{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T00:16:48Z","timestamp":1784333808317,"version":"3.55.0"},"reference-count":75,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Alibaba Cloud through the Research Intern Program"},{"name":"Zhejiang Provincial Natural Science Foundation of China","award":["LDT23F01013F01"],"award-info":[{"award-number":["LDT23F01013F01"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tip.2024.3501853","type":"journal-article","created":{"date-parts":[[2024,11,25]],"date-time":"2024-11-25T18:55:59Z","timestamp":1732560959000},"page":"183-195","source":"Crossref","is-referenced-by-count":63,"title":["ESOD: Efficient Small Object Detection on High-Resolution Images"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-5786-6489","authenticated-orcid":false,"given":"Kai","family":"Liu","sequence":"first","affiliation":[{"name":"College of Biomedical Engineering and Instrument Science, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0418-2553","authenticated-orcid":false,"given":"Zhihang","family":"Fu","sequence":"additional","affiliation":[{"name":"Alibaba Cloud, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7254-1664","authenticated-orcid":false,"given":"Sheng","family":"Jin","sequence":"additional","affiliation":[{"name":"Alibaba Cloud, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2333-2759","authenticated-orcid":false,"given":"Ze","family":"Chen","sequence":"additional","affiliation":[{"name":"Alibaba Cloud, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0900-6965","authenticated-orcid":false,"given":"Fan","family":"Zhou","sequence":"additional","affiliation":[{"name":"College of Biomedical Engineering and Instrument Science, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7901-3047","authenticated-orcid":false,"given":"Rongxin","family":"Jiang","sequence":"additional","affiliation":[{"name":"College of Biomedical Engineering and Instrument Science, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6037-0631","authenticated-orcid":false,"given":"Yaowu","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Biomedical Engineering and Instrument Science, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8662-5818","authenticated-orcid":false,"given":"Jieping","family":"Ye","sequence":"additional","affiliation":[{"name":"Alibaba Cloud, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01283"},{"key":"ref2","first-page":"1","article-title":"Reppoints v2: Verification meets regression for object detection","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Chen"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2956516"},{"key":"ref4","first-page":"1","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Dosovitskiy"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref8","first-page":"1","article-title":"Dino: Detr with improved denoising anchor boxes for end-to-end object detection","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhang"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01301"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913491297"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995586"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00333"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2016.2645610"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093394"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3073319"},{"key":"ref18","article-title":"Vision meets drones: A challenge","author":"Zhu","year":"2018","journal-title":"arXiv:1804.07437"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01291"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2922095"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00294"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240544"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00120"},{"key":"ref24","first-page":"9310","article-title":"SNIPER: Efficient multi-scale training","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Singh"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICME51207.2021.9428241"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3228497"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00084"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2022.116675"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00840"},{"key":"ref30","article-title":"Submanifold sparse convolutional networks","author":"Graham","year":"2017","journal-title":"arXiv:1706.01307"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.3390\/s18103337"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref33","article-title":"Grounding DINO: Marrying DINO with grounded pre-training for open-set object detection","author":"Liu","year":"2023","journal-title":"arXiv:2303.05499"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00313"},{"key":"ref35","article-title":"CornerNet-lite: Efficient keypoint based object detection","author":"Law","year":"2019","journal-title":"arXiv:1904.08900"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_23"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2209.02976"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00377"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414162"},{"key":"ref41","article-title":"Stitcher: Feedback-driven data provider for object detection","author":"Chen","year":"2020","journal-title":"arXiv:2004.12432"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2983686"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00103"},{"issue":"1","key":"ref44","first-page":"1026","article-title":"UFPMP-Det: Toward accurate and efficient object detection on drone imagery","volume-title":"Proc. AAAI Conf. Artif. Intell.","volume":"36","author":"Huang"},{"key":"ref45","article-title":"PerforatedCNNs: Acceleration through elimination of redundant convolutions","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Figurnov"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00239"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_31"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01330"},{"key":"ref49","first-page":"1","article-title":"Categorical reparameterization with gumbel-softmax","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Jang"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref51","volume-title":"Ultralytics\/YOLOv5: V5.0\u2014YOLOv5-P6 1280 Models","author":"Jocher","year":"2020"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"ref53","article-title":"Objects as points","author":"Zhou","year":"2019","journal-title":"arXiv:1904.07850"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref55","first-page":"1","article-title":"Deformable detr: Deformable transformers for end-to-end object detection","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhu"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00853"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref58","article-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017","journal-title":"arXiv:1704.04861"},{"key":"ref59","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Ren"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298684"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00624"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00745"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3166956"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.79"},{"key":"ref65","volume-title":"Computers and Intractability: A Guide To the Theory of NP-Completeness","author":"Garey","year":"1979"},{"key":"ref66","article-title":"YOLOX: Exceeding YOLO series in 2021","author":"Ge","year":"2021","journal-title":"arXiv:2107.08430"},{"key":"ref67","first-page":"1","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Paszke"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00093"},{"key":"ref69","article-title":"Rtmdet: An empirical study of designing real-time object detectors","author":"Lyu","year":"2022","journal-title":"arXiv:2212.07784"},{"key":"ref70","volume-title":"Ultralytics YOLO","author":"Jocher","year":"2023"},{"key":"ref71","first-page":"1","article-title":"Gpvit: A high resolution non-hierarchical vision transformer with group propagation","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Yang"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00203"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2389824"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/10795784\/10767172.pdf?arnumber=10767172","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,19]],"date-time":"2024-12-19T19:44:39Z","timestamp":1734637479000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10767172\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":75,"URL":"https:\/\/doi.org\/10.1109\/tip.2024.3501853","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}