{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T19:03:35Z","timestamp":1773342215560,"version":"3.50.1"},"reference-count":73,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61673396"],"award-info":[{"award-number":["61673396"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007129","name":"Natural Science Foundation of Shandong Province","doi-asserted-by":"publisher","award":["ZR2020MF136"],"award-info":[{"award-number":["ZR2020MF136"]}],"id":[{"id":"10.13039\/501100007129","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2021.3116324","type":"journal-article","created":{"date-parts":[[2021,9,29]],"date-time":"2021-09-29T21:37:51Z","timestamp":1632951471000},"page":"134649-134659","source":"Crossref","is-referenced-by-count":8,"title":["Transformed Dynamic Feature Pyramid for Small Object Detection"],"prefix":"10.1109","volume":"9","author":[{"given":"Hong","family":"Liang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5972-5239","authenticated-orcid":false,"given":"Ying","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qian","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Linxia","family":"Feng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Ren","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiyao","family":"Liang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref2","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Tan"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01161"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00203"},{"key":"ref5","article-title":"Object detection in 20 years: A survey","author":"Zou","year":"2019","journal-title":"arXiv:1905.05055"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_15"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01261"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_11"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2021.104128"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.314"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00069"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00378"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3047209"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00377"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-019-2723-1"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/BTAS.2017.8272675"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00644"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.211"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00615"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-46466-9_18"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.4.541"},{"key":"ref23","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"arXiv:1706.03762"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref25","first-page":"1691","article-title":"Generative pretraining from pixels","volume-title":"Proc. 37th Int. Conf. Mach. Learn., (ICML)","volume":"119","author":"Chen"},{"key":"ref26","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"ref28","article-title":"End-to-end object detection with transformers","author":"Carion","year":"2020","journal-title":"arXiv:2005.12872"},{"key":"ref29","article-title":"UP-DETR: Unsupervised pre-training for object detection with transformers","author":"Dai","year":"2020","journal-title":"arXiv:2011.09094"},{"key":"ref30","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020","journal-title":"arXiv:2010.04159"},{"key":"ref31","article-title":"End-to-end object detection with adaptive clustering transformer","author":"Zheng","year":"2020","journal-title":"arXiv:2011.09315"},{"key":"ref32","article-title":"Rethinking transformer-based set prediction for object detection","author":"Sun","year":"2020","journal-title":"arXiv:2011.10881"},{"key":"ref33","first-page":"16519","article-title":"Bottleneck transformers for visual recognition","author":"Srinivas","year":"2021","journal-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit."},{"key":"ref34","article-title":"MaX-DeepLab: End-to-end panoptic segmentation with mask transformers","author":"Wang","year":"2020","journal-title":"arXiv:2012.00759"},{"key":"ref35","article-title":"SOLQ: Segmenting objects by learning queries","author":"Dong","year":"2021","journal-title":"arXiv:2106.02351"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2437384"},{"key":"ref37","article-title":"Simple training strategies and model scaling for object detection","author":"Du","year":"2021","journal-title":"arXiv:2107.00057"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2020.103910"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01283"},{"key":"ref42","article-title":"You only learn one representation: Unified network for multiple tasks","author":"Wang","year":"2021","journal-title":"arXiv:2105.04206"},{"key":"ref43","article-title":"YOLOv4: Optimal speed and accuracy of object detection","author":"Bochkovskiy","year":"2020","journal-title":"arXiv:2004.10934"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"ref45","article-title":"DSSD: Deconvolutional single shot detector","author":"Fu","year":"2017","journal-title":"arXiv:1701.06659"},{"key":"ref46","article-title":"FSSD: Feature fusion single shot multibox detector","author":"Li","year":"2017","journal-title":"arXiv:1712.00960"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_32"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00972"},{"key":"ref50","article-title":"Object detection made simpler by eliminating heuristic NMS","author":"Zhou","year":"2021","journal-title":"arXiv:2101.11782"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3002345"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00975"},{"key":"ref53","first-page":"1","article-title":"Reppoints v2: Verification meets regression for object detection","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_24"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.25088\/ComplexSystems.23.3.197"},{"key":"ref56","article-title":"Probabilistic two-stage detection","author":"Zhou","year":"2021","journal-title":"arXiv:2103.07461"},{"key":"ref57","article-title":"On the relationship between self-attention and convolutional layers","author":"Cordonnier","year":"2019","journal-title":"arXiv:1911.03584"},{"key":"ref58","article-title":"Transformers in vision: A survey","author":"Khan","year":"2021","journal-title":"arXiv:2101.01169"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_20"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref61","article-title":"Toward transformer-based object detection","author":"Beal","year":"2020","journal-title":"arXiv:2012.09958"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref63","article-title":"Focal self-attention for local-global interactions in vision transformers","author":"Yang","year":"2021","journal-title":"arXiv:2107.00641"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00729"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00913"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref67","article-title":"Dynamic feature pyramid networks for object detection","author":"Zhu","year":"2020","journal-title":"arXiv:2012.00779"},{"key":"ref68","article-title":"DropBlock: A regularization method for convolutional networks","author":"Ghiasi","year":"2018","journal-title":"arXiv:1810.12890"},{"key":"ref69","article-title":"Categorical reparameterization with Gumbel\u2013Softmax","author":"Jang","year":"2016","journal-title":"arXiv:1611.01144"},{"key":"ref70","article-title":"COCO-text: Dataset and benchmark for text detection and recognition in natural images","author":"Veit","year":"2016","journal-title":"arXiv:1601.07140"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00747"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09551884.pdf?arnumber=9551884","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,24]],"date-time":"2024-01-24T01:15:20Z","timestamp":1706058920000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9551884\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":73,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3116324","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}