{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T05:51:59Z","timestamp":1781589119665,"version":"3.54.5"},"reference-count":58,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62576089"],"award-info":[{"award-number":["62576089"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62576091"],"award-info":[{"award-number":["62576091"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Jiangsu Province Carbon Peak Carbon Neutrality Science and Technology Innovation Special Fund Project","award":["BT2025029"],"award-info":[{"award-number":["BT2025029"]}]},{"name":"Domestic Computing Power Platform of the Network and Information Center of Southeast University"},{"name":"Southeast University Kunpeng &amp; AscendCenter of Cultivation and the Big Data Computing Center of Southeast University"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tmm.2026.3660118","type":"journal-article","created":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T21:17:53Z","timestamp":1771622273000},"page":"4475-4484","source":"Crossref","is-referenced-by-count":0,"title":["Adaptively Clustering Neighbor Elements for Image-Text Generation"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-5871-6973","authenticated-orcid":false,"given":"Zihua","family":"Wang","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering and the Key Laboratory of New Generation Artificial Intelligence Technology and its Interdisciplinary Applications, Southeast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xu","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering and the Key Laboratory of New Generation Artificial Intelligence Technology and its Interdisciplinary Applications, Southeast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haiyang","family":"Xu","sequence":"additional","affiliation":[{"name":"Tongyi Lab, Alibaba Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7374-8739","authenticated-orcid":false,"given":"Hanwang","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Computing &amp; Data Science, Nanyang Technological University, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4959-8878","authenticated-orcid":false,"given":"Ming","family":"Yan","sequence":"additional","affiliation":[{"name":"Tongyi Lab, Alibaba Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3709-5053","authenticated-orcid":false,"given":"Fei","family":"Huang","sequence":"additional","affiliation":[{"name":"Tongyi Lab, Alibaba Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0140-7366","authenticated-orcid":false,"given":"Yu","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering and the Key Laboratory of New Generation Artificial Intelligence Technology and its Interdisciplinary Applications, Southeast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref2","first-page":"11137","article-title":"Image Captioning: Transforming objects into words","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Herdade","year":"2019"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00644"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013159"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00008"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3262578"},{"key":"ref8","first-page":"1","article-title":"On the connection between local attention and dynamic depth-wise convolution","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Qi","year":"2021"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00902"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00473"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"ref12","first-page":"1","article-title":"An image is worth 16 x 16 words: Transformers for image recognition at scale","volume-title":"Proc. 9th Int. Conf. Learn. Representations","author":"Dosovitskiy","year":"2021"},{"key":"ref13","article-title":"Cptr: Full transformer network for image captioning","author":"Liu","year":"2021"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16328"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.eval4nlp-1.4"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00553"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3384678"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3369863"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-60832-x"},{"key":"ref20","article-title":"CLIPcap: CLIP prefix for image captioning","author":"Mokady","year":"2021"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01745"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3265842"},{"key":"ref23","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","year":"2023"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00220"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01028"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3380259"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3326616"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d15-1166"},{"key":"ref30","article-title":"Longformer: The long-document transformer","author":"Beltagy","year":"2020"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.13"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00599"},{"key":"ref33","article-title":"Relational inductive biases, deep learning, and graph networks","author":"Battaglia","year":"2018"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d19-1098"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01098"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref40","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","year":"2005"},{"key":"ref41","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","author":"Lin","year":"2004","journal-title":"Text Summarization Branches Out"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548358"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2909864"},{"key":"ref46","first-page":"1","article-title":"FILIP: Fine-grained interactive language-image pre-training","volume-title":"Proc. 10th Int. Conf. Learn. Representations","author":"Yao","year":"2022"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00972"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2022.01.011"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20160"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7005"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01748"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01034"},{"issue":"198","key":"ref55","first-page":"1","article-title":"Codalab competitions: An open source platform to organize scientific challenges","volume":"24","author":"Pavao","year":"2023","journal-title":"J. Mach. Learn. Res."},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00637"},{"key":"ref57","first-page":"1564","article-title":"Bilinear attention networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kim","year":"2018"},{"key":"ref58","first-page":"13854","article-title":"Implicit differentiable outlier detection enable robust deep multimodal analysis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang","year":"2023"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/11342315\/11404240.pdf?arnumber=11404240","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T04:59:24Z","timestamp":1781585964000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11404240\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":58,"URL":"https:\/\/doi.org\/10.1109\/tmm.2026.3660118","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}