{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T16:40:19Z","timestamp":1783183219772,"version":"3.54.6"},"reference-count":98,"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\/501100005089","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["L252009"],"award-info":[{"award-number":["L252009"]}],"id":[{"id":"10.13039\/501100005089","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62571294"],"award-info":[{"award-number":["62571294"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62441614"],"award-info":[{"award-number":["62441614"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62525103"],"award-info":[{"award-number":["62525103"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Tsinghua University-Fuzhou Joint Institute for Data Technology","award":["JIDT2024012"],"award-info":[{"award-number":["JIDT2024012"]}]},{"name":"Key Research and Development Program of Xinjiang","award":["2022B01006"],"award-info":[{"award-number":["2022B01006"]}]},{"name":"CCF-DiDi Gaia Collaborative Research Funds"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tip.2025.3607621","type":"journal-article","created":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T17:36:12Z","timestamp":1758044172000},"page":"5948-5963","source":"Crossref","is-referenced-by-count":6,"title":["Source-Free Object Detection With Detection Transformer"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-5245-349X","authenticated-orcid":false,"given":"Huizai","family":"Yao","sequence":"first","affiliation":[{"name":"BNRist, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5843-6411","authenticated-orcid":false,"given":"Sicheng","family":"Zhao","sequence":"additional","affiliation":[{"name":"BNRist, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuo","family":"Lu","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences, Institute of Automation, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4180-5801","authenticated-orcid":false,"given":"Hui","family":"Chen","sequence":"additional","affiliation":[{"name":"BNRist, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yangyang","family":"Li","sequence":"additional","affiliation":[{"name":"Academy of Cyber, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guoping","family":"Liu","sequence":"additional","affiliation":[{"name":"DiDi Chuxing, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tengfei","family":"Xing","sequence":"additional","affiliation":[{"name":"DiDi Chuxing, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1204-0512","authenticated-orcid":false,"given":"Chenggang","family":"Yan","sequence":"additional","affiliation":[{"name":"School of Automation, Hangzhou Dianzi University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9344-6428","authenticated-orcid":false,"given":"Jianhua","family":"Tao","sequence":"additional","affiliation":[{"name":"BNRist, Department of Automation, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0137-9975","authenticated-orcid":false,"given":"Guiguang","family":"Ding","sequence":"additional","affiliation":[{"name":"BNRist and the School of Software, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1106","article-title":"Imagenet classification with deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Krizhevsky"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref3","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":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref5","article-title":"Concrete problems in AI safety","author":"Amodei","year":"2016","journal-title":"arXiv:1606.06565"},{"key":"ref6","article-title":"Domain adaptation for object detection via style consistency","author":"Rodriguez","year":"2019","journal-title":"arXiv:1911.10033"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00050"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3235367"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02277"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_42"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00936"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475317"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_37"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02278"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28405"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01721"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447182"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02181-w"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i10.17029"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00343"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00785"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25119"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00278"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3376380"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02170-z"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72943-0_19"},{"key":"ref27","first-page":"1195","article-title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Tarvainen"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612273"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP49359.2023.10222353"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00972"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01887"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01605"},{"key":"ref36","article-title":"DAB-DETR: Dynamic anchor boxes are better queries for DETR","author":"Liu","year":"2022","journal-title":"arXiv:2201.12329"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01325"},{"key":"ref38","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhu"},{"key":"ref39","article-title":"DINO: DETR with improved DeNoising anchor boxes for end-to-end object detection","author":"Zhang","year":"2022","journal-title":"arXiv:2203.03605"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00352"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02282"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01224"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58586-0_19"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00326"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02283"},{"key":"ref46","first-page":"4516","article-title":"MeGA-CDA: Memory guided attention for category-aware unsupervised domain adaptive object detection","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Vibashan"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3613116"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3409024"},{"key":"ref49","first-page":"785","article-title":"Domain adaptive YOLO for one-stage cross-domain detection","volume-title":"Proc. Asian Conf. Mach. Learn.","author":"Zhang"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3255106"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3353539"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2024.106230"},{"key":"ref53","first-page":"6028","article-title":"Do we really need to access the source data? Source hypothesis transfer for unsupervised domain adaptation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liang"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00736"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00127"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00445"},{"key":"ref57","article-title":"SpGesture: Source-free domain-adaptive sEMG-based gesture recognition with Jaccard attentive spiking neural network","author":"Guo","year":"2024","journal-title":"arXiv:2405.14398"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3490619"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00888"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00286"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2004.10934"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01128"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01129"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref65","first-page":"18661","article-title":"Supervised contrastive learning","volume-title":"Proc. NIPS","author":"Khosla"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00393"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_45"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref69","article-title":"Generalized focal loss: Learning qualified and distributed bounding boxes for dense object detection","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst. (NIPS)","author":"Li"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.12.102"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00902"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00635"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28227"},{"key":"ref74","first-page":"2017","article-title":"Spatial transformer networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst. Annu. Conf. Neural Inf. Process. Syst.","volume":"28","author":"Jaderberg"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00503"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00507"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01165"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475351"},{"key":"ref79","article-title":"Domain adaptation based object detection for autonomous driving in foggy and rainy weather","author":"Li","year":"2023","journal-title":"arXiv:2307.09676"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/136"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1072-8"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989092"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00271"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16239"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00068"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00821"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_45"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01059"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00743"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00442"},{"key":"ref93","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref94","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00905"},{"key":"ref98","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/10795784\/11164935.pdf?arnumber=11164935","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T12:29:46Z","timestamp":1759235386000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11164935\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":98,"URL":"https:\/\/doi.org\/10.1109\/tip.2025.3607621","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}