{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T16:08:51Z","timestamp":1780589331820,"version":"3.54.1"},"reference-count":61,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Shanghai Science and Technology Program\u2014Distributed and generative few-shot algorithm and theory research","award":["20511100600"],"award-info":[{"award-number":["20511100600"]}]},{"DOI":"10.13039\/100007219","name":"Natural Science Foundation of Shanghai\u2014Research on image sentiment analysis and expression based on human vision and cognitive psychology","doi-asserted-by":"publisher","award":["22ZR1418400"],"award-info":[{"award-number":["22ZR1418400"]}],"id":[{"id":"10.13039\/100007219","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2024,2]]},"DOI":"10.1109\/tnnls.2022.3185320","type":"journal-article","created":{"date-parts":[[2022,6,29]],"date-time":"2022-06-29T19:36:21Z","timestamp":1656531381000},"page":"1785-1796","source":"Crossref","is-referenced-by-count":47,"title":["Adaptive Semantic-Enhanced Transformer for Image Captioning"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6270-7771","authenticated-orcid":false,"given":"Jing","family":"Zhang","sequence":"first","affiliation":[{"name":"Department of Computer Science and Technology, East China University of Science and Technology, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2978-1384","authenticated-orcid":false,"given":"Zhongjun","family":"Fang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, East China University of Science and Technology, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Han","family":"Sun","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, East China University of Science and Technology, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3759-2041","authenticated-orcid":false,"given":"Zhe","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, East China University of Science and Technology, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/d14-1179"},{"key":"ref2","article-title":"Neural machine translation by jointly learning to align and translate","author":"Bahdanau","year":"2014","journal-title":"arXiv:1409.0473"},{"key":"ref3","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. NIPS","author":"Vaswani"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.162"},{"key":"ref5","first-page":"747","article-title":"Midge: Generating image descriptions from computer vision detections","volume-title":"Proc. 13th Conf. Eur. Chapter Assoc. Comput. Linguistics","author":"Mitchell"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00754"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.667"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2929141"},{"key":"ref10","article-title":"Aligning where to see and what to tell: Image caption with region-based attention and scene factorization","author":"Jin","year":"2015","journal-title":"arXiv:1506.06272"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.138"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.140"},{"key":"ref13","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Krizhevsky"},{"key":"ref14","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12266"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2941820"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.12.073"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045336"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.345"},{"key":"ref23","article-title":"Adaptively aligned image captioning via adaptive attention time","author":"Huang","year":"2019","journal-title":"arXiv:1909.09060"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2019.102178"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2997034"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.29"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.127"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2888822"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461507"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.524"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/110"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_42"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01094"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350943"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00271"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2947482"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01034"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00473"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01098"},{"key":"ref45","first-page":"1","article-title":"Image captioning: Transforming objects into words","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Herdade"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-69538-5_10"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298754"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00902"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16258"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref54","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":"ref55","article-title":"ROUGE: A package for automatic evaluation of summaries","volume-title":"Proc. Workshop Text Summarization ACL","author":"Lin"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00553"},{"key":"ref60","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. ICLR","author":"Kingma"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10422842\/09810877.pdf?arnumber=9810877","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,16]],"date-time":"2024-02-16T19:09:23Z","timestamp":1708110563000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9810877\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2]]},"references-count":61,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2022.3185320","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2]]}}}