{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T21:01:36Z","timestamp":1775682096988,"version":"3.50.1"},"reference-count":43,"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:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Innovation Theory Technology Group Fund of China Electronics Tian\u2019ao Company Ltd."}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3679948","type":"journal-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T19:51:30Z","timestamp":1775159490000},"page":"51544-51557","source":"Crossref","is-referenced-by-count":0,"title":["DFCap: Zero-Shot Image Captioning With Dynamic Fusion Module"],"prefix":"10.1109","volume":"14","author":[{"given":"Huaming","family":"Ran","sequence":"first","affiliation":[{"name":"National Key Laboratory of Complex Aviation System Simulation, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-6550-5206","authenticated-orcid":false,"given":"Dongzhen","family":"Li","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Harbin Engineering University, Harbin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wensheng","family":"Qiao","sequence":"additional","affiliation":[{"name":"National Key Laboratory of Complex Aviation System Simulation, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liliang","family":"Zhou","sequence":"additional","affiliation":[{"name":"National Key Laboratory of Complex Aviation System Simulation, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Shen","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Harbin Engineering University, Harbin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4837-9956","authenticated-orcid":false,"given":"Haibo","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Harbin Engineering University, Harbin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3617592"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref6","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":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref9","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"issue":"8","key":"ref10","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref11","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.299"},{"key":"ref13","article-title":"DeCap: Decoding CLIP latents for zero-shot captioning via text-only training","author":"Li","year":"2023","journal-title":"arXiv:2303.03032"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00383"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00252"},{"key":"ref17","article-title":"Connect, collapse, corrupt: Learning cross-modal tasks with uni-modal data","author":"Zhang","year":"2024","journal-title":"arXiv:2401.08567"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1280"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/481"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00291"},{"key":"ref21","article-title":"Language models can see: Plugging visual controls in text generation","author":"Su","year":"2022","journal-title":"arXiv:2205.02655"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16258"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16328"},{"key":"ref26","article-title":"ClipCap: CLIP prefix for image captioning","author":"Mokady","year":"2021","journal-title":"arXiv:2111.09734"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096424"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00278"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00425"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00751"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01739"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01337"},{"key":"ref33","article-title":"MPLUG-owl3: Towards long image-sequence understanding in multi-modal large language models","author":"Ye","year":"2024","journal-title":"arXiv:2408.04840"},{"key":"ref34","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":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01094"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01748"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/BigData59044.2023.10386812"},{"key":"ref38","article-title":"CPTR: Full transformer network for image captioning","author":"Liu","year":"2021","journal-title":"arXiv:2101.10804"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.128666"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref41","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Li"},{"key":"ref42","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. (ICML)","author":"Li"},{"key":"ref43","article-title":"CoCa: Contrastive captioners are image-text foundation models","author":"Yu","year":"2022","journal-title":"arXiv:2205.01917"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11471300.pdf?arnumber=11471300","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T20:07:44Z","timestamp":1775678864000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11471300\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3679948","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}