{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T16:03:21Z","timestamp":1778601801647,"version":"3.51.4"},"reference-count":56,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2020,7,29]],"date-time":"2020-07-29T00:00:00Z","timestamp":1595980800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,7,29]],"date-time":"2020-07-29T00:00:00Z","timestamp":1595980800000},"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":["Neural Comput & Applic"],"published-print":{"date-parts":[[2021,4]]},"DOI":"10.1007\/s00521-020-05202-0","type":"journal-article","created":{"date-parts":[[2020,7,29]],"date-time":"2020-07-29T06:03:44Z","timestamp":1596002624000},"page":"3583-3596","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Single-shot augmentation detector for object detection"],"prefix":"10.1007","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2802-8139","authenticated-orcid":false,"given":"Jiaxu","family":"Leng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ying","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,7,29]]},"reference":[{"key":"5202_CR1","doi-asserted-by":"crossref","unstructured":"Bell S, Lawrence\u00a0Zitnick 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":"5202_CR2","doi-asserted-by":"crossref","unstructured":"Cai Z, Vasconcelos N (2018) Cascade r-cnn: delving into high quality object detection. In: IEEE CVPR","DOI":"10.1109\/CVPR.2018.00644"},{"key":"5202_CR3","doi-asserted-by":"crossref","unstructured":"He K, Gkioxari G, Doll\u00e1r P, Girshick R (2017) Mask r-cnn. In Computer vision (ICCV), 2017 IEEE International conference on IEEE, pp. 2980\u20132988","DOI":"10.1109\/ICCV.2017.322"},{"key":"5202_CR4","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"6","author":"S Ren","year":"2017","unstructured":"Ren S, He K, Girshick R, Sun J (2017) Faster r-cnn: towards real-time object detection with region proposal networks. IEEE Trans Pattern Anal Mach Intell 6:1137\u20131149","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"5202_CR5","doi-asserted-by":"crossref","unstructured":"Hu R, Doll\u00e1r P, He K, Darrell T, Girshick R (2018) Learning to segment every thing. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 4233\u20134241","DOI":"10.1109\/CVPR.2018.00445"},{"key":"5202_CR6","unstructured":"Fu CY, Liu W, Ranga A, Tyagi A, Berg AC (2017) Dssd: Deconvolutional single shot detector. arXiv preprint arXiv:1701.06659 2017"},{"key":"5202_CR7","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":"5202_CR8","unstructured":"Redmon J, Farhadi A (2018) Yolov3: an incremental improvement. arXiv preprint arXiv:1804.02767"},{"key":"5202_CR9","doi-asserted-by":"crossref","unstructured":"Zhang S, Wen L, Bian X, Lei Z, Li SZ (2018) Single-shot refinement neural network for object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 4203\u20134212","DOI":"10.1109\/CVPR.2018.00442"},{"key":"5202_CR10","doi-asserted-by":"crossref","unstructured":"Woo S, Hwang S, Kweon IS (2018) Stairnet: top-down semantic aggregation for accurate one shot detection. In: 2018 IEEE Winter conference on applications of computer vision (WACV). IEEE, pp. 1093\u20131102","DOI":"10.1109\/WACV.2018.00125"},{"issue":"2","key":"5202_CR11","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 Vision 88(2):303\u2013338","journal-title":"Int J Comput Vision"},{"key":"5202_CR12","doi-asserted-by":"crossref","unstructured":"Lin TY, Maire M, Belongie S, Hays J, Perona P, Ramanan D, Doll\u00e1r P, Zitnick CL (2014) Microsoft coco: common objects in context. In: European conference on computer vision. Springer, Berlin pp. 740\u2013755","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"5202_CR13","doi-asserted-by":"publisher","first-page":"6549","DOI":"10.1007\/s00521-018-3486-1","volume":"31","author":"J Leng","year":"2018","unstructured":"Leng J, Liu Y (2018) An enhanced SSD with feature fusion and visual reasoning for object detection. Neural Comput Appl 31:6549","journal-title":"Neural Comput Appl"},{"key":"5202_CR14","doi-asserted-by":"crossref","unstructured":"Redmon J, Farhadi A (2017) Yolo9000: better, faster, stronger. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 7263\u20137271","DOI":"10.1109\/CVPR.2017.690"},{"key":"5202_CR15","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Identity mappings in deep residual networks. In: European conference on computer vision. Springer, pp. 630\u2013645","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"5202_CR16","unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556"},{"key":"5202_CR17","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":"5202_CR18","doi-asserted-by":"crossref","unstructured":"Zitnick CL, Doll\u00e1r P (2014) Edge boxes: locating object proposals from edges. In: European conference on computer vision. Springer, pp. 391\u2013405","DOI":"10.1007\/978-3-319-10602-1_26"},{"issue":"2","key":"5202_CR19","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 (2013) Selective search for object recognition. Int J Comput Vision 104(2):154\u2013171","journal-title":"Int J Comput Vision"},{"issue":"9","key":"5202_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 (2015) Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans Pattern Anal Mach Intell 37(9):1904\u20131916","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"5202_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":"5202_CR22","doi-asserted-by":"crossref","unstructured":"Chen X, Gupta A (2017) Spatial memory for context reasoning in object detection. In: Proceedings of the IEEE international conference on computer vision, pp. 4086\u20134096","DOI":"10.1109\/ICCV.2017.440"},{"key":"5202_CR23","doi-asserted-by":"crossref","unstructured":"Chen Z, Huang S, Tao D (2018) Context refinement for object detection. In: The European conference on computer vision (ECCV)","DOI":"10.1007\/978-3-030-01237-3_5"},{"issue":"5","key":"5202_CR24","doi-asserted-by":"publisher","first-page":"944","DOI":"10.1109\/TMM.2016.2642789","volume":"19","author":"J Li","year":"2017","unstructured":"Li J, Wei Y, Liang X, Dong J, Xu T, Feng J, Yan S (2017) Attentive contexts for object detection. IEEE Trans Multimedia 19(5):944\u2013954","journal-title":"IEEE Trans Multimedia"},{"key":"5202_CR25","doi-asserted-by":"crossref","unstructured":"Tang X, Du DK, He Z, Liu J (2018) Pyramidbox: a context-assisted single shot face detector. In: Proceedings of the European conference on computer vision (ECCV), pp. 797\u2013813","DOI":"10.1007\/978-3-030-01240-3_49"},{"key":"5202_CR26","doi-asserted-by":"crossref","unstructured":"Shrivastava A, Gupta A, Girshick R (2016) 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","DOI":"10.1109\/CVPR.2016.89"},{"key":"5202_CR27","doi-asserted-by":"crossref","unstructured":"Wang X, Shrivastava A, Gupta A (2017) A-fast-rcnn: Hard positive generation via adversary for object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 2606\u20132615","DOI":"10.1109\/CVPR.2017.324"},{"key":"5202_CR28","doi-asserted-by":"crossref","unstructured":"Chen Y, Li W, Sakaridis C, Dai D, Van\u00a0Gool L (2018) Domain adaptive faster r-cnn for object detection in the wild. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 3339\u20133348","DOI":"10.1109\/CVPR.2018.00352"},{"key":"5202_CR29","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":"5202_CR30","unstructured":"Lee H, Eum S, Kwon H (2017) Me r-cnn: Multi-expert r-cnn for object detection. arXiv preprint arXiv:1704.01069"},{"key":"5202_CR31","unstructured":"Li Z, Peng C, Yu G, Zhang X, Deng Y, Sun J (2017) Light-head r-cnn: In defense of two-stage object detector. arXiv preprint arXiv:1711.07264"},{"key":"5202_CR32","doi-asserted-by":"crossref","unstructured":"Zhu Y, Zhao C, Wang J, Zhao X, Wu Y, Lu H (2017) Couplenet: coupling global structure with local parts for object detection. In: Proceedings of the IEEE international conference on computer vision, pp. 4126\u20134134","DOI":"10.1109\/ICCV.2017.444"},{"key":"5202_CR33","unstructured":"Hara K, Liu MY, Tuzel O, Farahmand A-m (2017) Attentional network for visual object detection. arXiv preprint arXiv:1702.01478"},{"key":"5202_CR34","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, 2016, pp. 779\u2013788","DOI":"10.1109\/CVPR.2016.91"},{"key":"5202_CR35","doi-asserted-by":"crossref","unstructured":"Neubeck A, Van\u00a0Gool L (2006) Efficient non-maximum suppression. In: 18th International conference on pattern recognition (ICPR\u201906), vol.\u00a03.IEEE, 2006, pp. 850\u2013855","DOI":"10.1109\/ICPR.2006.479"},{"key":"5202_CR36","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: Proceedings of the IEEE international conference on computer vision, pp. 1919\u20131927","DOI":"10.1109\/ICCV.2017.212"},{"key":"5202_CR37","unstructured":"Iandola F, Moskewicz M, Karayev S, Girshick R, Darrell T, Keutzer K (2014) Densenet: implementing efficient convnet descriptor pyramids. arXiv preprint arXiv:1404.1869"},{"key":"5202_CR38","doi-asserted-by":"crossref","unstructured":"Zhao Q, Sheng T, Wang Y, Tang Z, Chen Y, Cai L, Ling H (2019) M2det: a single-shot object detector based on multi-level feature pyramid network. In: Proceedings of the AAAI conference on artificial intelligence, vol.\u00a033, pp. 9259\u20139266","DOI":"10.1609\/aaai.v33i01.33019259"},{"key":"5202_CR39","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), 2018, pp. 169\u2013185","DOI":"10.1007\/978-3-030-01228-1_11"},{"key":"5202_CR40","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":"5202_CR41","unstructured":"Liu W, Rabinovich A, Berg AC (2015) Parsenet: looking wider to see better. arXiv preprint arXiv:1506.04579"},{"key":"5202_CR42","doi-asserted-by":"crossref","unstructured":"Long J, Shelhamer E, Darrell T (2015) Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 3431\u20133440","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"5202_CR43","doi-asserted-by":"crossref","unstructured":"Lin TY, Doll\u00e1r P, Girshick R, He K, Hariharan B, Belongie S (2017) Feature pyramid networks for object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 2117\u20132125","DOI":"10.1109\/CVPR.2017.106"},{"key":"5202_CR44","doi-asserted-by":"crossref","unstructured":"Jeong J, Park H, Kwak N (2017) Enhancement of SSD by concatenating feature maps for object detection.","DOI":"10.5244\/C.31.76"},{"key":"5202_CR45","doi-asserted-by":"crossref","unstructured":"Pang J, Chen K, Shi J, Feng H, Ouyang W, Lin D (2019) Libra r-cnn: towards balanced learning for object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 821\u2013830","DOI":"10.1109\/CVPR.2019.00091"},{"key":"5202_CR46","unstructured":"Yang T, Zhang X, Li Z, Zhang W, Sun J (2018) Metaanchor: learning to detect objects with customized anchors. In: Advances in neural information processing systems, 2018, pp. 318\u2013328"},{"key":"5202_CR47","doi-asserted-by":"crossref","unstructured":"Wang J, Chen K, Yang S, Loy CC, Lin D (2019) Region proposal by guided anchoring. arXiv preprint arXiv:1901.03278 2019","DOI":"10.1109\/CVPR.2019.00308"},{"key":"5202_CR48","doi-asserted-by":"crossref","unstructured":"Zhu C, He Y, Savvides M (2019) Feature selective anchor-free module for single-shot object detection. arXiv preprint arXiv:1903.00621","DOI":"10.1109\/CVPR.2019.00093"},{"key":"5202_CR49","unstructured":"Ioffe S, Szegedy C (2015) Batch normalization: Accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167"},{"key":"5202_CR50","unstructured":"Chen LC, Papandreou G, Kokkinos I, Murphy K, Yuille AL (2014) Semantic image segmentation with deep convolutional nets and fully connected CRFS. arXiv preprint arXiv:1412.7062"},{"key":"5202_CR51","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":"5202_CR52","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":"5202_CR53","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. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 5936\u20135944","DOI":"10.1109\/CVPR.2017.557"},{"key":"5202_CR54","doi-asserted-by":"crossref","unstructured":"Dai J, Qi H, Xiong Y, Li Y, Zhang G, Hu H, Wei Y (2017) Deformable convolutional networks. In: Proceedings of the IEEE international conference on computer vision, pp. 764\u2013773","DOI":"10.1109\/ICCV.2017.89"},{"key":"5202_CR55","doi-asserted-by":"crossref","unstructured":"Tychsen-Smith L, Petersson L (2018) Improving object localization with fitness NMS and bounded IOU loss. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 6877\u20136885","DOI":"10.1109\/CVPR.2018.00719"},{"key":"5202_CR56","doi-asserted-by":"crossref","unstructured":"Lin TY, Goyal P, Girshick R, He K, Doll\u00e1r P (2017) Focal loss for dense object detection. In: Proceedings of the IEEE international conference on computer vision, pp. 2980\u20132988","DOI":"10.1109\/ICCV.2017.324"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-020-05202-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-020-05202-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-020-05202-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,7,28]],"date-time":"2021-07-28T23:38:06Z","timestamp":1627515486000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-020-05202-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,7,29]]},"references-count":56,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2021,4]]}},"alternative-id":["5202"],"URL":"https:\/\/doi.org\/10.1007\/s00521-020-05202-0","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,7,29]]},"assertion":[{"value":"16 April 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 July 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 July 2020","order":3,"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":"We declare that we do not have any commercial or associative interest that represents a conflict of interest in connection with the work submitted.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}