{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T16:22:11Z","timestamp":1791303731757,"version":"4.1.0"},"reference-count":57,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","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":["61772563"],"award-info":[{"award-number":["61772563"]}],"id":[{"id":"10.13039\/501100001809","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":[[2025,1]]},"DOI":"10.1109\/tcsvt.2024.3452437","type":"journal-article","created":{"date-parts":[[2024,8,30]],"date-time":"2024-08-30T18:01:47Z","timestamp":1725040907000},"page":"91-102","source":"Crossref","is-referenced-by-count":6,"title":["Exploring Vision-Language Foundation Model for Novel Object Captioning"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1592-3444","authenticated-orcid":false,"given":"Jianjie","family":"Luo","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9603-1113","authenticated-orcid":false,"given":"Yehao","family":"Li","sequence":"additional","affiliation":[{"name":"HiDream.ai Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4344-8898","authenticated-orcid":false,"given":"Yingwei","family":"Pan","sequence":"additional","affiliation":[{"name":"HiDream.ai Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7587-101X","authenticated-orcid":false,"given":"Ting","family":"Yao","sequence":"additional","affiliation":[{"name":"HiDream.ai Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4975-7093","authenticated-orcid":false,"given":"Jianlin","family":"Feng","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6104-2322","authenticated-orcid":false,"given":"Hongyang","family":"Chao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2497-7732","authenticated-orcid":false,"given":"Tao","family":"Mei","sequence":"additional","affiliation":[{"name":"HiDream.ai Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2599174"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2598339"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3121062"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3181490"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3336371"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3243725"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3343520"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1098"},{"key":"ref10","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref11","article-title":"Sequence to sequence learning with neural networks","author":"Sutskever","year":"2014","journal-title":"arXiv:1409.3215"},{"key":"ref12","article-title":"Neural machine translation by jointly learning to align and translate","author":"Bahdanau","year":"2015","journal-title":"arXiv:1409.0473"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/2589\/1\/012012"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.524"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2708709"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_42"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01094"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00271"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref23","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01098"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01746"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02237"},{"key":"ref29","first-page":"1","article-title":"Image captioning: Transforming objects into words","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Herdade"},{"key":"ref30","article-title":"How much can clip benefit vision-and-language tasks?","author":"Shen","year":"2022","journal-title":"arXiv:2107.06383"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.8"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.130"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.559"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00754"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01278"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2965966"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.104"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/86"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3460426.3463587"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref44","first-page":"1","article-title":"Partially-supervised image captioning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Anderson"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00904"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref47","volume-title":"Openimages: A Public Dataset for Large-scale Multi-label and Multi-class Image Classification","author":"Krasin","year":"2017"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3478331"},{"key":"ref49","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2015","journal-title":"arXiv:1412.6980"},{"key":"ref50","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","volume-title":"Proc. ACL Workshop Intrinsic Extrinsic Eval. Measures Mach. Transl. Summarization","author":"Banerjee"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3144984"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01747"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01422"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00553"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00278"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/10857816\/10659916.pdf?arnumber=10659916","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,30]],"date-time":"2025-01-30T19:24:50Z","timestamp":1738265090000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10659916\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":57,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3452437","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1]]}}}