{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T23:58:36Z","timestamp":1780444716162,"version":"3.54.1"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,7,29]],"date-time":"2023-07-29T00:00:00Z","timestamp":1690588800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,7,29]],"date-time":"2023-07-29T00:00:00Z","timestamp":1690588800000},"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","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,7,29]]},"DOI":"10.1109\/icnc-fskd59587.2023.10281090","type":"proceedings-article","created":{"date-parts":[[2023,10,18]],"date-time":"2023-10-18T13:43:48Z","timestamp":1697636628000},"page":"1-7","source":"Crossref","is-referenced-by-count":6,"title":["Swin Transformer-based Image Captioning with Feature Enhancement and Multi-stage Fusion"],"prefix":"10.1109","author":[{"given":"Lei","family":"Liu","sequence":"first","affiliation":[{"name":"Beijing University of Technology,Faculty of Science,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yidi","family":"Jiao","sequence":"additional","affiliation":[{"name":"Beijing University of Technology,Faculty of Science,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoran","family":"Li","sequence":"additional","affiliation":[{"name":"Beijing University of Technology,Faculty of Science,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Li","sequence":"additional","affiliation":[{"name":"Beijing University of Technology,Faculty of Science,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haitao","family":"Wang","sequence":"additional","affiliation":[{"name":"China National Institute of Standardization,Fundamental Standardization,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinyu","family":"Cao","sequence":"additional","affiliation":[{"name":"China National Institute of Standardization,Fundamental Standardization,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref3","article-title":"Im2text: Describing images using 1 million captioned photographs","volume":"24","author":"Ordonez","year":"2011","journal-title":"Advances in neural information processing systems"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P14-2097"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.298"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.162"},{"key":"ref7","first-page":"444","article-title":"Corpus-guided sentence generation of natural images","volume-title":"Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing","author":"Yang"},{"key":"ref8","first-page":"747","article-title":"Midge: Generating image descriptions from computer vision detections","volume-title":"Proceedings of the 13th Conference of the European Chapter of the Association for Computational Linguistics","author":"Mitchell"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCSCE.2012.6487177"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref11","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv preprint arXiv:1409.1556"},{"key":"ref12","article-title":"A Deep Neural Framework for Image Caption Generation Using GRU-Based Attention Mechanism","author":"Khan","year":"2022","journal-title":"arXiv preprint arXiv:2203.01594"},{"key":"ref13","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","volume-title":"International conference on machine learning","author":"Xu"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3036860"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1089\/big.2021.0049"},{"issue":"11","key":"ref16","first-page":"139","article-title":"Generative adversarial nets","volume":"63","author":"Goodfellow","year":"2020","journal-title":"Generative adversarial networks, Communications of the ACM"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.445"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6998"},{"key":"ref19","first-page":"30","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2022.01.011"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.3390\/sym15010190"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref24","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","volume-title":"Proceedings of the ACL workshop on intrinsic and extrinsic evaluation measures for machine translation and\/or summarization","author":"Banerjee"},{"key":"ref25","first-page":"595","article-title":"Multimodal neural language models","volume-title":"International conference on machine learning, PMLR","author":"Kiros"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.667"},{"key":"ref27","article-title":"Deep captioning with multimodal recurrent neural networks (m-run)","author":"Mao","year":"2014","journal-title":"arXiv preprint arXiv:1412.6632"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-68780-9_32"}],"event":{"name":"2023 19th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD)","location":"Harbin, China","start":{"date-parts":[[2023,7,29]]},"end":{"date-parts":[[2023,7,31]]}},"container-title":["2023 19th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10280770\/10280781\/10281090.pdf?arnumber=10281090","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T17:28:17Z","timestamp":1757438897000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10281090\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,29]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icnc-fskd59587.2023.10281090","relation":{},"subject":[],"published":{"date-parts":[[2023,7,29]]}}}