{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T17:27:15Z","timestamp":1783099635086,"version":"3.54.6"},"reference-count":73,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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 Hainan Province, China","award":["ZDYF2024(LALH)005"],"award-info":[{"award-number":["ZDYF2024(LALH)005"]}]},{"name":"2024 National Social Science Fund of China","award":["24VJXG063"],"award-info":[{"award-number":["24VJXG063"]}]},{"name":"Hainan Provincial Joint Project of Li'an International Education","award":["624LALH004"],"award-info":[{"award-number":["624LALH004"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2025.3557678","type":"journal-article","created":{"date-parts":[[2025,4,3]],"date-time":"2025-04-03T19:59:13Z","timestamp":1743710353000},"page":"3184-3196","source":"Crossref","is-referenced-by-count":3,"title":["Cross-Lingual Adaptation for Vision-Language Model via Multimodal Semantic Distillation"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0787-550X","authenticated-orcid":false,"given":"Yu","family":"Weng","sequence":"first","affiliation":[{"name":"Department of Information Engineering, Minzu University of China, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5643-3309","authenticated-orcid":false,"given":"Wenbin","family":"He","sequence":"additional","affiliation":[{"name":"Department of Information Engineering, Minzu University of China, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-0629-3805","authenticated-orcid":false,"given":"Jun","family":"Dong","sequence":"additional","affiliation":[{"name":"Department of Information Engineering, Minzu University of China, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2736-3878","authenticated-orcid":false,"family":"Chaomurilige","sequence":"additional","affiliation":[{"name":"Department of Information Engineering, Minzu University of China, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5064-6526","authenticated-orcid":false,"given":"Xuan","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Information Engineering, Minzu University of China, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8522-565X","authenticated-orcid":false,"given":"Zheng","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Information Engineering, Minzu University of China, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01522"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3447778"},{"key":"ref3","first-page":"32897","article-title":"VLMo: Unified vision-language pre-training with mixture-of-modality-experts","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Bao","year":"2022"},{"key":"ref4","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2023"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3291588"},{"key":"ref6","article-title":"Chatgpt","year":"2023"},{"key":"ref7","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref8","article-title":"Deepseek-v3 technical report","author":"Liu","year":"2024"},{"key":"ref9","first-page":"34892","article-title":"Visual instruction tuning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Liu","year":"2023"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1093\/nsr\/nwae403"},{"key":"ref11","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023"},{"key":"ref12","first-page":"8469","article-title":"PaLM-E: An embodied multimodal language model","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","volume":"202","author":"Driess","year":"2023"},{"key":"ref13","article-title":"Qwen-VL: A frontier large vision-language model with versatile abilities","author":"Bai","year":"2023"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01239"},{"key":"ref15","article-title":"A survey on large language models with multilingualism: Recent advances and new frontiers","author":"Huang","year":"2025"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.488"},{"key":"ref17","first-page":"1","article-title":"Large multilingual models pivot zero-shot multimodal learning across languages","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Hu","year":"2024"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00397"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00414"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.818"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.315"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.176"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1175"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-short.32"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.196"},{"key":"ref26","first-page":"10858","article-title":"m3P: Towards multimodal multilingual translation with multimodal prompt","volume-title":"Proc. Joint Int. Conf. Comput. Linguistics Lang. Resour. Eval. (LREC-COLING 2024)","author":"Yang","year":"2024"},{"key":"ref27","first-page":"1","article-title":"Pali: A jointly-scaled multilingual language-image model","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Chen","year":"2023"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.alvr-1.2"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-024-01339-7"},{"key":"ref30","first-page":"1","article-title":"Outrageously large neural networks: The sparsely-gated mixture-of-experts layer","volume-title":"Proc. 5th Int. Conf. Learn. Representations","author":"Shazeer","year":"2017"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00258"},{"key":"ref32","first-page":"2370","article-title":"IGLUE: A benchmark for transfer learning across modalities, tasks, and languages","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Bugliarello","year":"2022"},{"key":"ref33","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":"ref34","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref35","first-page":"23318","article-title":"OFA: Unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang","year":"2022"},{"key":"ref36","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2022"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3713070"},{"key":"ref38","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li","year":"2021"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3339661"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01838"},{"key":"ref41","article-title":"MoE-LLaVA: Mixture of experts for large vision-language models","author":"Lin","year":"2024"},{"key":"ref42","first-page":"121475","article-title":"CogVLM: Visual expert for pretrained language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"37","author":"Wang","year":"2025"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3369699"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.308"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR56361.2022.9956259"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/SPCOM55316.2022.9840835"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.891"},{"key":"ref48","article-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01453-z"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.365"},{"key":"ref51","article-title":"A survey on knowledge distillation of large language models","author":"Xu","year":"2024"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3435790"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.747"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref56","first-page":"7057","article-title":"Cross-lingual language model pretraining","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Conneau","year":"2019"},{"key":"ref57","first-page":"1538","article-title":"Simple, scalable adaptation for neural machine translation","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process. 9th Int. Joint Conf. Natural Lang. Process.","author":"Bapna","year":"2019"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-eacl.186"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.617"},{"key":"ref60","doi-asserted-by":"crossref","first-page":"3635","DOI":"10.18653\/v1\/P19-1354","article-title":"Assessing the ability of self-attention networks to learn word order","volume-title":"Proc. 57th Annu. Meeting Assoc. Comput. Linguistics","author":"Yang","year":"2019"},{"key":"ref61","first-page":"2214","article-title":"Parallel data, tools and interfaces in opus","volume-title":"Proc. Lrec","volume":"2012","author":"Tiedemann","year":"2012"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.507"},{"key":"ref63","first-page":"1742","article-title":"OpenSubtitles2018: Statistical rescoring of sentence alignments in large, noisy parallel corpora","volume-title":"Proc. 11th Int. Conf. Lang. Resour. Eval.","author":"Lison","year":"2018"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref66","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. 7th Int. Conf. Learn. Representations","author":"Loshchilov","year":"2019"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1644"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i11.26574"},{"key":"ref71","article-title":"VisualBERT: A simple and performant baseline for vision and language","author":"Li","year":"2019"},{"key":"ref72","first-page":"1","article-title":"Vl-BERT: Pre-training of generic visual-linguistic representations","volume-title":"Proc. 8th Int. Conf. Learn. Representations","author":"Su","year":"2020"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1002\/wics.101"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/10948343.pdf?arnumber=10948343","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,29]],"date-time":"2025-05-29T17:30:47Z","timestamp":1748539847000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10948343\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":73,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3557678","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}