{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T23:31:04Z","timestamp":1792798264336,"version":"4.5.0"},"reference-count":64,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2022,7,1]],"date-time":"2022-07-01T00:00:00Z","timestamp":1656633600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,7,1]],"date-time":"2022-07-01T00:00:00Z","timestamp":1656633600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,7,1]],"date-time":"2022-07-01T00:00:00Z","timestamp":1656633600000},"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":["61772359"],"award-info":[{"award-number":["61772359"]}],"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":["62002257"],"award-info":[{"award-number":["62002257"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Tianjin New Generation Artificial Intelligence Major Program","award":["19ZXZNGX00110"],"award-info":[{"award-number":["19ZXZNGX00110"]}]},{"DOI":"10.13039\/501100002858","name":"China Post-Doctoral Science Foundation","doi-asserted-by":"publisher","award":["2021M692395"],"award-info":[{"award-number":["2021M692395"]}],"id":[{"id":"10.13039\/501100002858","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":[[2022,7]]},"DOI":"10.1109\/tcsvt.2021.3121062","type":"journal-article","created":{"date-parts":[[2021,10,19]],"date-time":"2021-10-19T23:00:18Z","timestamp":1634684418000},"page":"4417-4430","source":"Crossref","is-referenced-by-count":91,"title":["High-Order Interaction Learning for Image Captioning"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3027-2114","authenticated-orcid":false,"given":"Yanhui","family":"Wang","sequence":"first","affiliation":[{"name":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7526-4356","authenticated-orcid":false,"given":"Ning","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5755-9145","authenticated-orcid":false,"given":"An-An","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9609-6120","authenticated-orcid":false,"given":"Wenhui","family":"Li","sequence":"additional","affiliation":[{"name":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1151-1792","authenticated-orcid":false,"given":"Yongdong","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Heifei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01098"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.667"},{"key":"ref32","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","volume":"2015","author":"xu","year":"2015","journal-title":"Comput Sci"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.29"},{"key":"ref30","first-page":"1","article-title":"Deep captioning with multimodal recurrent neural networks (m-RNN)","author":"mao","year":"2015","journal-title":"Proc ICLR"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00473"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.345"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2921655"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref62","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc ICLR"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref63","first-page":"1","article-title":"Automatic differentiation in pytorch","author":"paszke","year":"2017","journal-title":"Proc NIPS"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.162"},{"key":"ref64","doi-asserted-by":"crossref","first-page":"5514","DOI":"10.1109\/TIP.2018.2855406","article-title":"Attentive linear transformation for image captioning","volume":"27","author":"gu","year":"2018","journal-title":"IEEE Trans Image Process"},{"key":"ref27","first-page":"359","article-title":"Collective generation of natural image descriptions","author":"kuznetsova","year":"2012","journal-title":"Proc ACL"},{"key":"ref29","first-page":"1","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2015","journal-title":"Proc ICLR"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00754"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2598339"},{"key":"ref20","first-page":"1","article-title":"The neuro-symbolic concept learner: Interpreting scenes, words, and sentences from natural supervision","author":"mao","year":"2019","journal-title":"Proc ICLR"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2867286"},{"key":"ref21","first-page":"1","article-title":"CLEVRER: Collision events for video representation and reasoning","author":"yi","year":"2020","journal-title":"Proc ICLR"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.683"},{"key":"ref26","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"lin","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref25","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.524"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref57","first-page":"1","article-title":"Rouge: A package for automatic evaluation of summaries","author":"flick","year":"2018","journal-title":"Proc ACL Workshop"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.3115\/1626355.1626389"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2896516"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/110"},{"key":"ref10","first-page":"676","article-title":"Dialog-based interactive image retrieval","author":"guo","year":"2018","journal-title":"Neural Information Processing Systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/2998181.2998364"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.121"},{"key":"ref13","first-page":"261","article-title":"Leveraging visual question answering for image-caption ranking","volume":"9906","author":"lin","year":"2016","journal-title":"Computer Vision"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1348"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1164"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01094"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_42"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00902"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.108"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.364"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2947482"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2638622"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3036860"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.560"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2019.00054"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350943"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.664"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00611"},{"key":"ref41","first-page":"852","article-title":"Visual relationship detection with language priors","volume":"9905","author":"lu","year":"2016","journal-title":"Computer Vision"},{"key":"ref44","first-page":"747","article-title":"Midge: Generating image descriptions from computer vision detections","author":"mitchell","year":"2012","journal-title":"Proc EACL"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2953692"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/9812753\/09579002.pdf?arnumber=9579002","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,25]],"date-time":"2022-07-25T19:58:23Z","timestamp":1658779103000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9579002\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7]]},"references-count":64,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2021.3121062","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,7]]}}}