{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T22:39:40Z","timestamp":1757630380109,"version":"3.44.0"},"reference-count":38,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100016692","name":"Key Research and Development Program of Xinjiang, China,","doi-asserted-by":"publisher","award":["2022B01006"],"award-info":[{"award-number":["2022B01006"]}],"id":[{"id":"10.13039\/100016692","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62301066","62021002"],"award-info":[{"award-number":["62301066","62021002"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Zhejiang Provincial Natural Science Foundation of China","award":["LDT23F01013F01"],"award-info":[{"award-number":["LDT23F01013F01"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2025,9]]},"DOI":"10.1109\/tcsvt.2025.3552596","type":"journal-article","created":{"date-parts":[[2025,3,18]],"date-time":"2025-03-18T13:45:32Z","timestamp":1742305532000},"page":"9351-9364","source":"Crossref","is-referenced-by-count":0,"title":["Toward Realistic Hierarchical Object Detection: Problem, Benchmark, and Solution"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-4614-8607","authenticated-orcid":false,"given":"Juexiao","family":"Feng","sequence":"first","affiliation":[{"name":"National Research Center for Information Science and Technology (BNRist), School of Software, Tsinghua University, Beijing, China"}]},{"given":"Yuhong","family":"Yang","sequence":"additional","affiliation":[{"name":"National Research Center for Information Science and Technology (BNRist), School of Software, Tsinghua University, Beijing, China"}]},{"given":"Mengyao","family":"Lyu","sequence":"additional","affiliation":[{"name":"National Research Center for Information Science and Technology (BNRist), School of Software, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1952-6083","authenticated-orcid":false,"given":"Tianxiang","family":"Hao","sequence":"additional","affiliation":[{"name":"National Research Center for Information Science and Technology (BNRist), School of Software, Tsinghua University, Beijing, China"}]},{"given":"Yi-Jie","family":"Huang","sequence":"additional","affiliation":[{"name":"OPPO Research Institute, Beijing, China"}]},{"given":"Yanchun","family":"Xie","sequence":"additional","affiliation":[{"name":"OPPO Research Institute, Beijing, China"}]},{"given":"Yaqian","family":"Li","sequence":"additional","affiliation":[{"name":"OPPO Research Institute, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4361-956X","authenticated-orcid":false,"given":"Jungong","family":"Han","sequence":"additional","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8486-6255","authenticated-orcid":false,"given":"Liuyu","family":"Xiang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0137-9975","authenticated-orcid":false,"given":"Guiguang","family":"Ding","sequence":"additional","affiliation":[{"name":"OPPO Research Institute, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540221"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548412"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00073"},{"key":"ref6","first-page":"567","article-title":"Fast and balanced: Efficient label tree learning for large scale object recognition","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"24","author":"Deng"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587410"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2615423"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995720"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2871660"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3104932"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3248791"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3435014"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00445"},{"key":"ref15","first-page":"2121","article-title":"DeViSE: A deep visual-semantic embedding model","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"26","author":"Frome"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01252"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58598-3_11"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_15"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01616"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.690"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/219717.219748"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00131"},{"key":"ref23","first-page":"18034","article-title":"Hierarchical classification at multiple operating points","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Valmadre"},{"key":"ref24","article-title":"Leveraging hierarchical structures for few-shot musical instrument recognition","author":"Flores Garcia","year":"2021","journal-title":"arXiv:2107.07029"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.5244\/c.35.20"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01817"},{"key":"ref27","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01629"},{"key":"ref30","article-title":"Zero-shot detection via vision and language knowledge distillation","author":"Gu","year":"2021","journal-title":"arXiv:2104.13921"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_21"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01369"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01316-z"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00852"},{"key":"ref35","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref36","article-title":"Evaluating large-vocabulary object detectors: The devil is in the details","author":"Dave","year":"2022","journal-title":"arXiv:2102.01066"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1906.07155"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1907.11692"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11154820\/10930933.pdf?arnumber=10930933","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T17:49:20Z","timestamp":1757526560000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10930933\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9]]},"references-count":38,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3552596","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"type":"print","value":"1051-8215"},{"type":"electronic","value":"1558-2205"}],"subject":[],"published":{"date-parts":[[2025,9]]}}}