{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T16:57:28Z","timestamp":1783529848859,"version":"3.55.0"},"reference-count":103,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2023YFC3807603"],"award-info":[{"award-number":["2023YFC3807603"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"name":"RIE2020 Industry Alignment Fund Industry Collaboration Projects (IAF-ICP) Funding Initiative"},{"name":"cash and in-kind contributions from the industry partne"},{"DOI":"10.13039\/501100006730","name":"Singapore Ministry of Education (MOE) Academic Research Fund (AcRF) Tier 2","doi-asserted-by":"publisher","award":["MOE-T2EP20120-0001"],"award-info":[{"award-number":["MOE-T2EP20120-0001"]}],"id":[{"id":"10.13039\/501100006730","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2025,5]]},"DOI":"10.1109\/tcsvt.2024.3520734","type":"journal-article","created":{"date-parts":[[2024,12,20]],"date-time":"2024-12-20T19:09:13Z","timestamp":1734721753000},"page":"5037-5050","source":"Crossref","is-referenced-by-count":8,"title":["DST-Det: Open-Vocabulary Object Detection via Dynamic Self-Training"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-7178-5358","authenticated-orcid":false,"given":"Shilin","family":"Xu","sequence":"first","affiliation":[{"name":"National Key Laboratory of General Artificial Intelligence, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiangtai","family":"Li","sequence":"additional","affiliation":[{"name":"TikTok, Raffles Quay, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Size","family":"Wu","sequence":"additional","affiliation":[{"name":"S-Lab, Nanyang Technological University, Jurong West, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2748-4514","authenticated-orcid":false,"given":"Wenwei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8735-2516","authenticated-orcid":false,"given":"Yunhai","family":"Tong","sequence":"additional","affiliation":[{"name":"National Key Laboratory of General Artificial Intelligence, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5345-1591","authenticated-orcid":false,"given":"Chen","family":"Change Loy","sequence":"additional","affiliation":[{"name":"S-Lab, Nanyang Technological University, Jurong West, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"23716","article-title":"Flamingo: A visual language model for few-shot learning","volume-title":"Proc. NeurIPS","author":"Alayrac"},{"key":"ref2","article-title":"Three ways to improve feature alignment for open vocabulary detection","author":"Arandjelovi\u0107","year":"2023","journal-title":"arXiv:2303.13518"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16788-1_24"},{"key":"ref4","article-title":"Investigating the role of attribute context in vision-language models for object recognition and detection","author":"Buettner","year":"2023","journal-title":"arXiv:2303.10093"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_40"},{"key":"ref7","article-title":"Open vocabulary object detection with proposal mining and prediction equalization","author":"Chen","year":"2022","journal-title":"arXiv:2206.11134"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3286896"},{"key":"ref9","article-title":"Open-vocabulary object detection using pseudo caption labels","author":"Cho","year":"2023","journal-title":"arXiv:2303.13040"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01369"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_41"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_16"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_31"},{"key":"ref15","first-page":"1","article-title":"Open-vocabulary object detection via vision and language knowledge distillation","volume-title":"Proc. ICLR","author":"Gu"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00550"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00689"},{"key":"ref20","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. ICML","author":"Jia"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3268680"},{"key":"ref22","first-page":"15946","article-title":"Multi-modal classifiers for open-vocabulary object detection","volume-title":"Proc. ICML","author":"Kaul"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01430"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01072"},{"key":"ref25","first-page":"5583","article-title":"ViLT: Vision-and-language transformer without convolution or region supervision","volume-title":"Proc. ICML","author":"Kim"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref27","first-page":"1","article-title":"F-VLM: Open-vocabulary object detection upon frozen vision and language models","volume-title":"Proc. ICLR","author":"Kuo"},{"key":"ref28","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. ICML","author":"Li"},{"key":"ref29","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. NeurIPS","author":"Li"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01578"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02640"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02240"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01100"},{"key":"ref35","first-page":"1","article-title":"Learning object-language alignments for open-vocabulary object detection","volume-title":"Proc. ICLR","author":"Lin"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3292940"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3253210"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00304"},{"key":"ref42","first-page":"1","article-title":"DAB-DETR: Dynamic anchor boxes are better queries for DETR","volume-title":"Proc. ICLR","author":"Liu"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1512.02325"},{"key":"ref44","first-page":"1","article-title":"CoDet: Co-occurrence guided region-word alignment for open-vocabulary object detection","volume-title":"Proc. NeurIPS","volume":"36","author":"Ma"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01368"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3322465"},{"key":"ref47","first-page":"1","article-title":"Scaling open-vocabulary object detection","volume-title":"Proc. NeurIPS","volume":"36","author":"Minderer"},{"key":"ref48","first-page":"728","article-title":"Simple open-vocabulary object detection with vision transformers","volume-title":"Proc. ECCV","author":"Minderer"},{"key":"ref49","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. ICML","author":"Radford"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01755"},{"key":"ref51","first-page":"33781","article-title":"Bridging the gap between object and image-level representations for open-vocabulary detection","volume-title":"Proc. NeurIPS","author":"Rasheed"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref53","first-page":"4175","article-title":"Balanced meta-softmax for long-tailed visual recognition","volume-title":"Proc. NeurIPS","author":"Ren"},{"key":"ref54","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. NeurIPS","author":"Ren"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01228-7"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01441"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612407"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00939"},{"key":"ref59","article-title":"Prompt-guided transformers for end-to-end open-vocabulary object detection","author":"Song","year":"2023","journal-title":"arXiv:2303.14386"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01422"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00173"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01168"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3323879"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3301854"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3032166"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3263557"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01817"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01076"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00681"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_43"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00312"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3269951"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3361862"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413970"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01464"},{"key":"ref77","first-page":"1","article-title":"CLIPSelf: Vision transformer distills itself for open-vocabulary dense prediction","volume-title":"Proc. ICLR","author":"Wu"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00679"},{"key":"ref79","article-title":"MosaicFusion: Diffusion models as data augmenters for large vocabulary instance segmentation","author":"Xie","year":"2023","journal-title":"arXiv:2309.13042"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3286072"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00289"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3198329"},{"key":"ref83","first-page":"32215","article-title":"Convolutions die hard: Open-vocabulary segmentation with single frozen convolutional CLIP","volume-title":"Proc. NeurIPS","author":"Yu"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3318672"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_7"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01416"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00100"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3287167"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00978"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3277621"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00239"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01322"},{"key":"ref93","first-page":"13938","article-title":"Improving pseudo labels for open-vocabulary object detection","volume-title":"Proc. CVPR","author":"Zhao"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_10"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3326279"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01629"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_40"},{"key":"ref98","article-title":"Rethinking evaluation metrics of open-vocabulary segmentaion","author":"Zhou","year":"2023","journal-title":"arXiv:2311.03352"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_21"},{"key":"ref100","article-title":"Objects as points","author":"Zhou","year":"2019","journal-title":"arXiv:1904.07850"},{"key":"ref101","first-page":"1","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","volume-title":"Proc. ICLR","author":"Zhu"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00906"},{"key":"ref103","first-page":"3833","article-title":"Rethinking pre-training and self-training","volume-title":"Proc. NeurIPS","author":"Zoph"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/10989278\/10810446.pdf?arnumber=10810446","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,7]],"date-time":"2025-05-07T04:21:00Z","timestamp":1746591660000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10810446\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5]]},"references-count":103,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3520734","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5]]}}}