{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T22:39:21Z","timestamp":1757630361720,"version":"3.44.0"},"reference-count":83,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Artificial Intelligence-National Science and Technology Major Project","award":["2023ZD0121200"],"award-info":[{"award-number":["2023ZD0121200"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62222212","62336001"],"award-info":[{"award-number":["62222212","62336001"]}],"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":[[2025,9]]},"DOI":"10.1109\/tcsvt.2025.3558088","type":"journal-article","created":{"date-parts":[[2025,4,4]],"date-time":"2025-04-04T16:55:29Z","timestamp":1743785729000},"page":"9365-9383","source":"Crossref","is-referenced-by-count":0,"title":["Fully Semantic Gap Recovery for End-to-End Image Captioning"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-5273-8212","authenticated-orcid":false,"given":"Jingchun","family":"Gao","sequence":"first","affiliation":[{"name":"School of Cyberspace Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2839-8693","authenticated-orcid":false,"given":"Lei","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9561-7550","authenticated-orcid":false,"given":"Jingyu","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5739-8126","authenticated-orcid":false,"given":"Zhendong","family":"Mao","sequence":"additional","affiliation":[{"name":"School of Cyberspace Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3107035"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3067449"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2965966"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3121062"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00473"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3181490"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01521"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20160"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3336371"},{"key":"ref10","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Ren"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref14","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":"ref15","article-title":"How much can CLIP benefit vision-and-language tasks?","author":"Shen","year":"2021","journal-title":"arXiv:2107.06383"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01746"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00282"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01744"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548024"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3343520"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_40"},{"key":"ref22","article-title":"Clip surgery for better explainability with enhancement in open-vocabulary tasks","author":"Li","year":"2023","journal-title":"arXiv:2304.05653"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3425513"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3178844"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045336"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01098"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16328"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3243725"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01749"},{"key":"ref33","article-title":"Expansionnet v2: Block static expansion in fast end to end training for image captioning","author":"Hu","year":"2022","journal-title":"arXiv:2208.06551"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_10"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/2072298.2072405"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-014-0399-4"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01748"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02237"},{"key":"ref39","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":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01062"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00553"},{"key":"ref43","article-title":"SimVLM: Simple visual language model pretraining with weak supervision","author":"Wang","year":"2021","journal-title":"arXiv:2108.10904"},{"key":"ref44","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":"ref45","article-title":"CoCa: Contrastive captioners are image-text foundation models","author":"Yu","year":"2022","journal-title":"arXiv:2205.01917"},{"key":"ref46","article-title":"Image as a foreign language: BEiT pretraining for all vision and vision-language tasks","author":"Wang","year":"2022","journal-title":"arXiv:2208.10442"},{"key":"ref47","first-page":"23318","article-title":"OFA: Unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref48","article-title":"GIT: A generative image-to-text transformer for vision and language","author":"Wang","year":"2022","journal-title":"arXiv:2205.14100"},{"key":"ref49","article-title":"PaLI: A jointly-scaled multilingual language-image model","author":"Chen","year":"2022","journal-title":"arXiv:2209.06794"},{"key":"ref50","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref51","first-page":"34892","article-title":"Visual instruction tuning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Liu"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00731"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3454274"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611792"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3287506"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1016\/j.displa.2024.102715"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73113-6_5"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01629"},{"key":"ref60","article-title":"SCLIP: Rethinking self-attention for dense vision-language inference","author":"Wang","year":"2023","journal-title":"arXiv:2312.01597"},{"key":"ref61","article-title":"Recognize anything: A strong image tagging model","author":"Zhang","year":"2023","journal-title":"arXiv:2306.03514"},{"key":"ref62","first-page":"18661","article-title":"Supervised contrastive learning","volume-title":"Proc. NIPS","author":"Khosla"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref64","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Houlsby"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_42"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01094"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3183434"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00904"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref73","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":"ref74","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","volume-title":"Proc. Text Summarization Branches Out","author":"Lin"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01745"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2947482"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109420"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.119"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00132"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00754"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11154820\/10949179.pdf?arnumber=10949179","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T17:49:28Z","timestamp":1757526568000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10949179\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9]]},"references-count":83,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3558088","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"type":"print","value":"1051-8215"},{"type":"electronic","value":"1558-2205"}],"subject":[],"published":{"date-parts":[[2025,9]]}}}