{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T14:17:14Z","timestamp":1766067434156,"version":"3.37.3"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2020AAA0106300","2018AAA0102000"],"award-info":[{"award-number":["2020AAA0106300","2018AAA0102000"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62050110"],"award-info":[{"award-number":["62050110"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shenzhen Nanshan District Ling-Hang Team","award":["LHTD20170005"],"award-info":[{"award-number":["LHTD20170005"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2022,12,1]]},"DOI":"10.1109\/tpami.2021.3131618","type":"journal-article","created":{"date-parts":[[2021,11,30]],"date-time":"2021-11-30T23:46:41Z","timestamp":1638316001000},"page":"10209-10221","source":"Crossref","is-referenced-by-count":6,"title":["Syntax Customized Video Captioning by Imitating Exemplar Sentences"],"prefix":"10.1109","volume":"44","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8701-7689","authenticated-orcid":false,"given":"Yitian","family":"Yuan","sequence":"first","affiliation":[{"name":"Meituan, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7331-6132","authenticated-orcid":false,"given":"Lin","family":"Ma","sequence":"additional","affiliation":[{"name":"Meituan, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2236-9290","authenticated-orcid":false,"given":"Wenwu","family":"Zhu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P14-5010"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P14-5010"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P14-1022"},{"key":"ref37","article-title":"HuggingFace's transformers: State-of-the-art natural language processing","volume":"abs 1910 3771","author":"wolf","year":"2019"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1137\/0218082"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00425"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.512"},{"key":"ref40","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc Int Conf Learning Representations"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.323"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.337"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-11752-2_15"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9512"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1103"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11330"},{"article-title":"Deep learning for text style transfer: A survey","year":"2020","author":"jin","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3390\/app10186196"},{"article-title":"Diverse video captioning through latent variable expansion with conditional GAN","year":"2019","author":"xiao","key":"ref28"},{"key":"ref4","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00273"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.515"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.339"},{"article-title":"Image captioning at will: A versatile scheme for effectively injecting sentiments into image descriptions","year":"2018","author":"you","key":"ref29"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/N15-1173"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00795"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.497"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.61"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123448"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/877"},{"key":"ref20","first-page":"189","article-title":"Fighting offensive language on social media with unsupervised text style transfer","author":"melnyk","year":"2018","journal-title":"Proc 32nd Ann Meeting Assoc for Computational Linguistics"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00998"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.263"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298754"},{"key":"ref24","first-page":"3059","article-title":"Weakly supervised dense event captioning in videos","author":"duan","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref41","first-page":"8024","article-title":"PyTorch: An imperative style, high-performance deep learning library","author":"paszke","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01095"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00896"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00432"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.108"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/9940445\/09629327.pdf?arnumber=9629327","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,5]],"date-time":"2022-12-05T22:37:41Z","timestamp":1670279861000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9629327\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,1]]},"references-count":43,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2021.3131618","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"type":"print","value":"0162-8828"},{"type":"electronic","value":"2160-9292"},{"type":"electronic","value":"1939-3539"}],"subject":[],"published":{"date-parts":[[2022,12,1]]}}}