{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T11:38:15Z","timestamp":1783510695128,"version":"3.55.0"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2022,11,1]],"date-time":"2022-11-01T00:00:00Z","timestamp":1667260800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,11,1]],"date-time":"2022-11-01T00:00:00Z","timestamp":1667260800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,11,1]],"date-time":"2022-11-01T00:00:00Z","timestamp":1667260800000},"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":["62076262"],"award-info":[{"award-number":["62076262"]}],"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":["61673402"],"award-info":[{"award-number":["61673402"]}],"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":["60802069"],"award-info":[{"award-number":["60802069"]}],"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":["61273270"],"award-info":[{"award-number":["61273270"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2022,11]]},"DOI":"10.1109\/tcsvt.2022.3181490","type":"journal-article","created":{"date-parts":[[2022,6,8]],"date-time":"2022-06-08T19:35:58Z","timestamp":1654716958000},"page":"7706-7718","source":"Crossref","is-referenced-by-count":61,"title":["Double-Stream Position Learning Transformer Network for Image Captioning"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7168-9357","authenticated-orcid":false,"given":"Weitao","family":"Jiang","sequence":"first","affiliation":[{"name":"School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4884-323X","authenticated-orcid":false,"given":"Haifeng","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vaswani"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref3","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sutskever"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045336"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00636"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00473"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2577031"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_42"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00902"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_31"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018957"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3036860"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00378"},{"key":"ref16","first-page":"11137","article-title":"Image captioning: Transforming objects into words","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Herdade"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.162"},{"key":"ref19","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":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v26i1.8205"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00188"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2017.667"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3067449"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.127"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413753"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00898"},{"key":"ref27","first-page":"8942","article-title":"Adaptively aligned image captioning via adaptive attention time","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Huang"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00486"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00856"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2017.131"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.128"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00443"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3390891"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00271"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.01094"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3107035"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00644"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00220"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01098"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2947482"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01521"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16258"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref44","article-title":"TransUNet: Transformers make strong encoders for medical image segmentation","author":"Chen","year":"2021","journal-title":"arXiv:2102.04306"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01398"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3161735"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01028"},{"key":"ref48","first-page":"1","article-title":"Universal transformers","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Dehghani"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p19-1285"},{"key":"ref50","article-title":"Position, padding and predictions: A deeper look at position information in CNNs","author":"Amirul Islam","year":"2021","journal-title":"arXiv:2101.12322"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.524"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2009.5206848"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref57","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":"ref58","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","volume-title":"Proc. Workshop Text Summarization Branches Out","author":"Lin"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/9931687\/09791335.pdf?arnumber=9791335","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T02:54:40Z","timestamp":1706756080000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9791335\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11]]},"references-count":60,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2022.3181490","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,11]]}}}