{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T20:11:38Z","timestamp":1779221498804,"version":"3.51.4"},"reference-count":44,"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\/501100014188","name":"Ministry of Science and ICT, South Korea","doi-asserted-by":"publisher","award":["IITP-2024-RS-2024-00418847"],"award-info":[{"award-number":["IITP-2024-RS-2024-00418847"]}],"id":[{"id":"10.13039\/501100014188","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["RS-2024-00355008"],"award-info":[{"award-number":["RS-2024-00355008"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003561","name":"Ministry of Culture, Sports and Tourism","doi-asserted-by":"publisher","award":["RS-2024-00352578"],"award-info":[{"award-number":["RS-2024-00352578"]}],"id":[{"id":"10.13039\/501100003561","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.2026.3687083","type":"journal-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:54:23Z","timestamp":1777492463000},"page":"5181-5195","source":"Crossref","is-referenced-by-count":0,"title":["FAST-GOAL: Fast and Efficient Global-Local Object Alignment Learning"],"prefix":"10.1109","volume":"35","author":[{"given":"Hyungyu","family":"Choi","sequence":"first","affiliation":[{"name":"Department of Virtual Convergence, Graduate School of Advanced Imaging Science, Multimedia and Films (GSAIM), Chung-Ang University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Young Kyun","family":"Jang","sequence":"additional","affiliation":[{"name":"independent researcher, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0623-8074","authenticated-orcid":false,"given":"Chanho","family":"Eom","sequence":"additional","affiliation":[{"name":"Department of Virtual Convergence, Graduate School of Advanced Imaging Science, Multimedia and Films (GSAIM), Chung-Ang University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"8748","article-title":"Learning transferable visual representations from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref2","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01759"},{"key":"ref4","first-page":"26070","article-title":"Modeling caption diversity in contrastive vision-language pretraining","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lavoie"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref6","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":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.5573\/IEIESPC.2024.13.6.541"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.5573\/IEIESPC.2025.14.3.419"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref11","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Simonyan"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73027-6_17"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02521"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00385"},{"key":"ref19","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":"ref20","article-title":"Florence: A new foundation model for computer vision","author":"Yuan","year":"2021","journal-title":"arXiv:2111.11432"},{"key":"ref21","first-page":"1","article-title":"FG-CLIP: Fine-grained visual and textual alignment","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xie"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72983-6_18"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72643-9_22"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01351"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_24"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01621"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01572"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.357"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.389"},{"key":"ref30","first-page":"1","article-title":"Contrastive localized language-image pre-training","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3191"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2614"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0875"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.02209"},{"key":"ref35","first-page":"26183","article-title":"You only look at one sequence: Rethinking transformer in vision through object detection","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Fang"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref37","article-title":"LLaVA-NeXT: Improved reasoning, OCR, and world knowledge","author":"Liu","year":"2024"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref39","article-title":"Qwen technical report","volume-title":"arXiv:2309.16609","author":"Bai","year":"2023"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref41","article-title":"Gemini: A family of highly capable multimodal models","author":"Team","year":"2023","journal-title":"arXiv:2312.11805"},{"key":"ref42","first-page":"1395","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Dosovitskiy"},{"key":"ref43","article-title":"EVA-CLIP: Improved training techniques for CLIP at scale","author":"Sun","year":"2023","journal-title":"arXiv:2303.15389"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1037\/h0070888"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/11355710\/11501196.pdf?arnumber=11501196","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T19:51:48Z","timestamp":1779220308000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11501196\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/tip.2026.3687083","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}