{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:19:44Z","timestamp":1777655984448,"version":"3.51.4"},"reference-count":36,"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":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["T2293720\/T2293723"],"award-info":[{"award-number":["T2293720\/T2293723"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["226-2023-00126"],"award-info":[{"award-number":["226-2023-00126"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["226-2022-00051"],"award-info":[{"award-number":["226-2022-00051"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["226-2023-00048"],"award-info":[{"award-number":["226-2023-00048"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tmm.2023.3296944","type":"journal-article","created":{"date-parts":[[2023,7,26]],"date-time":"2023-07-26T18:40:10Z","timestamp":1690396810000},"page":"2456-2466","source":"Crossref","is-referenced-by-count":9,"title":["Show Me a Video: A Large-Scale Narrated Video Dataset for Coherent Story Illustration"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4888-4314","authenticated-orcid":false,"given":"Yu","family":"Lu","sequence":"first","affiliation":[{"name":"CCAI, College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6062-3459","authenticated-orcid":false,"given":"Feiyue","family":"Ni","sequence":"additional","affiliation":[{"name":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3934-0224","authenticated-orcid":false,"given":"Haofan","family":"Wang","sequence":"additional","affiliation":[{"name":"KuaiShou Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-8268-9736","authenticated-orcid":false,"given":"Xiaofeng","family":"Guo","sequence":"additional","affiliation":[{"name":"KuaiShou Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4093-7557","authenticated-orcid":false,"given":"Linchao","family":"Zhu","sequence":"additional","affiliation":[{"name":"CCAI, College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8783-8313","authenticated-orcid":false,"given":"Zongxin","family":"Yang","sequence":"additional","affiliation":[{"name":"CCAI, College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2163-7401","authenticated-orcid":false,"given":"Ruihua","family":"Song","sequence":"additional","affiliation":[{"name":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4267-6063","authenticated-orcid":false,"given":"Lele","family":"Cheng","sequence":"additional","affiliation":[{"name":"KuaiShou Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0512-880X","authenticated-orcid":false,"given":"Yi","family":"Yang","sequence":"additional","affiliation":[{"name":"CCAI, College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-69541-5_28"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref3","first-page":"1815","article-title":"Enhancing sentence embedding with generalized pooling","volume-title":"Proc. 27th Int. Conf. Comput. Linguistics","author":"Chen","year":"2018"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350571"},{"key":"ref5","article-title":"Improving video-text retrieval by multi-stream corpus alignment and dual softmax loss","author":"Cheng","year":"2021","journal-title":"CoRR"},{"key":"ref6","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. NAACL-HL","author":"Devlin","year":"2019"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00912"},{"key":"ref8","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy","year":"2021"},{"key":"ref9","article-title":"PP-OCR: A practical ultra lightweight OCR system","author":"Du","year":"2020","journal-title":"CoRR"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1117"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1147"},{"key":"ref14","article-title":"ADAM: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_20"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548034"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2930041"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00649"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-11018-5_19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.07.028"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00990"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00272"},{"key":"ref23","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00794"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0987-1"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_2"},{"key":"ref27","first-page":"6000","article-title":"Attention is all you need","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Vaswani","year":"2017"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00895"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2022.3204444"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3037461"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548268"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2807588"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1631\/fitee.2100463"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3014488"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3057503"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10384483\/10195243.pdf?arnumber=10195243","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,6]],"date-time":"2024-02-06T20:40:48Z","timestamp":1707252048000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10195243\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/tmm.2023.3296944","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}