{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T08:57:55Z","timestamp":1778144275730,"version":"3.51.4"},"reference-count":54,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2020YFB1406702-3"],"award-info":[{"award-number":["2020YFB1406702-3"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61772575"],"award-info":[{"award-number":["61772575"]}],"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":["62006257"],"award-info":[{"award-number":["62006257"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100009592","name":"Beijing Municipal Science & Technology Commission","doi-asserted-by":"publisher","award":["Z231100001723002"],"award-info":[{"award-number":["Z231100001723002"]}],"id":[{"id":"10.13039\/501100009592","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Comput. Soc. Syst."],"published-print":{"date-parts":[[2025,8]]},"DOI":"10.1109\/tcss.2024.3402270","type":"journal-article","created":{"date-parts":[[2024,6,27]],"date-time":"2024-06-27T14:48:34Z","timestamp":1719499714000},"page":"1869-1879","source":"Crossref","is-referenced-by-count":6,"title":["Zero-Shot Cross-Lingual Knowledge Transfer in VQA via Multimodal Distillation"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0787-550X","authenticated-orcid":false,"given":"Yu","family":"Weng","sequence":"first","affiliation":[{"name":"Department of Key Laboratory of Ethnic Language Intelligent Analysis and Security Governance, Ministry of Education, Minzu University of China, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-0629-3805","authenticated-orcid":false,"given":"Jun","family":"Dong","sequence":"additional","affiliation":[{"name":"Department of Key Laboratory of Ethnic Language Intelligent Analysis and Security Governance, Ministry of Education, Minzu University of China, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5643-3309","authenticated-orcid":false,"given":"Wenbin","family":"He","sequence":"additional","affiliation":[{"name":"Department of Key Laboratory of Ethnic Language Intelligent Analysis and Security Governance, Ministry of Education, Minzu University of China, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2736-3878","authenticated-orcid":false,"family":"Chaomurilige","sequence":"additional","affiliation":[{"name":"Department of Key Laboratory of Ethnic Language Intelligent Analysis and Security Governance, Ministry of Education, Minzu University of China, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5064-6526","authenticated-orcid":false,"given":"Xuan","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Key Laboratory of Ethnic Language Intelligent Analysis and Security Governance, Ministry of Education, Minzu University of China, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8522-565X","authenticated-orcid":false,"given":"Zheng","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Key Laboratory of Ethnic Language Intelligent Analysis and Security Governance, Ministry of Education, Minzu University of China, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6861-9684","authenticated-orcid":false,"given":"Honghao","family":"Gao","sequence":"additional","affiliation":[{"name":"School of Computer Engineering and Science, Shanghai University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"5998","article-title":"Attention is all you\n                    need","volume-title":"Proc. Adv. Neural Inf. Process.\n                        Syst.","volume":"30","author":"Vaswani","year":"2017"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref6","first-page":"1","article-title":"PaLI: A jointly-scaled multilingual\n                        language-image model","volume-title":"Proc. 11th Int.\n                        Conf. Learn. Representations (ICLR)","author":"Chen","year":"2023"},{"key":"ref7","first-page":"8748","article-title":"Learning transferable visual models from natural\n                        language supervision","volume-title":"Proc. 38th Int.\n                        Conf. Mach. Learn. (ICML)","volume":"139","author":"Radford","year":"2021"},{"key":"ref8","first-page":"5583","article-title":"ViLT: Vision-and-language transformer without\n                        convolution or region supervision","volume-title":"Proc.\n                        38th Int. Conf. Mach. Learn. (ICML)","volume":"139","author":"Kim","year":"2021"},{"key":"ref9","first-page":"9694","article-title":"Align before fuse: Vision and language representation\n                        learning with momentum distillation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Li","year":"2021"},{"key":"ref10","first-page":"32897","article-title":": Unified vision-language pre-training with\n                        mixture-of-modality-experts","volume-title":"Proc. Adv.\n                        Neural Inf. Process. Syst.","volume":"35","author":"Bao","year":"2022"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611740"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00397"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00414"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.818"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.315"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.196"},{"key":"ref22","first-page":"2296","article-title":"Are you talking to a machine? Dataset and methods for\n                        multilingual image question","volume-title":"Proc. Adv.\n                        Neural Inf. Process. Syst., 2015","author":"Gao"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.308"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.202"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.7717\/peerj-cs.1400"},{"key":"ref26","first-page":"642","article-title":"UniLMv2: Pseudo-masked language models for\n                        unified language model pre-training","volume-title":"Proc. 37th Int. Conf. Mach. Learn. (ICML)","volume":"119","author":"Bao","year":"2020"},{"key":"ref27","article-title":"RoBERTa: A robustly optimized BERT pretraining\n                        approach","author":"Liu","year":"2019"},{"key":"ref28","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for\n                        unified vision-language understanding and\n                    generation","volume-title":"Proc. Int. Conf. Mach. Learn.\n                        (ICML)","volume":"162","author":"Li","year":"2022"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref30","first-page":"1143","article-title":"Im2Text: Describing images using 1 million captioned\n                        photographs","volume-title":"Proc. Adv. Neural Inf.\n                        Process. Syst.","author":"Ordonez","year":"2011"},{"key":"ref31","article-title":"VisualBERT: A simple and performant baseline for\n                        vision and language","author":"Li","year":"2019"},{"key":"ref32","first-page":"13","article-title":"VilBERT: Pretraining task-agnostic visiolinguistic\n                        representations for vision-and-language tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Lu","year":"2019"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.7"},{"key":"ref34","article-title":"Distilling the knowledge in a neural\n                        network","author":"Hinton","year":"2015"},{"key":"ref35","first-page":"10347","article-title":"Training data-efficient image transformers &\n                        distillation through attention","volume-title":"Proc.\n                        38th Int. Conf. Mach. Learn. (ICML)","volume":"139","author":"Touvron","year":"2021"},{"key":"ref36","first-page":"1602","article-title":"Born-again neural networks","volume-title":"Proc. 35th Int. Conf. Mach. Learn. (ICML)","volume":"80","author":"Furlanello","year":"2018"},{"key":"ref37","article-title":"DistilBERT, a distilled version of BERT: smaller,\n                        faster, cheaper and lighter","author":"Sanh","year":"2019"},{"key":"ref38","first-page":"8092","article-title":"Learning to specialize with knowledge distillation\n                        for visual question answering","volume-title":"Proc. Adv.\n                        Neural Inf. Process. Syst.","author":"Mun","year":"2018"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00048"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/533"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.aacl-main.90"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.151"},{"key":"ref43","first-page":"2790","article-title":"Parameter-efficient transfer learning for\n                        NLP","volume-title":"Proc. 36th Int. Conf. Mach. Learn.\n                        (ICML)","volume":"97","author":"Houlsby","year":"2019"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00258"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.617"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.365"},{"key":"ref47","article-title":"Microsoft COCO captions: Data collection and\n                        evaluation server","author":"Chen","year":"2015"},{"key":"ref48","first-page":"2214","article-title":"Parallel data, tools and interfaces in\n                        OPUS","volume-title":"Proc. 8th Int. Conf. Lang. Resour.\n                        Eval. (LREC)","author":"Tiedemann","year":"2012"},{"key":"ref49","first-page":"1364","article-title":"Open subtitles paraphrase corpus for six\n                        languages","volume-title":"Proc. 11th Int. Conf. Lang.\n                        Resour. Eval. (LREC)","author":"Creutz","year":"2018"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.507"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.747"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-eacl.186"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00553"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00180"}],"container-title":["IEEE Transactions on Computational Social Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6570650\/11118943\/10574223.pdf?arnumber=10574223","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,8]],"date-time":"2025-08-08T04:34:00Z","timestamp":1754627640000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10574223\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8]]},"references-count":54,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tcss.2024.3402270","relation":{},"ISSN":["2329-924X","2373-7476"],"issn-type":[{"value":"2329-924X","type":"electronic"},{"value":"2373-7476","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8]]}}}