{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T05:20:12Z","timestamp":1768368012757,"version":"3.49.0"},"reference-count":71,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62202385"],"award-info":[{"award-number":["62202385"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["G2021KY05103"],"award-info":[{"award-number":["G2021KY05103"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key Construction Discipline Scientific Research Capability Promotion Project of Guangdong Province","award":["2022ZDJS015"],"award-info":[{"award-number":["2022ZDJS015"]}]},{"name":"Dazhi Leading Talent Project of Guangdong Polytechnic Normal University"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tmm.2025.3632649","type":"journal-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:50:18Z","timestamp":1763146218000},"page":"757-771","source":"Crossref","is-referenced-by-count":0,"title":["Cas-OVD: Cascaded Open-Vocabulary Detection of Small Objects Using Multi-Refined Region Proposal Network in Autonomous Driving"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0120-4585","authenticated-orcid":false,"given":"Zhenyu","family":"Fang","sequence":"first","affiliation":[{"name":"School of Software, Northwestern Polytechnical University, Xi'an, China"}]},{"given":"Yulong","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Software, Northwestern Polytechnical University, Xi'an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6116-3194","authenticated-orcid":false,"given":"Jinchang","family":"Ren","sequence":"additional","affiliation":[{"name":"School of Computer Science, Guangdong Polytechnic Normal University, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5249-2148","authenticated-orcid":false,"given":"Jiangbin","family":"Zheng","sequence":"additional","affiliation":[{"name":"School of Software, Northwestern Polytechnical University, Xi'an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0224-0078","authenticated-orcid":false,"given":"Yijun","family":"Yan","sequence":"additional","affiliation":[{"name":"Joint Laboratory of Power Remote Sensing Technology, Electric Power Research Institute, Yunnan Power Grid Company Ltd., Kunming, China"}]},{"given":"Lixiang","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Northwestern Polytechnical University, Xi'an, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.l007\/978-3-319-46448-0_2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref4","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Krizhevsky","year":"2012"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01416"},{"key":"ref6","first-page":"1","article-title":"Open-vocabulary object detection via vision and language knowledge distillation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gu","year":"2022"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01629"},{"key":"ref8","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n19-1423"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.114602"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00308"},{"key":"ref13","first-page":"1432","article-title":"Cascade RPN: Delving into high-quality region proposal network with adaptive convolution","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vu","year":"2019"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00644"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01330"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00550"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00852"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00271"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3290594"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3119563"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.60"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_31"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108998"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.211"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref30","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Simonyan","year":"2015"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00581"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01422"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref35","first-page":"5561","article-title":"Soft-NMSimproving object detection with one line of code","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis.","author":"Bodla","year":"2017"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_24"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.690"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2019.00019"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1911.08287"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00953"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539906"},{"key":"ref46","article-title":"SIoU loss: More powerful learning for bounding box regression","author":"Gevorgyan","year":"2022"},{"key":"ref47","article-title":"MMDetection: Open MMlab detection toolbox and benchmark","author":"Chen","year":"2019"},{"key":"ref48","article-title":"GPT-4 technical report","author":"Achiam","year":"2023"},{"key":"ref49","article-title":"Detectron2","author":"Wu","year":"2019"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.534"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1162\/neco_a_01362"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3234368"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2929059"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_7"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01369"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_21"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_41"},{"key":"ref59","first-page":"1","article-title":"Learning object-language alignments for open-vocabulary object detection","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lin","year":"2023"},{"key":"ref60","first-page":"71078","article-title":"CoDet: Co-occurrence guided region-word alignment for open-vocabulary object detection","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ma","year":"2024"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01464"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3381835"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01599"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3519195"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3519173"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2025.3540784"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2024.109730"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.127585"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2024.3384609"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/11342315\/11248945.pdf?arnumber=11248945","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T20:59:40Z","timestamp":1768337980000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11248945\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":71,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3632649","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}