{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T16:20:21Z","timestamp":1779207621337,"version":"3.51.4"},"reference-count":46,"publisher":"Springer Science and Business Media LLC","issue":"12","license":[{"start":{"date-parts":[[2022,11,18]],"date-time":"2022-11-18T00:00:00Z","timestamp":1668729600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,11,18]],"date-time":"2022-11-18T00:00:00Z","timestamp":1668729600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"the Natural Science Foundation of Anhui Higher Education Institutions of China","award":["KJ2021A0025"],"award-info":[{"award-number":["KJ2021A0025"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62072002"],"award-info":[{"award-number":["62072002"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2023,5]]},"DOI":"10.1007\/s11042-022-14159-2","type":"journal-article","created":{"date-parts":[[2022,11,18]],"date-time":"2022-11-18T15:04:34Z","timestamp":1668783874000},"page":"18529-18544","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["An attention-based feature pyramid network for single-stage small object detection"],"prefix":"10.1007","volume":"82","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0403-0365","authenticated-orcid":false,"given":"Lin","family":"Jiao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenrui","family":"Kang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shifeng","family":"Dong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gaoqiang","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rujing","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,11,18]]},"reference":[{"key":"14159_CR1","doi-asserted-by":"publisher","unstructured":"Bello I, Zoph B, Le Q, Vaswani A, Shlens J (2019) Attention augmented convolutional networks. In: 2019 IEEE\/CVF International conference on computer vision (ICCV), pp 3285\u20133294. https:\/\/doi.org\/10.1109\/ICCV.2019.00338","DOI":"10.1109\/ICCV.2019.00338"},{"key":"14159_CR2","doi-asserted-by":"crossref","unstructured":"Bottou L (2012) Stochastic gradient descent tricks. In: Neural networks: Tricks of the trade. Springer, pp 421\u2013436","DOI":"10.1007\/978-3-642-35289-8_25"},{"key":"14159_CR3","doi-asserted-by":"crossref","unstructured":"Cai Z, Vasconcelos N (2018) Cascade r-cnn: delving into high quality object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 6154\u20136162","DOI":"10.1109\/CVPR.2018.00644"},{"key":"14159_CR4","doi-asserted-by":"publisher","unstructured":"Cao Y, Xu J, Lin S, Wei F, Hu H (2019) Gcnet: non-local networks meet squeeze-excitation networks and beyond. In: 2019 IEEE\/CVF International conference on computer vision workshop (ICCVW), pp 1971\u20131980. https:\/\/doi.org\/10.1109\/ICCVW.2019.00246","DOI":"10.1109\/ICCVW.2019.00246"},{"key":"14159_CR5","unstructured":"Chen K, Wang J, Pang J, Cao Y, Xiong Y, Li X, Sun S, Feng W, Liu Z, Xu J et al (2019) Mmdetection: open mmlab detection toolbox and benchmark. arXiv:1906.07155"},{"key":"14159_CR6","doi-asserted-by":"crossref","unstructured":"Dai P, Zhang S, Zhang H, Cao X (2021) Progressive contour regression for arbitrary-shape scene text detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 7393\u20137402","DOI":"10.1109\/CVPR46437.2021.00731"},{"key":"14159_CR7","doi-asserted-by":"crossref","unstructured":"Duan K, Bai S, Xie L, Qi H, Huang Q, Tian Q (2019) Centernet: keypoint triplets for object detection. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 6569\u20136578","DOI":"10.1109\/ICCV.2019.00667"},{"key":"14159_CR8","doi-asserted-by":"publisher","unstructured":"Gao Z, Xie J, Wang Q, Li P (2019) Global second-order pooling convolutional networks. In: 2019 IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), pp 3019\u20133028. https:\/\/doi.org\/10.1109\/CVPR.2019.00314","DOI":"10.1109\/CVPR.2019.00314"},{"key":"14159_CR9","doi-asserted-by":"crossref","unstructured":"Ghiasi G, Lin TY, Le QV (2019) Nas-fpn: learning scalable feature pyramid architecture for object detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 7036\u20137045","DOI":"10.1109\/CVPR.2019.00720"},{"key":"14159_CR10","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":"14159_CR11","doi-asserted-by":"crossref","unstructured":"Gong Y, Yu X, Ding Y, Peng X, Zhao J, Han Z (2020) Effective fusion factor in fpn for tiny object detection","DOI":"10.1109\/WACV48630.2021.00120"},{"key":"14159_CR12","doi-asserted-by":"crossref","unstructured":"He K, Gkioxari G, Doll\u00e1r P, Girshick R (2017) Mask r-cnn. In: Proceedings of the IEEE international conference on computer vision, pp 2961\u20132969","DOI":"10.1109\/ICCV.2017.322"},{"key":"14159_CR13","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":"14159_CR14","doi-asserted-by":"crossref","unstructured":"Hoiem D, Chodpathumwan Y, Dai Q (2012) Diagnosing error in object detectors. In: European conference on computer vision. Springer, pp 340\u2013353","DOI":"10.1007\/978-3-642-33712-3_25"},{"key":"14159_CR15","doi-asserted-by":"publisher","unstructured":"Hosang J, Omran M, Benenson R, Schiele B (2015) Taking a deeper look at pedestrians. In: 2015 IEEE Conference on computer vision and pattern recognition (CVPR), pp 4073\u20134082. https:\/\/doi.org\/10.1109\/CVPR.2015.7299034","DOI":"10.1109\/CVPR.2015.7299034"},{"issue":"8","key":"14159_CR16","doi-asserted-by":"publisher","first-page":"2011","DOI":"10.1109\/TPAMI.2019.2913372","volume":"42","author":"J Hu","year":"2020","unstructured":"Hu J, Shen L, Albanie S, Sun G, Wu E (2020) Squeeze-and-excitation networks. IEEE Trans Pattern Anal Mach Intell 42 (8):2011\u20132023. https:\/\/doi.org\/10.1109\/TPAMI.2019.2913372","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"14159_CR17","doi-asserted-by":"publisher","first-page":"7389","DOI":"10.1109\/TIP.2020.3002345","volume":"29","author":"T Kong","year":"2020","unstructured":"Kong T, Sun F, Liu H, Jiang Y, Li L, Shi J (2020) Foveabox: beyound anchor-based object detection. IEEE Trans Image Process 29:7389\u20137398","journal-title":"IEEE Trans Image Process"},{"key":"14159_CR18","doi-asserted-by":"crossref","unstructured":"Law H, Deng J (2018) Cornernet: detecting objects as paired keypoints. In: Proceedings of the European conference on computer vision (ECCV), pp 734\u2013750","DOI":"10.1007\/978-3-030-01264-9_45"},{"issue":"107","key":"14159_CR19","doi-asserted-by":"publisher","first-page":"256","DOI":"10.1016\/j.asoc.2021.107256","volume":"105","author":"S Lee","year":"2021","unstructured":"Lee S, Tariq S, Shin Y, Woo S (2021) Detecting handcrafted facial image manipulations and gan-generated facial images using shallow-fakefacenet. Appl Soft Comput 105(107):256. https:\/\/doi.org\/10.1016\/j.asoc.2021.107256","journal-title":"Appl Soft Comput"},{"key":"14159_CR20","doi-asserted-by":"publisher","unstructured":"Li X, Wang W, Hu X, Yang J (2019) Selective kernel networks. In: 2019 IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), pp 510\u2013519. https:\/\/doi.org\/10.1109\/CVPR.2019.00060","DOI":"10.1109\/CVPR.2019.00060"},{"key":"14159_CR21","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":"14159_CR22","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"},{"key":"14159_CR23","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, pp 740\u2013755","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"14159_CR24","doi-asserted-by":"publisher","unstructured":"Liu S, Qi L, Qin H, Shi J, Jia J (2018) Path aggregation network for instance segmentation. In: 2018 IEEE\/CVF Conference on computer vision and pattern recognition, pp 8759\u20138768. https:\/\/doi.org\/10.1109\/CVPR.2018.00913","DOI":"10.1109\/CVPR.2018.00913"},{"key":"14159_CR25","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":"14159_CR26","doi-asserted-by":"crossref","unstructured":"Nyo MT, Mebarek-Oudina F, Hlaing SS, Khan NA (2022) Otsu\u2019s thresholding technique for mri image brain tumor segmentation. Multimedia Tools and Applications","DOI":"10.1007\/s11042-022-13215-1"},{"key":"14159_CR27","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, pp 779\u2013788","DOI":"10.1109\/CVPR.2016.91"},{"key":"14159_CR28","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"},{"key":"14159_CR29","doi-asserted-by":"publisher","unstructured":"Schroff F, Kalenichenko D, Philbin J (2015) Facenet: a unified embedding for face recognition and clustering. In: 2015 IEEE Conference on computer vision and pattern recognition (CVPR), pp 815\u2013823. https:\/\/doi.org\/10.1109\/CVPR.2015.7298682","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"14159_CR30","doi-asserted-by":"crossref","unstructured":"Tian Z, Shen C, Chen H, He T (2019) Fcos: fully convolutional one-stage object detection. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 9627\u20139636","DOI":"10.1109\/ICCV.2019.00972"},{"key":"14159_CR31","doi-asserted-by":"crossref","unstructured":"Tian Z, Shen C, Chen H, He T (2020) Fcos: a simple and strong anchor-free object detector. IEEE Transactions on Pattern Analysis and Machine Intelligence","DOI":"10.1109\/TPAMI.2020.3032166"},{"issue":"106","key":"14159_CR32","doi-asserted-by":"publisher","first-page":"810","DOI":"10.1016\/j.asoc.2020.106810","volume":"97","author":"M To\u011fa\u00e7ar","year":"2020","unstructured":"To\u011fa\u00e7ar M, Ergen B, C\u00f6mert Z (2020) Classification of white blood cells using deep features obtained from convolutional neural network models based on the combination of feature selection methods. Appl Soft Comput 97(106):810. https:\/\/doi.org\/10.1016\/j.asoc.2020.106810","journal-title":"Appl Soft Comput"},{"issue":"106","key":"14159_CR33","doi-asserted-by":"publisher","first-page":"897","DOI":"10.1016\/j.asoc.2020.106897","volume":"98","author":"B Wang","year":"2020","unstructured":"Wang B, Jin S, Yan Q, Xu H, Luo C, Wei L, Zhao W, Hou X, Ma W, Xu Z, Zheng Z, Sun W, Lan L, Zhang W, Mu X, Shi C, Wang Z, Lee J, Jin Z, Dong J (2020) Ai-assisted ct imaging analysis for covid-19 screening: building and deploying a medical ai system. Appl Soft Comput 98(106):897. https:\/\/doi.org\/10.1016\/j.asoc.2020.106897","journal-title":"Appl Soft Comput"},{"key":"14159_CR34","doi-asserted-by":"publisher","unstructured":"Wang Q, Wu B, Zhu P, Li P, Zuo W, Hu Q (2020) Eca-net: efficient channel attention for deep convolutional neural networks. In: 2020 IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), pp 11,531\u201311,539. https:\/\/doi.org\/10.1109\/CVPR42600.2020.01155","DOI":"10.1109\/CVPR42600.2020.01155"},{"key":"14159_CR35","doi-asserted-by":"publisher","first-page":"106,290","DOI":"10.1016\/j.compag.2021.106290","volume":"187","author":"R Wang","year":"2021","unstructured":"Wang R, Jiao L, Xie C, Chen P, Du J, Li R (2021) S-rpn: sampling-balanced region proposal network for small crop pest detection. Comput Electron Agric 187:106,290. https:\/\/doi.org\/10.1016\/j.compag.2021.106290. https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0168169921003070","journal-title":"Comput Electron Agric"},{"key":"14159_CR36","doi-asserted-by":"crossref","unstructured":"Woo S, Park J, Lee JY, Kweon IS (2018) Cbam: convolutional block attention module. In: Ferrari V, Hebert M, Sminchisescu C, Weiss Y (eds) Computer vision \u2013 ECCV 2018. Springer International Publishing, Cham, pp 3\u201319","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"14159_CR37","doi-asserted-by":"crossref","unstructured":"Zhang L, Lin L, Liang X, He K (2016) Is faster r-cnn doing well for pedestrian detection?. In: Leibe B, Matas J, Sebe N, Welling M (eds) Computer vision \u2013 ECCV 2016, Springer International Publishing, Cham, pp 443\u2013457","DOI":"10.1007\/978-3-319-46475-6_28"},{"key":"14159_CR38","doi-asserted-by":"crossref","unstructured":"Zhang S, Chi C, Yao Y, Lei Z, Li SZ (2020) Bridging the gap between anchor-based and anchor-free detection via adaptive training sample selection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 9759\u20139768","DOI":"10.1109\/CVPR42600.2020.00978"},{"key":"14159_CR39","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":"14159_CR40","doi-asserted-by":"publisher","first-page":"3096","DOI":"10.1109\/TPAMI.2021.3050494","volume":"44","author":"X Zhang","year":"2021","unstructured":"Zhang X, Wan F, Liu C, Ji X, Ye Q (2021) Learning to match anchors for visual object detection. IEEE Trans Pattern Anal Mach Intell 44:3096\u20133109. https:\/\/doi.org\/10.1109\/TPAMI.2021.3050494","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"14159_CR41","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 33, pp 9259\u20139266","DOI":"10.1609\/aaai.v33i01.33019259"},{"key":"14159_CR42","doi-asserted-by":"publisher","first-page":"8326","DOI":"10.1109\/TIP.2020.3013162","volume":"29","author":"T Zhou","year":"2020","unstructured":"Zhou T, Li J, Wang S, Tao R, Shen J (2020) Matnet: motion-attentive transition network for zero-shot video object segmentation. IEEE Trans Image Process 29:8326\u20138338. https:\/\/doi.org\/10.1109\/TIP.2020.3013162","journal-title":"IEEE Trans Image Process"},{"key":"14159_CR43","doi-asserted-by":"publisher","unstructured":"Zhou T, Wang W, Qi S, Ling H, Shen J (2020) Cascaded human-object interaction recognition. In: 2020 IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), pp 4262\u20134271. https:\/\/doi.org\/10.1109\/CVPR42600.2020.00432","DOI":"10.1109\/CVPR42600.2020.00432"},{"key":"14159_CR44","doi-asserted-by":"publisher","unstructured":"Zhu C, He Y, Savvides M (2019) Feature selective anchor-free module for single-shot object detection. In: 2019 IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), pp. 840\u2013849. https:\/\/doi.org\/10.1109\/CVPR.2019.00093","DOI":"10.1109\/CVPR.2019.00093"},{"key":"14159_CR45","unstructured":"Zhu P, Wen L, Bian X, Ling H, Hu Q (2018) Vision meets drones: a challenge. arXiv:1804.07437"},{"key":"14159_CR46","doi-asserted-by":"publisher","first-page":"107,336","DOI":"10.1016\/j.patcog.2020.107336","volume":"110","author":"Y Zhu","year":"2021","unstructured":"Zhu Y, Du J (2021) Textmountain: accurate scene text detection via instance segmentation. Pattern Recogn 110:107,336. https:\/\/doi.org\/10.1016\/j.patcog.2020.107336. https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0031320320301394","journal-title":"Pattern Recogn"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-022-14159-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-022-14159-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-022-14159-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,4,20]],"date-time":"2023-04-20T15:02:18Z","timestamp":1682002938000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-022-14159-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,18]]},"references-count":46,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2023,5]]}},"alternative-id":["14159"],"URL":"https:\/\/doi.org\/10.1007\/s11042-022-14159-2","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,11,18]]},"assertion":[{"value":"1 March 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 July 2022","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 October 2022","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 November 2022","order":4,"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":"<!--Emphasis Type='Bold' removed-->Conflict of Interests"}}]}}