{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T13:24:47Z","timestamp":1784294687577,"version":"3.55.0"},"reference-count":105,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&D Program of China","award":["2022YFC2009903\/2022YFC2009900"],"award-info":[{"award-number":["2022YFC2009903\/2022YFC2009900"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62122018"],"award-info":[{"award-number":["62122018"]}],"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":["62020106008"],"award-info":[{"award-number":["62020106008"]}],"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":["61772116"],"award-info":[{"award-number":["61772116"]}],"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":["61872064"],"award-info":[{"award-number":["61872064"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004806","name":"Fok Ying Tong Education Foundation","doi-asserted-by":"publisher","award":["171106"],"award-info":[{"award-number":["171106"]}],"id":[{"id":"10.13039\/501100004806","id-type":"DOI","asserted-by":"publisher"}]},{"name":"SongShan Laboratory","award":["YYJC012022019"],"award-info":[{"award-number":["YYJC012022019"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tmm.2023.3295098","type":"journal-article","created":{"date-parts":[[2023,7,13]],"date-time":"2023-07-13T17:28:30Z","timestamp":1689269310000},"page":"2367-2379","source":"Crossref","is-referenced-by-count":53,"title":["Memory-Based Augmentation Network for Video Captioning"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6797-4238","authenticated-orcid":false,"given":"Shuaiqi","family":"Jing","sequence":"first","affiliation":[{"name":"Future Media Center and School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1015-7338","authenticated-orcid":false,"given":"Haonan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Future Media Center and School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0672-3790","authenticated-orcid":false,"given":"Pengpeng","family":"Zeng","sequence":"additional","affiliation":[{"name":"Future Media Center and School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2522-6394","authenticated-orcid":false,"given":"Lianli","family":"Gao","sequence":"additional","affiliation":[{"name":"Future Media Center and School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2549-8322","authenticated-orcid":false,"given":"Jingkuan","family":"Song","sequence":"additional","affiliation":[{"name":"Future Media Center and School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2999-2088","authenticated-orcid":false,"given":"Heng Tao","family":"Shen","sequence":"additional","affiliation":[{"name":"Future Media Center and School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16353"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018191"},{"key":"ref3","first-page":"6634","article-title":"Multi-modal dependency tree for video captioning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhao","year":"2021"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCICT50803.2021.9510102"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/2818048.2820013"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3469877.3495636"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00688"},{"key":"ref8","volume-title":"Human-Computer Interaction","author":"Dix","year":"2003"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.321"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.347"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475241"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475301"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00048"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045336"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.345"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.512"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2729019"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11239"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3323491"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00751"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01329"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6731"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00714"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3120867"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01742"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16421"},{"key":"ref29","first-page":"2397","article-title":"Dynamic memory networks for visual and textual question answering","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xiong","year":"2016"},{"key":"ref30","article-title":"Large-scale simple question answering with memory networks","author":"Bordes","year":"2015"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2023.3235523"},{"key":"ref32","first-page":"4331","article-title":"Using fast weights to attend to the recent past","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Ba","year":"2016"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995423"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3205212"},{"issue":"2","key":"ref35","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1023\/A:1020346032608","article-title":"Natural language description of human activities from video images based on concept hierarchy of actions","volume":"50","author":"Kojima","year":"2002","journal-title":"Int. J. Comput. Vis."},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.337"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.61"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v27i1.8679"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2924576"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01743"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/N15-1173"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/104"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01741"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123327"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00852"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2984062"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00795"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2021.108332"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018965"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00971"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01747"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3539225"},{"key":"ref53","article-title":"Wikicorpus: A word-sense disambiguated multilingual wikipedia corpus","volume-title":"Proc. 7th Int. Conf. Lang. Resour. Eval.","author":"Reese","year":"2010"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/219717.219748"},{"key":"ref55","article-title":"Neural turing machines","author":"Graves","year":"2014"},{"key":"ref56","first-page":"190","article-title":"Inferring algorithmic patterns with stack-augmented recurrent nets","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Joulin","year":"2015"},{"key":"ref57","first-page":"1828","article-title":"Learning to transduce with unbounded memory","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Grefenstette","year":"2015"},{"key":"ref58","article-title":"Memory networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Weston","year":"2015"},{"key":"ref59","first-page":"2440","article-title":"End-to-end memory networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Sukhbaatar","year":"2015"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1118"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00784"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16220"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.233"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15561-1_2"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v26i1.8205"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.162"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.306"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.neuro.26.041002.131047"},{"key":"ref69","article-title":"Deep captioning with multimodal recurrent neural networks (M-RNN)","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Mao","year":"2015"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref72","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vaswani","year":"2017"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_10"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/224"},{"key":"ref76","first-page":"190","article-title":"Collecting highly parallel data for paraphrase evaluation","volume-title":"Proc. Assoc. Comput. Linguistics","author":"Chen","year":"2011"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00468"},{"key":"ref79","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3348"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref85","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","volume-title":"Proc. Text Summarization Branches Out","author":"Lin","year":"2004"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref88","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01277"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01311"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00157"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01088"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00854"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_20"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_31"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_42"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01094"},{"key":"ref99","first-page":"11137","article-title":"Image captioning: Transforming objects into words","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Herdade","year":"2019"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00473"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/91"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01098"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01028"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.21105\/joss.00861"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10384483\/10183355.pdf?arnumber=10183355","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,6]],"date-time":"2024-02-06T20:30:33Z","timestamp":1707251433000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10183355\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":105,"URL":"https:\/\/doi.org\/10.1109\/tmm.2023.3295098","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}