{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,28]],"date-time":"2026-10-28T16:48:26Z","timestamp":1793206106683,"version":"4.5.0"},"reference-count":82,"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":"Key-Area Research and Development Program of Guangdong Province","award":["2019B010155002"],"award-info":[{"award-number":["2019B010155002"]}]},{"name":"Major Key Project of PCL","award":["PCL2021A07"],"award-info":[{"award-number":["PCL2021A07"]}]},{"name":"Multi-source Cross-platform Video Analysis and Understanding for Intelligent Perception in Smart City","award":["U20B2052"],"award-info":[{"award-number":["U20B2052"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62102205"],"award-info":[{"award-number":["62102205"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012236","name":"Beijing Institute of Technology Research Fund Program for Young Scholars","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012236","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.2023.3265842","type":"journal-article","created":{"date-parts":[[2023,4,10]],"date-time":"2023-04-10T15:21:44Z","timestamp":1681140104000},"page":"379-393","source":"Crossref","is-referenced-by-count":43,"title":["Prompt-Based Learning for Unpaired Image Captioning"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7678-0005","authenticated-orcid":false,"given":"Peipei","family":"Zhu","sequence":"first","affiliation":[{"name":"School of Science and Engineering, Chinese University of Hong Kong, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6117-6745","authenticated-orcid":false,"given":"Xiao","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Anhui University, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6487-0441","authenticated-orcid":false,"given":"Lin","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Computer Science, Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8135-1659","authenticated-orcid":false,"given":"Zhenglong","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Science and Engineering, Chinese University of Hong Kong, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8327-0003","authenticated-orcid":false,"given":"Wei-Shi","family":"Zheng","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-Sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2197-9038","authenticated-orcid":false,"given":"Yaowei","family":"Wang","sequence":"additional","affiliation":[{"name":"Peng Cheng Laboratory, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6720-234X","authenticated-orcid":false,"given":"Changwen","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Computing, The Hong Kong Polytechnic University, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3011317"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2976552"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2990074"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2587640"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3142759"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3460418.3480405"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.121"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00169"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/2998181.2998364"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00380"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_25"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_35"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_3"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3122865"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3060948"},{"key":"ref17","first-page":"16736","article-title":"RATT: Recurrent attention to transient tasks for continual image captioning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chiaro","year":"2020"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2869276"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2888822"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2896516"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.64"},{"key":"ref22","article-title":"Adversarial feature learning","author":"Donahue","year":"2016"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00425"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00751"},{"key":"ref25","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":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00381"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00836"},{"key":"ref28","first-page":"13988","article-title":"CLIP-IT! Language-guided video summarization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Narasimhan","year":"2021"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3560815"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.576"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2931815"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2941820"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045336"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00473"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01098"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01746"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00271"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_42"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.524"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref46","first-page":"898","article-title":"Contrastive learning for image captioning","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Dai","year":"2017"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3295748"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2951226"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.559"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.8"},{"key":"ref51","article-title":"A semi-supervised framework for image captioning","author":"Chen","year":"2016"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1208"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/128"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01042"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2019.00054"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.08.019"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2022.3214090"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00024"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.158"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.191"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-demo.10"},{"key":"ref62","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Brown","year":"2020"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.20"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2024.01.004"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.197"},{"key":"ref67","article-title":"How much can CLIP benefit vision-and-language tasks?","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Shen","year":"2021"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00512"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref70","article-title":"An image is worth 1616 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref71","first-page":"4055","article-title":"Image transformer","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Parmar","year":"2018"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.345"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref76","first-page":"3128","article-title":"Deep visual-semantic alignments for generating image descriptions","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Andrej","year":"2015"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3348"},{"key":"ref79","first-page":"1","article-title":"Looking for a good metrics: Rouge and its evaluation","volume-title":"Proc. 4th NTCIR Workshops","author":"LIN","year":"2004"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10384483\/10097833.pdf?arnumber=10097833","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T02:30:55Z","timestamp":1725676255000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10097833\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":82,"URL":"https:\/\/doi.org\/10.1109\/tmm.2023.3265842","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}