{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,15]],"date-time":"2025-08-15T02:08:26Z","timestamp":1755223706351,"version":"3.43.0"},"reference-count":29,"publisher":"World Scientific Pub Co Pte Ltd","issue":"12","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["Grant No. 12064004"],"award-info":[{"award-number":["Grant No. 12064004"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangxi Science and Technology Program","award":["Guike AB23075076"],"award-info":[{"award-number":["Guike AB23075076"]}]},{"name":"Guangxi Science and Technology Program","award":["Grant Nos. Guike AD21075020"],"award-info":[{"award-number":["Grant Nos. Guike AD21075020"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Int. J. Patt. Recogn. Artif. Intell."],"published-print":{"date-parts":[[2025,9,30]]},"abstract":"<jats:p> Object detection is widely used in many fields, and multi-scale feature extraction is crucial for accurate detection. The Feature Pyramid Network (FPN) is a commonly adopted feature extraction approach in object detection. Nevertheless, direct fusion between top-down feature layers in FPN leads to misalignment and loss of feature information. To address these limitations, this paper proposes a novel feature pyramid network based on FPN, termed SAR-FPN, which consists of two components: the Scale Adaptive Triple-Branch Module (SATM) and the Reverse Feature Fusion Module (RFFM). Specifically, SATM enhances the performance for large objects through its triple-branch design. It selects the appropriate branch based on object scale, assigns suitable receptive fields for objects of different sizes, and performs feature alignment. The RFFM addresses the issue of poor performance in small object detection by implementing a bottom-up feature fusion pathway. Extensive experiments on the PASCAL VOC 2012 and MS COCO 2017 datasets validated the effectiveness of SAR-FPN. <\/jats:p>","DOI":"10.1142\/s021800142550020x","type":"journal-article","created":{"date-parts":[[2025,6,13]],"date-time":"2025-06-13T00:11:24Z","timestamp":1749773484000},"source":"Crossref","is-referenced-by-count":0,"title":["SAR-FPN: Scale Adaptive and Reverse Fusion Object Detection"],"prefix":"10.1142","volume":"39","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-2024-0961","authenticated-orcid":false,"given":"Nuo","family":"Cheng","sequence":"first","affiliation":[{"name":"School of Computer Science and Information Security, Guilin University of Electronic Technology, Guilin 541004, P. R. China"},{"name":"Guangxi Key Laboratory of Image and Graphic Intelligent Processing, Guilin 541004, P. R. China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2822-3340","authenticated-orcid":false,"given":"TaiPing","family":"Xiong","sequence":"additional","affiliation":[{"name":"School of Computer Science and Information Security, Guilin University of Electronic Technology, Guilin 541004, P. R. China"},{"name":"Guangxi Key Laboratory of Image and Graphic Intelligent Processing, Guilin 541004, P. R. China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3945-2958","authenticated-orcid":false,"given":"Gengshen","family":"Cui","sequence":"additional","affiliation":[{"name":"School of Computer Science and Information Security, Guilin University of Electronic Technology, Guilin 541004, P. R. China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-2428-9280","authenticated-orcid":false,"given":"Minghua","family":"Pan","sequence":"additional","affiliation":[{"name":"School of Computer Science and Information Security, Guilin University of Electronic Technology, Guilin 541004, P. R. China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-9868-2189","authenticated-orcid":false,"given":"Xiangjie","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Information Security, Guilin University of Electronic Technology, Guilin 541004, P. R. China"},{"name":"Guangxi Key Laboratory of Image and Graphic Intelligent Processing, Guilin 541004, P. R. China"}]}],"member":"219","published-online":{"date-parts":[[2025,7,31]]},"reference":[{"key":"S021800142550020XBIB002","first-page":"12592","volume-title":"2020 IEEE\/CVF Conf. Computer Vision and Pattern Recognition (CVPR)","author":"Chaoxu G.","year":"2020"},{"key":"S021800142550020XBIB003","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00729"},{"key":"S021800142550020XBIB004","first-page":"1","volume":"60","author":"Gong C.","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"S021800142550020XBIB005","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3376773"},{"issue":"1","key":"S021800142550020XBIB006","first-page":"550","volume":"44","author":"Huang Z.","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"S021800142550020XBIB007","first-page":"821","volume-title":"Proc. IEEE\/CVF Conf. Computer Vision and Pattern Recognition (CVPR)","author":"Jiangmiao P.","year":"2019"},{"key":"S021800142550020XBIB008","first-page":"764","volume-title":"2017 IEEE Int. Conf. Computer Vision (ICCV)","author":"Jifeng D.","year":"2017"},{"key":"S021800142550020XBIB009","first-page":"779","volume-title":"Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR)","author":"Joseph R.","year":"2016"},{"key":"S021800142550020XBIB010","first-page":"2980","volume-title":"2017 IEEE Int. Conf. Computer Vision (ICCV)","author":"Kaiming H.","year":"2017"},{"key":"S021800142550020XBIB011","first-page":"770","volume-title":"2016 IEEE Conf. Computer Vision and Pattern Recognition (CVPR)","author":"Kaiming H.","year":"2016"},{"key":"S021800142550020XBIB012","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00615"},{"key":"S021800142550020XBIB013","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"S021800142550020XBIB015","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"S021800142550020XBIB016","doi-asserted-by":"publisher","DOI":"10.1109\/ICME51207.2021.9428241"},{"key":"S021800142550020XBIB018","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01008"},{"key":"S021800142550020XBIB019","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"S021800142550020XBIB020","first-page":"844","volume-title":"Proc. IEEE\/CVF Int. Conf. Computer Vision (ICCV)","author":"Shihua H.","year":"2021"},{"key":"S021800142550020XBIB021","first-page":"8759","volume-title":"Proc. IEEE\/CVF Conf. Computer Vision and Pattern Recognition (CVPR)","author":"Shu L.","year":"2018"},{"key":"S021800142550020XBIB023","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01422"},{"key":"S021800142550020XBIB024","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"S021800142550020XBIB025","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00972"},{"key":"S021800142550020XBIB026","first-page":"1971","volume-title":"2019 IEEE\/CVF Int. Conf. Computer Vision (ICCV)","author":"Tiancai W.","year":"2019"},{"key":"S021800142550020XBIB027","first-page":"936","volume-title":"Proc. IEEE Conf. Computer Vision and Pattern Recognition","author":"Tsung Yi L.","year":"2017"},{"key":"S021800142550020XBIB029","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"S021800142550020XBIB030","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00247"},{"key":"S021800142550020XBIB032","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3143707"},{"key":"S021800142550020XBIB033","first-page":"3357","volume-title":"2020 IEEE\/CVF Conf. Computer Vision and Pattern Recognition (CVPR)","author":"Yapeng T.","year":"2020"},{"key":"S021800142550020XBIB036","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00978"},{"key":"S021800142550020XBIB037","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2956516"}],"container-title":["International Journal of Pattern Recognition and Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.worldscientific.com\/doi\/pdf\/10.1142\/S021800142550020X","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,12]],"date-time":"2025-08-12T06:25:20Z","timestamp":1754979920000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.worldscientific.com\/doi\/10.1142\/S021800142550020X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,31]]},"references-count":29,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2025,9,30]]}},"alternative-id":["10.1142\/S021800142550020X"],"URL":"https:\/\/doi.org\/10.1142\/s021800142550020x","relation":{},"ISSN":["0218-0014","1793-6381"],"issn-type":[{"type":"print","value":"0218-0014"},{"type":"electronic","value":"1793-6381"}],"subject":[],"published":{"date-parts":[[2025,7,31]]},"article-number":"2550020"}}