{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T16:46:42Z","timestamp":1781974002930,"version":"3.54.5"},"reference-count":70,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001321","name":"National Research Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001321","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01956","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"21048-21058","source":"Crossref","is-referenced-by-count":3,"title":["Leveraging the Power of MLLMs for Gloss-Free Sign Language Translation"],"prefix":"10.1109","author":[{"given":"Jungeun","family":"Kim","sequence":"first","affiliation":[{"name":"Yonsei University,Department of Artificial Intelligence"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hyeongwoo","family":"Jeon","sequence":"additional","affiliation":[{"name":"Graduate School of Information, Yonsei University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jongseong","family":"Bae","sequence":"additional","affiliation":[{"name":"Yonsei University,Department of Artificial Intelligence"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ha Young","family":"Kim","sequence":"additional","affiliation":[{"name":"Graduate School of Information, Yonsei University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","article-title":"Pixtral 12b","author":"Agrawal","year":"2024","journal-title":"Pixtral 12b"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref4","author":"Bahdanau","year":"2016","journal-title":"Neural machine translation by jointly learning to align and translate"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00812"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01004"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-022-1369-5"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00506"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1240"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.63317\/4qo2dsetvyk8"},{"issue":"3","key":"ref13","volume":"2","author":"Chiang","year":"2023","journal-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90 \\%^{*} chatgpt quality"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref15","author":"Devlin","year":"2019","journal-title":"Bert: Pre-training of deep bidirectional transformers for language understanding"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3352587"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095466"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01738"},{"key":"ref19","article-title":"Multimodal-gpt: A vision and language model for dialogue with humans","author":"Gong","year":"2023","journal-title":"arXiv preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.90"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00503"},{"key":"ref22","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"International Conference on Learning Representations","author":"Hu","year":"2022"},{"key":"ref23","article-title":"Park","author":"Hwang","year":"2024","journal-title":"Universal gloss-level representation for gloss-free sign language translation and production"},{"key":"ref24","article-title":"An efficient sign language translation using spatial configuration and motion dynamics with 11 ms","author":"Hwang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref25","author":"Izacard","year":"2022","journal-title":"Unsupervised dense information retrieval with contrastive learning"},{"key":"ref26","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"International conference on machine learning","author":"Jia","year":"2021"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72946-1_20"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.297"},{"key":"ref29","author":"Li","year":"2024","journal-title":"Llava-onevision: Easy visual task transfer"},{"key":"ref30","first-page":"12034","article-title":"Tspnet: Hierarchical feature learning via temporal semantic pyramid for sign language translation","volume":"33","author":"Li","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref31","author":"Li","year":"2024","journal-title":"Llava-next-interleave: Tackling multi-image, video, and 3d in large multimodal models"},{"key":"ref32","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume":"34","author":"Li","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref33","author":"Li","year":"2023","journal-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"key":"ref35","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","author":"Lin","year":"2004","journal-title":"Text summarization branches out"},{"key":"ref36","article-title":"Visual instruction tuning","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref37","article-title":"Univl: A unified video and language pre-training model for multimodal understanding and generation","author":"Luo","journal-title":"arXiv preprint"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d15-1166"},{"key":"ref39","volume-title":"Towards faithful sign language translation","author":"Min","year":"2023"},{"key":"ref40","author":"Mo","year":"2024","journal-title":"Mochat: Joints-grouped spatio-temporal grounding 11 m for multi-turn motion comprehension and description"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref42","article-title":"Kosmos-2: Grounding multimodal large language models to the world","author":"Peng","year":"2023","journal-title":"arXiv preprint"},{"key":"ref43","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref44","author":"Rastgoo","year":"2022","journal-title":"All you need in sign language production"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"issue":"2","key":"ref46","first-page":"14","article-title":"Sign language gesture recognition","volume":"7","author":"Sharma","year":"2020","journal-title":"International Journal of Recent Research Aspects"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1093\/deafed\/eni001"},{"key":"ref48","author":"Tang","year":"2020","journal-title":"Multilingual translation with extensible multilingual pretraining and finetuning"},{"issue":"6","key":"ref49","volume":"3","author":"Taori","year":"2023","journal-title":"Alpaca: A strong, replicable instructionfollowing model. Stanford Center for Research on Foundation Models"},{"key":"ref50","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref51","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1023\/A:1008014420317"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01173"},{"key":"ref54","author":"Wang","year":"2024","journal-title":"Text embeddings by weakly-supervised contrastive pretraining"},{"key":"ref55","author":"Wang","year":"2024","journal-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution"},{"key":"ref56","article-title":"Simvlm: Simple visual language model pretraining with weak supervision","author":"Wang","year":"2021","journal-title":"arXiv preprint"},{"key":"ref57","article-title":"Sign2gpt: Leveraging large language models for gloss-free sign language translation","author":"Wong","year":"2024","journal-title":"arXiv preprint"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/BigData59044.2023.10386743"},{"key":"ref59","author":"Yang","year":"2024","journal-title":"Qwen2 technical report"},{"key":"ref60","article-title":"Filip: Fine-grained interactive language-image pre-training","author":"Yao","year":"2021","journal-title":"arXiv preprint"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475544"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00251"},{"key":"ref63","article-title":"Sltunet: A simple unified model for sign language translation","author":"Zhang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.1055"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3087006"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.01908"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00137"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3059098"},{"key":"ref70","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023","journal-title":"arXiv preprint"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444586.pdf?arnumber=11444586","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:10:47Z","timestamp":1777612247000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444586\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":70,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01956","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}