{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T21:51:15Z","timestamp":1774043475668,"version":"3.50.1"},"reference-count":69,"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:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62476051"],"award-info":[{"award-number":["62476051"]}],"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":["62176047"],"award-info":[{"award-number":["62176047"]}],"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":["82121003"],"award-info":[{"award-number":["82121003"]}],"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":["U23B2013"],"award-info":[{"award-number":["U23B2013"]}],"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":["62276176"],"award-info":[{"award-number":["62276176"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018542","name":"Natural Science Foundation of Sichuan Province","doi-asserted-by":"publisher","award":["2024NSFTD0041"],"award-info":[{"award-number":["2024NSFTD0041"]}],"id":[{"id":"10.13039\/501100018542","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tip.2025.3627395","type":"journal-article","created":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T18:47:49Z","timestamp":1763491669000},"page":"2543-2554","source":"Crossref","is-referenced-by-count":0,"title":["ROOT: Region-Word Alignment With Partial Optimal Transport for Open-Vocabulary Object Detection"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0939-0669","authenticated-orcid":false,"given":"Jinhong","family":"Deng","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6856-3342","authenticated-orcid":false,"given":"Yinjie","family":"Lei","sequence":"additional","affiliation":[{"name":"College of Electronics and Information Engineering, Sichuan University, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5559-8594","authenticated-orcid":false,"given":"Wen","family":"Li","sequence":"additional","affiliation":[{"name":"Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0723-4016","authenticated-orcid":false,"given":"Lixin","family":"Duan","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00972"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00644"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00621"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref7","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Simonyan"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00550"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01629"},{"key":"ref12","article-title":"Learning object-language alignments for open-vocabulary object detection","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Lin"},{"key":"ref13","article-title":"CoDet: Co-occurrence guided region-word alignment for open-vocabulary object detection","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ma"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01464"},{"key":"ref15","article-title":"Open-vocabulary object detection via vision and language knowledge distillation","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Gu"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01369"},{"key":"ref17","article-title":"Open-vocabulary object detection upon frozen vision and language models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Kuo"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_21"},{"key":"ref19","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":"ref20","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"139","author":"Jia"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3362062"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28428"},{"key":"ref23","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-540-71050-9","volume":"338","author":"Villani","year":"2009","journal-title":"Optimal Transport: Old and New"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s00205-008-0212-7"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3297408"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3216771"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2938879"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2957850"},{"key":"ref30","article-title":"Detrex: Benchmarking detection transformers","author":"Ren","year":"2023","journal-title":"arXiv:2306.07265"},{"key":"ref31","article-title":"DAB-DETR: Dynamic anchor boxes are better queries for DETR","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Liu"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3263105"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3492733"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20158"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01325"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.01.095"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00079"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108233"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00230"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0620-5"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.49"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3305122"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.5244\/C.35.365"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref45","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv:2304.07193"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.311"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73001-6_15"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref49","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.","author":"Li"},{"key":"ref50","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Li"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3485518"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01416"},{"key":"ref53","first-page":"2292","article-title":"Sinkhorn distances: Lightspeed computation of optimal transport","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"26","author":"Cuturi"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref55","first-page":"5583","article-title":"ViLT: Vision-and-language transformer without convolution or region supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim"},{"key":"ref56","article-title":"Training-free boost for open-vocabulary object detection with confidence aggregation","author":"Zheng","year":"2024","journal-title":"arXiv:2404.08603"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00356"},{"key":"ref58","article-title":"Microsoft COCO captions: Data collection and evaluation server","author":"Chen","year":"2015","journal-title":"arXiv:1504.00325"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00852"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00294"},{"key":"ref61","article-title":"Probabilistic two-stage detection","author":"Zhou","year":"2021","journal-title":"arXiv:2103.07461"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_7"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01368"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_41"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01650"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_16"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_30"},{"key":"ref69","article-title":"RTGen: Generating region-text pairs for open-vocabulary object detection","author":"Chen","year":"2024","journal-title":"arXiv:2405.19854"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/11355710\/11258073.pdf?arnumber=11258073","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T20:01:11Z","timestamp":1774036871000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11258073\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":69,"URL":"https:\/\/doi.org\/10.1109\/tip.2025.3627395","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}