{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T19:11:44Z","timestamp":1782328304518,"version":"3.54.5"},"reference-count":57,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00294","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"3069-3079","source":"Crossref","is-referenced-by-count":2,"title":["STEP-DETR: Advancing DETR-based Semi-Supervised Object Detection with Super Teacher and Pseudo-Label Guided Text Queries"],"prefix":"10.1109","author":[{"given":"Tahira","family":"Shehzadi","sequence":"first","affiliation":[{"name":"DFKI"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Khurram Azeem","family":"Hashmi","sequence":"additional","affiliation":[{"name":"DFKI"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shalini","family":"Sarode","sequence":"additional","affiliation":[{"name":"DFKI"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Didier","family":"Stricker","sequence":"additional","affiliation":[{"name":"DFKI"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Muhammad Zeshan","family":"Afzal","sequence":"additional","affiliation":[{"name":"DFKI"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MCG.2025.3548554"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","article-title":"End-toend object detection with transformers","volume-title":"Computer Vision - ECCV 2020\u201316th European Conference","author":"Carion","year":"2020"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00477"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00610"},{"key":"ref5","article-title":"Mixed pseudo labels for semi-supervised object detection","author":"Chen","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref6","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv preprint arXiv"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0733-5"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IMTIC53841.2021.9719809"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ISIE.2010.5636922"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref11","article-title":"Pars: Pseudolabel aware robust sample selection for learning with noisy labels","author":"Goel","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01412"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00485"},{"key":"ref15","article-title":"Consistency-based semi-supervised learning for object detection","author":"Jeong","year":"2019","journal-title":"Neural Information Processing Systems"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01887"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01325"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_27"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812234"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01069"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018690"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref23","article-title":"DAB-DETR: dynamic anchor boxes are better queries for DETR","volume":"abs\/2201.12329","author":"Liu","year":"2022","journal-title":"CoRR"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref25","article-title":"Unbiased teacher for semi-supervised object detection","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Liu"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00959"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ECTC51906.2022.00297"},{"key":"ref28","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on machine learning","author":"Radford"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1804.02767"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/RAEECS50817.2020.9265692"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.3390\/app12199398"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-41679-8_4"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.3390\/s25196025"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00558"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.3390\/s26010310"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-70549-6_18"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-70546-5_2"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-98691-8_1"},{"key":"ref40","article-title":"A simple semisupervised learning framework for object detection","volume":"abs\/2005.04757","author":"Sohn","year":"2020","journal-title":"CoRR"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00315"},{"key":"ref42","article-title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","volume":"30","author":"Tarvainen","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00972"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00401"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00915"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00316"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01070"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00305"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00588"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3389497"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1556\/1848.2021.00315"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_7"},{"key":"ref53","article-title":"DINO: DETR with improved denoising anchor boxes for end-to-end object detection","volume-title":"The Eleventh International Conference on Learning Representations","author":"Zhang"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02280"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_3"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00407"},{"key":"ref57","article-title":"Deformable $\\{\\operatorname{detr}\\}$: Deformable transformers for end-to-end object detection","volume-title":"International Conference on Learning Representations","author":"Zhu"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11449025.pdf?arnumber=11449025","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:16:42Z","timestamp":1777529802000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11449025\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00294","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}