{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T15:10:11Z","timestamp":1777129811182,"version":"3.51.4"},"reference-count":23,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T00:00:00Z","timestamp":1764201600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T00:00:00Z","timestamp":1767052800000},"content-version":"vor","delay-in-days":33,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"name":"Research on image visual perception description generation technology integrating attention mechanism, The Scientific Research Project of Jilin Provincial Department of Education","award":["No. JJKH20230841KJ"],"award-info":[{"award-number":["No. JJKH20230841KJ"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Complex Intell. Syst."],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1007\/s40747-025-02183-2","type":"journal-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T15:07:16Z","timestamp":1764256036000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Enhancing image captioning with spatial relational attention and grid decoder"],"prefix":"10.1007","volume":"12","author":[{"given":"Xin","family":"Deng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yihuan","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Honghua","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,11,27]]},"reference":[{"key":"2183_CR1","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1109\/TPAMI.2022.3152247","volume":"45","author":"K Han","year":"2022","unstructured":"Han K, Wang Y, Chen H, Chen X, Guo J, Liu Z, Tang Y, Xiao A, Xu C, Xu Y (2022) A survey on vision transformer. IEEE Trans Pattern Anal Mach Intell 45:87\u2013110","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2183_CR2","unstructured":"Ke G, He D, Liu T-Y (2020) Rethinking positional encoding in language pre-training. arXiv preprint arXiv:2006.15595"},{"key":"2183_CR3","doi-asserted-by":"crossref","unstructured":"Wu K, Peng H, Chen M, Fu J, Chao H (2021) Rethinking and improving relative position encoding for vision transformer. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 10033\u201310041","DOI":"10.1109\/ICCV48922.2021.00988"},{"key":"2183_CR4","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser \u0141, Polosukhin I (2017) Attention is all you need. In: Advances in neural information processing systems, 30"},{"key":"2183_CR5","doi-asserted-by":"crossref","unstructured":"Cornia M, Stefanini M, Baraldi L, Cucchiara R (2020) Meshed-memory transformer for image captioning. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 10578\u201310587","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"2183_CR6","doi-asserted-by":"crossref","unstructured":"Pan Y, Yao T, Li Y, Mei T (2020) X-linear attention networks for image captioning. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 10971\u201310980","DOI":"10.1109\/CVPR42600.2020.01098"},{"key":"2183_CR7","doi-asserted-by":"crossref","unstructured":"Ji J, Luo Y, Sun X, Chen F, Luo G, Wu Y, Gao Y, Ji R (2021) Improving image captioning by leveraging intra-and inter-layer global representation in transformer network. In: Proceedings of the AAAI conference on artificial intelligence, pp 1655\u20131663","DOI":"10.1609\/aaai.v35i2.16258"},{"key":"2183_CR8","doi-asserted-by":"crossref","unstructured":"Huang L, Wang W, Chen J, Wei X-Y (2019) Attention on attention for image captioning. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 4634\u20134643","DOI":"10.1109\/ICCV.2019.00473"},{"key":"2183_CR9","doi-asserted-by":"crossref","unstructured":"Tran A, Mathews A, Xie L (2020) Transform and tell: Entity-aware news image captioning. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 13035\u201313045","DOI":"10.1109\/CVPR42600.2020.01305"},{"key":"2183_CR10","doi-asserted-by":"crossref","unstructured":"Lin T-Y, Maire M, Belongie S, Hays J, Perona P, Ramanan D, Doll\u00e1r P, Zitnick CL (2014) Microsoft coco: common objects in context. In: Proceedings of the computer vision\u2014ECCV 2014: 13th European conference, Zurich, Switzerland, September 6\u201312, 2014, Proceedings, part v 13, pp 740\u2013755","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"2183_CR11","doi-asserted-by":"crossref","unstructured":"Papineni K, Roukos S, Ward T, Zhu W-J (2002) Bleu: a method for automatic evaluation of machine translation. In: Proceedings of the 40th annual meeting of the Association for Computational Linguistics, pp 311\u2013318","DOI":"10.3115\/1073083.1073135"},{"key":"2183_CR12","doi-asserted-by":"crossref","unstructured":"Vedantam R, Lawrence Zitnick C, Parikh D (2015) Cider: consensus-based image description evaluation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4566\u20134575","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"2183_CR13","unstructured":"Banerjee S, Lavie A (2005) METEOR: an automatic metric for MT evaluation with improved correlation with human judgments [C. In: Proceedings of the acl workshop on intrinsic and extrinsic evaluation measures for machine translation and\/or summarization, pp 65\u201372"},{"key":"2183_CR14","unstructured":"Lin C-Y (2004) Rouge: a package for automatic evaluation of summaries. In: Proceedings of the text summarization branches out, pp 74\u201381"},{"key":"2183_CR15","doi-asserted-by":"crossref","unstructured":"Vedantam R, Lawrence Zitnick C, Parikh D (2015) Cider: consensus-based image description evaluation [C]. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4566\u20134575","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"2183_CR16","doi-asserted-by":"crossref","unstructured":"Anderson P, Fernando B, Johnson M, Gould S (2016) Spice: semantic propositional image caption evaluation. In: Proceedings of the computer vision\u2014ECCV 2016: 14th European conference, Amsterdam, The Netherlands, October 11\u201314, 2016, Proceedings, Part V 14, pp 382\u2013398","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"2183_CR17","doi-asserted-by":"crossref","unstructured":"Rennie SJ, Marcheret E, Mroueh Y, Ross J, Goel V (2017) Self-critical sequence training for image captioning. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7008\u20137024","DOI":"10.1109\/CVPR.2017.131"},{"key":"2183_CR18","doi-asserted-by":"crossref","unstructured":"Anderson P, He X, Buehler C, Teney D, Johnson M, Gould S, Zhang L (2018) Bottom-up and top-down attention for image captioning and visual question answering. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 6077\u20136086","DOI":"10.1109\/CVPR.2018.00636"},{"key":"2183_CR19","doi-asserted-by":"crossref","unstructured":"Yao T, Pan Y, Li Y, Mei T (2018) Exploring visual relationship for image captioning. In: Proceedings of the European conference on computer vision (ECCV), pp 684\u2013699","DOI":"10.1007\/978-3-030-01264-9_42"},{"key":"2183_CR20","doi-asserted-by":"crossref","unstructured":"Yang X, Tang K, Zhang H, Cai J (2019) Auto-encoding scene graphs for image captioning. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 10685\u201310694","DOI":"10.1109\/CVPR.2019.01094"},{"key":"2183_CR21","unstructured":"Herdade S, Kappeler A, Boakye K, Soares J (2019) Image captioning: transforming objects into words. In: Advances in neural information processing systems, 32"},{"key":"2183_CR22","doi-asserted-by":"crossref","unstructured":"Huang G, An J, Yang Z et al (2024) Stacked intelligent metasurfaces for task-oriented semantic communications [J]. IEEE Wirel Commun Lett","DOI":"10.1109\/LWC.2024.3499970"},{"key":"2183_CR23","unstructured":"Liu H, An J, Jia X et al (2024) Stacked intelligent metasurfaces for wireless sensing and communication: applications and challenges [J]. arXiv e-prints arXiv: 2407.03566"}],"container-title":["Complex & Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40747-025-02183-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s40747-025-02183-2","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40747-025-02183-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T11:48:31Z","timestamp":1769773711000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s40747-025-02183-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,27]]},"references-count":23,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1]]}},"alternative-id":["2183"],"URL":"https:\/\/doi.org\/10.1007\/s40747-025-02183-2","relation":{},"ISSN":["2199-4536","2198-6053"],"issn-type":[{"value":"2199-4536","type":"print"},{"value":"2198-6053","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,27]]},"assertion":[{"value":"21 April 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 October 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 November 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no conflicts of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"All authors have approved the manuscript and agree with its submission to (Complex and Intelligent Systems).","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent"}}],"article-number":"56"}}