{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T18:35:50Z","timestamp":1780511750047,"version":"3.54.1"},"reference-count":86,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Key Program of National Natural Science Foundation of China","award":["U20B2069"],"award-info":[{"award-number":["U20B2069"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tmm.2022.3177308","type":"journal-article","created":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T20:35:52Z","timestamp":1653338152000},"page":"4494-4507","source":"Crossref","is-referenced-by-count":9,"title":["Bidirectional Maximum Entropy Training With Word Co-Occurrence for Video Captioning"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9608-0524","authenticated-orcid":false,"given":"Sheng","family":"Liu","sequence":"first","affiliation":[{"name":"State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Annan","family":"Li","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8001-2703","authenticated-orcid":false,"given":"Jiahao","family":"Wang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6657-6403","authenticated-orcid":false,"given":"Yunhong","family":"Wang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2975798"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3404374"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3468872"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413499"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.neuro.26.041002.131047"},{"key":"ref6","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vaswani","year":"2017"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3067449"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/N15-1173"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.2.270"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01329"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00971"},{"key":"ref13","article-title":"Sequence level training with recurrent neural networks","volume-title":"Proc. 4th Int. Conf. Learn. Representations","author":"Ranzato","year":"2016"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12263"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00443"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00646"},{"key":"ref18","first-page":"1043","article-title":"Reinforcement learning with hierarchies of machines","volume-title":"Adv. Neural Inf. Process. Syst.","volume":"10","author":"Parr","year":"1998"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jctc.0c00971.s001"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729694"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01657"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00184"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/92"},{"key":"ref24","article-title":"Dvcflow: Modeling information flow towards human-like video captioning","author":"Yan","year":"2021"},{"key":"ref25","first-page":"190","article-title":"Collecting highly parallel data for paraphrase evaluation","volume-title":"Proc. 49th Annu. Meeting Assoc. Comput. Linguistics: Hum. Lang. Technol.","author":"Chen","year":"2011"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2477044"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2888822"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2990074"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3011317"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2976552"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3060948"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2896515"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01098"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16361"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16421"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2729019"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2924576"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093291"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01088"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2988435"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01109"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3003592"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3063423"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2940007"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16301"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413880"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.100"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00042"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3002669"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1162\/089120103321337458"},{"key":"ref54","first-page":"1171","article-title":"Scheduled sampling for sequence prediction with recurrent neural networks","volume-title":"Adv. Neural Inf. Process. Syst.","volume":"28","author":"Bengio","year":"2015"},{"key":"ref55","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja","year":"2018"},{"key":"ref56","article-title":"Soft actor-critic algorithms and applications","author":"Haarnoja","year":"2018"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_43"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2013.2291319"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2013.6738663"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00025"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.117"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.496"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/381"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/307"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_22"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00784"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018191"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.339"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00854"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00852"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00795"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16353"},{"issue":"1","key":"ref73","first-page":"39","article-title":"A maximum entropy approach to natural language processing","volume":"22","author":"Berger","year":"1996","journal-title":"Comput. Linguistics"},{"key":"ref74","volume-title":"The Maximum Entropy Method","volume":"32","author":"Wu","year":"2012"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/PROC.1982.12425"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref77","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","year":"2005"},{"key":"ref78","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":"ref79","article-title":"Microsoft COCO captions: Data collection and evaluation server","author":"Chen","year":"2015"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n16-1014"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00685"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"issue":"1","key":"ref86","first-page":"105","article-title":"Paddlepaddle: An open-source deep learning platform from industrial practice","volume":"1","author":"Ma","year":"2019","journal-title":"Front. Data Domputing"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10016790\/09780231.pdf?arnumber=9780231","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,22]],"date-time":"2024-01-22T22:49:26Z","timestamp":1705963766000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9780231\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":86,"URL":"https:\/\/doi.org\/10.1109\/tmm.2022.3177308","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}