{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T20:01:09Z","timestamp":1784923269956,"version":"3.55.0"},"reference-count":97,"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":[{"name":"Shanghai Artificial Intelligence Laboratory and in part by the China Postdoctoral Science Foundation","award":["2025M771515"],"award-info":[{"award-number":["2025M771515"]}]},{"name":"Anhui Postdoctoral Scientific Research Program Foundation","award":["2025C1166"],"award-info":[{"award-number":["2025C1166"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62402472"],"award-info":[{"award-number":["62402472"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tip.2026.3712347","type":"journal-article","created":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T19:47:04Z","timestamp":1784317624000},"page":"7767-7782","source":"Crossref","is-referenced-by-count":0,"title":["VMFormer: Visual Clues-Guided Multi-Stage Transformer for Image Captioning"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-9438-576X","authenticated-orcid":false,"given":"Yuchen","family":"Ren","sequence":"first","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Chen","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-9736-5994","authenticated-orcid":false,"given":"Hongrui","family":"Yuan","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China","place":["Hefei, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9561-7550","authenticated-orcid":false,"given":"Jingyu","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence","place":["Hefei, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6764-3375","authenticated-orcid":false,"given":"Peipei","family":"Song","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China","place":["Hefei, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7060-6708","authenticated-orcid":false,"given":"Lei","family":"Chen","sequence":"additional","affiliation":[{"name":"Institute of Intelligent Machines, Hefei Institutes of Physical Science, Chinese Academy of Sciences","place":["Hefei, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9163-2761","authenticated-orcid":false,"given":"Wanli","family":"Ouyang","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1004-8588","authenticated-orcid":false,"given":"Lan","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China","place":["Hefei, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1956-3367","authenticated-orcid":false,"given":"Jinyang","family":"Guo","sequence":"additional","affiliation":[{"name":"Beihang University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.14569\/IJACSA.2023.0140912"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3638558"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3390\/electronics14163325"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00902"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16258"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01034"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01098"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/91"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3343520"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3528216"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s44163-025-00315-8"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01744"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00282"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00278"},{"key":"ref18","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023","journal-title":"arXiv:2301.12597"},{"key":"ref19","first-page":"1171","article-title":"Scheduled sampling for sequence prediction with recurrent neural networks","volume-title":"Proc. NeurIPS","author":"Bengio"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-2049"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.205"},{"key":"ref22","article-title":"Improving generalization of transformer for speech recognition with parallel schedule sampling and relative positional embedding","author":"Zhou","year":"2019","journal-title":"arXiv:1911.00203"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.264"},{"key":"ref24","article-title":"Parallel scheduled sampling","author":"Duckworth","year":"2019","journal-title":"arXiv:1906.04331"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16328"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3243725"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3336371"},{"key":"ref29","article-title":"How much can CLIP benefit vision-and-language tasks?","author":"Shen","year":"2021","journal-title":"arXiv:2107.06383"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01746"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01062"},{"key":"ref32","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"arXiv:2103.00020"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref35","first-page":"1","article-title":"Sequence level training with recurrent neural networks","volume-title":"Proc. ICLR","author":"Ranzato"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref41","first-page":"190","article-title":"Collecting highly parallel data for paraphrase evaluation","volume-title":"Proc. 49th Annu. Meeting Assoc. Comput. Linguistics, Human Lang. Technol.","author":"Chen"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00904"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_44"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-2066"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref47","first-page":"11135","article-title":"Image captioning: Transforming objects into words","volume-title":"Proc. NeurIPS","author":"Herdade"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00473"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2947482"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16258"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3183434"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3181490"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3178844"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548409"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01748"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548024"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20160"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109420"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3159811"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02237"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/3663667"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110941"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.3115\/1626355.1626389"},{"key":"ref64","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","volume-title":"Proc. ACL Workshops","author":"Lin"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1437"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref68","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. ICLR","author":"Kingma"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01426"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00553"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01745"},{"key":"ref73","article-title":"GIT: A generative image-to-text transformer for vision and language","author":"Wang","year":"2022","journal-title":"arXiv:2205.14100"},{"key":"ref74","article-title":"Multi-grained vision language pre-training: Aligning texts with visual concepts","author":"Zeng","year":"2021","journal-title":"arXiv:2111.08276"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01094"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3093725"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3067449"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3107035"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3155795"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2642953"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.667"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2976552"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3121062"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1145\/3682067"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01088"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01311"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01329"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00157"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01741"},{"key":"ref90","article-title":"UniVL: A unified video and language pre-training model for multimodal understanding and generation","author":"Luo","year":"2020","journal-title":"arXiv:2002.06353"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01742"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01743"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_10"},{"key":"ref94","article-title":"PaLI: A jointly-scaled multilingual language-image model","author":"Chen","year":"2022","journal-title":"arXiv:2209.06794"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01001"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00356"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475607"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/11355710\/11614193.pdf?arnumber=11614193","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T19:02:11Z","timestamp":1784919731000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11614193\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":97,"URL":"https:\/\/doi.org\/10.1109\/tip.2026.3712347","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}