{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,8]],"date-time":"2026-02-08T07:43:14Z","timestamp":1770536594790,"version":"3.49.0"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Plan","award":["2018AAA0102000"],"award-info":[{"award-number":["2018AAA0102000"]}]},{"name":"National Key Research and Development Plan","award":["2019QY1801"],"award-info":[{"award-number":["2019QY1801"]}]},{"name":"National Key Research and Development Plan","award":["2019QY1802"],"award-info":[{"award-number":["2019QY1802"]}]},{"name":"National Key Research and Development Plan","award":["2019QY1800"],"award-info":[{"award-number":["2019QY1800"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61972186"],"award-info":[{"award-number":["61972186"]}],"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":["61732005"],"award-info":[{"award-number":["61732005"]}],"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":["U21B2027"],"award-info":[{"award-number":["U21B2027"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Yunnan High-Tech Industry Development Project","award":["201606"],"award-info":[{"award-number":["201606"]}]},{"DOI":"10.13039\/501100018531","name":"Yunnan Provincial Major Science and Technology Special Plan Projects","doi-asserted-by":"publisher","award":["202103AA080015"],"award-info":[{"award-number":["202103AA080015"]}],"id":[{"id":"10.13039\/501100018531","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018531","name":"Yunnan Provincial Major Science and Technology Special Plan Projects","doi-asserted-by":"publisher","award":["202002AD080001-5"],"award-info":[{"award-number":["202002AD080001-5"]}],"id":[{"id":"10.13039\/501100018531","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Yunnan Basic Research Project","award":["202001AS070014"],"award-info":[{"award-number":["202001AS070014"]}]},{"name":"Reserve Talents for Academic and Technological Leaders in Yunnan Province","award":["202105AC160018"],"award-info":[{"award-number":["202105AC160018"]}]},{"DOI":"10.13039\/501100002367","name":"CAAI-Huawei MindSpore Open Fund, Youth Innovation Promotion Association of Chinese Academy of Sciences","doi-asserted-by":"publisher","award":["2020108"],"award-info":[{"award-number":["2020108"]}],"id":[{"id":"10.13039\/501100002367","id-type":"DOI","asserted-by":"publisher"}]},{"name":"CCF-Baidu Open Fund","award":["2021PP15002000"],"award-info":[{"award-number":["2021PP15002000"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/tip.2022.3159472","type":"journal-article","created":{"date-parts":[[2022,3,21]],"date-time":"2022-03-21T20:27:08Z","timestamp":1647894428000},"page":"3565-3577","source":"Crossref","is-referenced-by-count":23,"title":["I<sup>2<\/sup>Transformer: Intra- and Inter-Relation Embedding Transformer for TV Show Captioning"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9525-9060","authenticated-orcid":false,"given":"Yunbin","family":"Tu","sequence":"first","affiliation":[{"name":"Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8437-4824","authenticated-orcid":false,"given":"Liang","family":"Li","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4038-753X","authenticated-orcid":false,"given":"Li","family":"Su","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China"}]},{"given":"Shengxiang","family":"Gao","sequence":"additional","affiliation":[{"name":"Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1204-0512","authenticated-orcid":false,"given":"Chenggang","family":"Yan","sequence":"additional","affiliation":[{"name":"School of Automation, Hangzhou Dianzi University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2510-8993","authenticated-orcid":false,"given":"Zheng-Jun","family":"Zha","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4012-461X","authenticated-orcid":false,"given":"Zhengtao","family":"Yu","sequence":"additional","affiliation":[{"name":"Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7542-296X","authenticated-orcid":false,"given":"Qingming","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.642"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01088"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2125"},{"key":"ref32","first-page":"6894","article-title":"Integrating both visual and audio cues for enhanced video caption","author":"hao","year":"2018","journal-title":"Proc AAAI"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.450"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_20"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01329"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_42"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.107075"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00900"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6881"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.233"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_22"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3042086"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3028651"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01311"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2976552"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2924576"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107702"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00308"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3067449"},{"key":"ref50","article-title":"The kinetics human action video dataset","author":"kay","year":"2017","journal-title":"arXiv 1705 06950"},{"key":"ref51","article-title":"RoBERTa: A robustly optimized BERT pretraining approach","author":"liu","year":"2019","journal-title":"arXiv 1907 11692"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.273"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref53","first-page":"8024","article-title":"PyTorch: An imperative style, high-performance deep learning library","author":"paszke","year":"2019","journal-title":"Proc NeurIPS"},{"key":"ref52","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv 1412 6980"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.400"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.662"},{"key":"ref40","article-title":"Layer normalization","author":"ba","year":"2016","journal-title":"arXiv 1607 06450"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00273"},{"key":"ref13","first-page":"1","article-title":"Semi-supervised classification with graph convolutional networks","author":"kipf","year":"2017","journal-title":"Proc ICLR"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107424"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2836969"},{"key":"ref16","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2014","journal-title":"arXiv 1409 0473"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.61"},{"key":"ref18","first-page":"2346","article-title":"Jointly modeling deep video and compositional text to bridge vision and language in a unified framework","author":"xu","year":"2015","journal-title":"Proc AAAI"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123354"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2855422"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3051476"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2988435"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2916757"},{"key":"ref8","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_27"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.161"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref45","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","author":"lin","year":"0","journal-title":"Text Summarization Branches Out"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref47","article-title":"Microsoft COCO captions: Data collection and evaluation server","author":"chen","year":"2015","journal-title":"arXiv 1504 00325"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00468"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref44","first-page":"65","article-title":"Meteor: An automatic metric for MT evaluation with improved correlation with human judgments","author":"banerjee","year":"2005","journal-title":"Proc ACL"},{"key":"ref43","first-page":"311","article-title":"BLEU: A method for automatic evaluation of machine translation","author":"papineni","year":"2002","journal-title":"Proc ACL"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/9626658\/09738841.pdf?arnumber=9738841","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,20]],"date-time":"2022-06-20T20:35:58Z","timestamp":1655757358000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9738841\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/tip.2022.3159472","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}