{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,3]],"date-time":"2026-02-03T08:56:59Z","timestamp":1770109019328,"version":"3.49.0"},"reference-count":83,"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:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Institute of Information and Communications Technology Planning and Evaluation"},{"name":"Korean Government (MSIT) through the Artificial Intelligence Graduate School Program","award":["RS-2019-II190079"],"award-info":[{"award-number":["RS-2019-II190079"]}]},{"DOI":"10.13039\/100018202","name":"Information Technology Research Center","doi-asserted-by":"publisher","award":["IITP-2025-RS-2024-00436857"],"award-info":[{"award-number":["IITP-2025-RS-2024-00436857"]}],"id":[{"id":"10.13039\/100018202","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3655392","type":"journal-article","created":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T20:55:44Z","timestamp":1768856144000},"page":"14709-14721","source":"Crossref","is-referenced-by-count":0,"title":["InterHier: Learning Interconnected Hierarchical Semantics for Open-Vocabulary Object Detection"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-7684-3885","authenticated-orcid":false,"given":"Yeong-Jin","family":"Kim","sequence":"first","affiliation":[{"name":"Department of Artificial Intelligence, Korea University, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4200-5136","authenticated-orcid":false,"given":"Ho-Joong","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Artificial Intelligence, Korea University, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6249-4996","authenticated-orcid":false,"given":"Seong-Whan","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Artificial Intelligence, Korea University, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref2","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Dosovitskiy"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01782"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2025.3596024"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2015.2395752"},{"key":"ref6","article-title":"3D vision-language Gaussian splatting","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Peng"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3233419"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.1998.711986"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.3390\/rs17091526"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2006.06.014"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3755341"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3137638"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3543063"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3345842"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2025.130571"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0316"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2025.110144"},{"key":"ref18","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Radford"},{"key":"ref19","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Jia"},{"key":"ref20","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Li"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.724"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref29","first-page":"5583","article-title":"ViLT: Vision-and-language transformer without convolution or region supervision","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Kim"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3968"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01574"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_35"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00407"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00550"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3361862"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3413013"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3480691"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.cogr.2021.08.001"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_21"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01629"},{"key":"ref42","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. (NeurIPS)","author":"Ma"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73036-8_10"},{"key":"ref44","article-title":"TextRegion: Text-aligned region tokens from frozen image-text models","author":"Xiao","year":"2025","journal-title":"arXiv:2505.23769"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/7287.001.0001"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00914"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/11527862_24"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15555-0_6"},{"key":"ref49","first-page":"2121","article-title":"DeViSE: A deep visual-semantic embedding model","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"26","author":"Frome"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.940893"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01252"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3560815"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"issue":"8","key":"ref54","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"issue":"140","key":"ref55","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2019","journal-title":"J. Mach. Learn. Res."},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_7"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01316-z"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref62","article-title":"Open-vocabulary object detection via vision and language knowledge distillation","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Gu"},{"key":"ref63","article-title":"Probabilistic two-stage detection","author":"Zhou","year":"2021","journal-title":"arXiv:2103.07461"},{"key":"ref64","article-title":"ImageNet-21K pretraining for the masses","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Ridnik"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_10"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_7"},{"key":"ref67","article-title":"F-VLM: Open-vocabulary object detection upon frozen vision and language models","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Kuo"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_41"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01464"},{"key":"ref70","first-page":"15946","article-title":"Multi-modal classifiers for open-vocabulary object detection","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Kaul"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01369"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01568"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01076"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00681"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_42"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01072"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00679"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01430"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01416"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_16"},{"key":"ref81","article-title":"Learning object-language alignments for open-vocabulary object detection","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Lin"},{"key":"ref82","article-title":"Open vocabulary object detection with proposal mining and prediction equalization","author":"Chen","year":"2022","journal-title":"arXiv:2206.11134"},{"key":"ref83","article-title":"Cyclic contrastive knowledge transfer for open-vocabulary object detection","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Zhang"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11357923.pdf?arnumber=11357923","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,2]],"date-time":"2026-02-02T20:45:50Z","timestamp":1770065150000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11357923\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":83,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3655392","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}