstructured":"Quan Q, He F, Li H. A multi-phase blending method with incremental intensity for training detection networks. Vis Comput.\u00a02020. pp. 1\u201315.","DOI":"10.1007\/s00371-020-01796-7"},{"key":"9814_CR46","doi-asserted-by":"crossref","unstructured":"Redmon J, Farhadi A. Yolo9000: better, faster, stronger. In: Proc IEEE Conf Comput Vis Pattern Recognit. 2017. pp. 7263\u20137271.","DOI":"10.1109\/CVPR.2017.690"},{"key":"9814_CR47","doi-asserted-by":"crossref","unstructured":"Shrivastava A, Gupta A, Girshick R. Training region-based object detectors with online hard example mining. In: Proc IEEE Conf Comput Vis Pattern Recognit. 2016. pp. 761\u2013769.","DOI":"10.1109\/CVPR.2016.89"},{"key":"9814_CR48","doi-asserted-by":"crossref","unstructured":"Dai J, Qi H, Xiong Y, Li Y, Zhang G, Hu H, Wei Y. Deformable convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision. 2017. pp. 764\u2013773.","DOI":"10.1109\/ICCV.2017.89"},{"key":"9814_CR49","doi-asserted-by":"crossref","unstructured":"Lin TY, Goyal P, Girshick R, He K, Doll\u00e1r P. Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision. 2017. pp. 2980\u20132988.","DOI":"10.1109\/ICCV.2017.324"},{"issue":"1","key":"9814_CR50","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1109\/TPAMI.2018.2875002","volume":"42","author":"Q Wang","year":"2018","unstructured":"Wang Q, Chen M, Nie F, Li X. Detecting coherent groups in crowd scenes by multiview clustering. IEEE Trans Pattern Anal Mach Intell. 2018;42(1):46\u201358.","journal-title":"IEEE Trans Pattern Anal Mach Intell"}],"container-title":["Cognitive Computation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12559-020-09814-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s12559-020-09814-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12559-020-09814-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,17]],"date-time":"2022-05-17T11:39:50Z","timestamp":1652787590000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s12559-020-09814-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,2,15]]},"references-count":50,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2022,5]]}},"alternative-id":["9814"],"URL":"https:\/\/doi.org\/10.1007\/s12559-020-09814-5","relation":{},"ISSN":["1866-9956","1866-9964"],"issn-type":[{"type":"print","value":"1866-9956"},{"type":"electronic","value":"1866-9964"}],"subject":[],"published":{"date-parts":[[2021,2,15]]},"assertion":[{"value":"28 September 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 December 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 February 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":"Conflicts of Interest"}},{"value":"This article does not contain any studies that used human participants or animals.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical Approval"}}]}}