{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,28]],"date-time":"2026-06-28T16:06:25Z","timestamp":1782662785689,"version":"3.54.5"},"reference-count":74,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":["62276120"],"award-info":[{"award-number":["62276120"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Yunnan Fundamental Research Projects","award":["202301AV070004"],"award-info":[{"award-number":["202301AV070004"]}]},{"name":"Yunnan Fundamental Research Projects","award":["202401AS070106"],"award-info":[{"award-number":["202401AS070106"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2025.3535345","type":"journal-article","created":{"date-parts":[[2025,1,30]],"date-time":"2025-01-30T14:20:10Z","timestamp":1738246810000},"page":"3979-3991","source":"Crossref","is-referenced-by-count":7,"title":["Phrase Decoupling Cross-Modal Hierarchical Matching and Progressive Position Correction for Visual Grounding"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9051-9612","authenticated-orcid":false,"given":"Minghong","family":"Xie","sequence":"first","affiliation":[{"name":"Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-5717-5290","authenticated-orcid":false,"given":"Mengzhao","family":"Wang","sequence":"additional","affiliation":[{"name":"Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2462-6174","authenticated-orcid":false,"given":"Huafeng","family":"Li","sequence":"additional","affiliation":[{"name":"Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2347-5642","authenticated-orcid":false,"given":"Yafei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0783-5273","authenticated-orcid":false,"given":"Dapeng","family":"Tao","sequence":"additional","affiliation":[{"name":"FIST LAB, School of Information Science and Engineering, Yunnan University, Kunming, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4012-461X","authenticated-orcid":false,"given":"Zhengtao","family":"Yu","sequence":"additional","affiliation":[{"name":"Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3296823"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICME52920.2022.9859880"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00928"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611721"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3090426"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01837"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3219642"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475317"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ITOEC.2018.8740604"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01746"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01745"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00512"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00502"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00503"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01438"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01738"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00708"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00142"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2911066"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00477"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16188"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3183827"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3147385"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3241802"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3227466"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00179"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01661"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413850"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475313"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413902"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00474"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00427"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2973983"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00205"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00478"},{"key":"ref39","article-title":"YOLOV3: An incremental improvement","author":"Redmon","year":"2018"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_23"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01089"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"ref44","article-title":"An image is worth 16  16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3247103"},{"key":"ref46","article-title":"Pyramid self-attention polymerization learning for semi-supervised skeleton-based action recognition","author":"Xu","year":"2023"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3222871"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3175605"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01506"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3250471"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3328185"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3321501"},{"key":"ref53","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref54","first-page":"1638","article-title":"Contextual string embeddings for sequence labeling","volume-title":"Proc. 27th Int. Conf. Comput. Linguistics","author":"Akbik","year":"2018"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n19-1423"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.470"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2926266"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00447"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01005"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_35"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00208"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.123223"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3181516"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612584"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2023.3324362"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2587640"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2009.03.008"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref73","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov","year":"2018"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/10858434.pdf?arnumber=10858434","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,9]],"date-time":"2025-07-09T23:19:53Z","timestamp":1752103193000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10858434\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":74,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3535345","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}