{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T08:10:01Z","timestamp":1790323801219,"version":"4.1.0"},"reference-count":52,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Expert Systems with Applications"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1016\/j.eswa.2026.133358","type":"journal-article","created":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T16:40:26Z","timestamp":1781800826000},"page":"133358","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PC","title":["GC-Fusion: Enhancing Dongba manuscript translation via multimodal LLMs with glyph-coordinate fusion"],"prefix":"10.1016","volume":"331","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2773-9588","authenticated-orcid":false,"given":"Junyao","family":"Xing","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5382-1000","authenticated-orcid":false,"given":"Xiaojun","family":"Bi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3488-6028","authenticated-orcid":false,"given":"Shuo","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.eswa.2026.133358_bib0001","unstructured":"Bai, J., Bai, S., Yang, S., Wang, S., Tan, S., Wang, P., Lin, J., Zhou, C., & Zhou, J. (2023). Qwen-VL: A versatile vision-language model for understanding, localization, text reading, and beyond. https:\/\/arxiv.org\/abs\/2308.12966."},{"key":"10.1016\/j.eswa.2026.133358_bib0002","unstructured":"Bai, S., Chen, K., Liu, X., Wang, J., Ge, W., Song, S., Dang, K., Wang, P., Wang, S., Tang, J., Zhong, H., Zhu, Y., Yang, M., Li, Z., Wan, J., Wang, P., Ding, W., Fu, Z., Xu, Y., Ye, J., Zhang, X., Xie, T., Cheng, Z., Zhang, H., Yang, Z., Xu, H., & Lin, J. (2025). Qwen2.5-VL technical report. https:\/\/arxiv.org\/abs\/2502.13923."},{"key":"10.1016\/j.eswa.2026.133358_bib0003","doi-asserted-by":"crossref","unstructured":"Bi, X., Li, S., Xing, J., Wang, Z., Luo, F., Qiao, W., Han, L., Sun, Z., Li, P., & Liu, Y. (2025a). DongbaMIE: A multimodal information extraction dataset for evaluating semantic understanding of dongba pictograms. On the arXiv. 10.48550\/arXiv.2503.03644.","DOI":"10.18653\/v1\/2025.findings-emnlp.51"},{"issue":"39","key":"10.1016\/j.eswa.2026.133358_bib0004","article-title":"A novel unsupervised contrastive learning framework for ancient yi script character dataset construction","volume":"13","author":"Bi","year":"2025","journal-title":"npj Heritage Science"},{"key":"10.1016\/j.eswa.2026.133358_bib0005","doi-asserted-by":"crossref","unstructured":"Dai, W., Li, J., Li, D., Tiong, A. M. H., Zhao, J., Wang, W., Li, B., Fung, P., & Hoi, S. (2023). InstructBLIP: Towards general-purpose vision-language models with instruction tuning. https:\/\/arxiv.org\/abs\/2305.06500.","DOI":"10.52202\/075280-2142"},{"key":"10.1016\/j.eswa.2026.133358_bib0006","series-title":"Naxi pictograph character chart","author":"Fang","year":"1981"},{"key":"10.1016\/j.eswa.2026.133358_bib0007","doi-asserted-by":"crossref","first-page":"351","DOI":"10.1504\/IJICT.2018.094323","article-title":"Chinese-naxi syntactic statistical machine translation based on tree-to-tree","volume":"13","author":"Gao","year":"2018","journal-title":"International Journal of Information and Communication Technology"},{"key":"10.1016\/j.eswa.2026.133358_bib0008","doi-asserted-by":"crossref","first-page":"333","DOI":"10.1007\/s13042-014-0325-2","article-title":"Chinese-naxi machine translation method based on naxi dependency language model","volume":"8","author":"Gao","year":"2017","journal-title":"International Journal of Machine Learning and Cybernetics"},{"issue":"1","key":"10.1016\/j.eswa.2026.133358_bib0009","article-title":"A chinese-naxi tree-to-tree machine translation method based on subtree alignment","volume":"2015","author":"Gao","year":"2015","journal-title":"Mathematical Problems in Engineering"},{"issue":"3","key":"10.1016\/j.eswa.2026.133358_bib0010","first-page":"39","article-title":"Deep learning approaches on image captioning: A review","volume":"56","author":"Ghandi","year":"2023","journal-title":"ACM Computing Surveys"},{"key":"10.1016\/j.eswa.2026.133358_bib0011","series-title":"2025 international conference on information and communication technology for development for africa (ICT4DA)","first-page":"83","article-title":"Image captioning in amharic language using deep convolutional neural networks with LSTM","author":"Guigsa","year":"2025"},{"issue":"5","key":"10.1016\/j.eswa.2026.133358_bib0012","first-page":"865","article-title":"Automatic segmentation algorithm for text lines of dongba hieroglyphs document image","volume":"43","author":"H. Kang","year":"2022","journal-title":"Journal of Graphics"},{"key":"10.1016\/j.eswa.2026.133358_bib0013","series-title":"2024 6th international conference on internet of things, automation and artificial intelligence (ioTAAI)","first-page":"714","article-title":"Research on tibetan-chinese machine translation method based on graphic multimodal fusion alignment","author":"He","year":"2024"},{"key":"10.1016\/j.eswa.2026.133358_bib0014","series-title":"2016 IEEE conference on computer vision and pattern recognition (CVPR)","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"10.1016\/j.eswa.2026.133358_bib0015","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2024.125557","article-title":"Vgts: Visually guided text spotting for novel categories in historical manuscripts","volume":"261","author":"Hu","year":"2025","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.133358_bib0016","doi-asserted-by":"crossref","first-page":"595","DOI":"10.1007\/978-3-030-99075-6_48","article-title":"Research on feature extraction and recognition of dongba hieroglyphs","volume":"117","author":"Huang","year":"2023","journal-title":"Mechanisms and Machine Science"},{"key":"10.1016\/j.eswa.2026.133358_bib0017","series-title":"An annotated collection of naxi dongba manuscripts","author":"Institute","year":"1999"},{"key":"10.1016\/j.eswa.2026.133358_bib0018","series-title":"2022 international joint conference on neural networks (IJCNN)","first-page":"1","article-title":"Multimodal neural machine translation for mongolian to chinese","author":"Jian","year":"2022"},{"key":"10.1016\/j.eswa.2026.133358_bib0019","series-title":"Findings of the association for computational linguistics: ACL-IJCNLP 2021","first-page":"3689","article-title":"Probing multi-modal machine translation with pre-trained language model","author":"Kong","year":"2021"},{"key":"10.1016\/j.eswa.2026.133358_bib0020","series-title":"2021 international conference on computational performance evaluation (comPE)","first-page":"387","article-title":"Multimodal neural machine translation for english-assamese pair","author":"Laskar","year":"2021"},{"key":"10.1016\/j.eswa.2026.133358_bib0021","series-title":"2023 international conference on data science, agents and artificial intelligence (ICDSAAI)","first-page":"1","article-title":"Multimodal fusion of transformer with attention mechanism for improved contextual image captioning","author":"Latha","year":"2023"},{"key":"10.1016\/j.eswa.2026.133358_bib0022","series-title":"2021 international conference on learning representations(ICLR)","article-title":"Prototypical contrastive learning of unsupervised representations","author":"Li","year":"2021"},{"key":"10.1016\/j.eswa.2026.133358_bib0023","doi-asserted-by":"crossref","first-page":"350","DOI":"10.1007\/978-3-642-45185-0_37","article-title":"The extracting method of chinese-naxi translation template based on improved dependency tree-to-string","volume":"8229","author":"Li","year":"2013","journal-title":"Chinese Lexical Semantics"},{"key":"10.1016\/j.eswa.2026.133358_bib0024","series-title":"Text summarization branches out","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","author":"Lin","year":"2004"},{"key":"10.1016\/j.eswa.2026.133358_bib0025","unstructured":"Liu, H., Li, C., Li, Y., Li, B., Zhang, Y., Shen, S., & Lee, Y. (2024). Llava-next: Improved reasoning, ocr, and world knowledge. https:\/\/llava-vl.github.io\/blog\/2024-01-30-llava-next\/."},{"key":"10.1016\/j.eswa.2026.133358_bib0026","unstructured":"Liu, H., Li, C., Wu, Q., & Lee, Y. J. (2023). Visual instruction tuning. https:\/\/arxiv.org\/abs\/2304.08485."},{"key":"10.1016\/j.eswa.2026.133358_bib0027","series-title":"2020 5th international conference on mechanical, control and computer engineering (ICMCCE)","first-page":"1571","article-title":"Multi-scale feature fusion based dongba character recognition","author":"Luo","year":"2020"},{"key":"10.1016\/j.eswa.2026.133358_bib0028","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.128744","article-title":"Mfnet: Multiscale fusion network for dongba character image inpainting","volume":"294","author":"Luo","year":"2025","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.133358_sbref0028","article-title":"Dongba pictographs recognition based on improved residual learning","volume":"17","author":"Luo","year":"2022","journal-title":"CAAI Transactions on Intelligent Systems"},{"key":"10.1016\/j.eswa.2026.133358_bib0030","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2022.118865","article-title":"Multiple attentional aggregation network for handwritten dongba character recognition","volume":"213","author":"Luo","year":"2023","journal-title":"Expert Systems with Applications"},{"issue":"5","key":"10.1016\/j.eswa.2026.133358_bib0031","doi-asserted-by":"crossref","DOI":"10.1145\/3721980","article-title":"Dongba machine translation with transfer learning: Leveraging pre-trained ancient chinese models","volume":"24","author":"Ma","year":"2025","journal-title":"ACM Transactions on Asian Low-Resource Language Information Processing"},{"key":"10.1016\/j.eswa.2026.133358_bib0032","article-title":"Stef: A swin transformer-based enhanced feature pyramid fusion model for dongba character detection","volume":"12","author":"Ma","year":"2024","journal-title":"npj Heritage Science"},{"key":"10.1016\/j.eswa.2026.133358_bib0033","doi-asserted-by":"crossref","DOI":"10.1038\/s41597-025-05434-6","article-title":"Dataset for single character detection in dongba manuscripts","volume":"12","author":"Ma","year":"2025","journal-title":"Scientific Data"},{"key":"10.1016\/j.eswa.2026.133358_bib0034","series-title":"Proceedings of the 40th annual meeting of the association for computational linguistics","first-page":"311","article-title":"BLEU: A method for automatic evaluation of machine translation","author":"Papineni","year":"2002"},{"issue":"4","key":"10.1016\/j.eswa.2026.133358_bib0035","first-page":"71","article-title":"On modern dongba calligraphy and painting","author":"Pinzheng","year":"1991","journal-title":"Ethnic Art Studies"},{"key":"10.1016\/j.eswa.2026.133358_bib0036","series-title":"Proceedings of the 38th international conference on machine learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.eswa.2026.133358_bib0037","series-title":"2025 8th international conference on advanced algorithms and control engineering (ICAACE)","first-page":"1202","article-title":"Blind restoration of masked dongba scripts images via hybrid CNN-transformer network","author":"Shi","year":"2025"},{"key":"10.1016\/j.eswa.2026.133358_bib0038","series-title":"2022 international conference for advancement in technology (ICONAT)","first-page":"1","article-title":"Image caption generation using deep neural networks","author":"Sudhakar","year":"2022"},{"key":"10.1016\/j.eswa.2026.133358_bib0039","doi-asserted-by":"crossref","first-page":"97","DOI":"10.1007\/s10590-020-09250-0","article-title":"Multimodal machine translation through visuals and speech","volume":"34","author":"Sulubacak","year":"2020","journal-title":"Machine Translation"},{"key":"10.1016\/j.eswa.2026.133358_bib0040","unstructured":"UNESCO, (2003). Ancient naxi dongba literature manuscripts - memory of the world. https:\/\/www.unesco.org\/en\/memory-world\/ancient-naxi-dongba-literature-manuscripts."},{"key":"10.1016\/j.eswa.2026.133358_bib0041","unstructured":"Wang, W., Gao, Z., Gu, L., Pu, H., Cui, L., Wei, X., Liu, Z., Jiang, L., Ye, S., Shao, J. et al. (2025). InternVL3.5: Advancing open-source multimodal models in versatility, reasoning, and efficiency. https:\/\/arxiv.org\/abs\/2508.18265."},{"key":"10.1016\/j.eswa.2026.133358_bib0042","doi-asserted-by":"crossref","unstructured":"Wang, W., Lv, Q., Yu, W., Hong, W., Qi, J., Wang, Y., Ji, J., Yang, Z., Zhao, L., Song, X., Xu, J., Xu, B., Li, J., Dong, Y., Ding, M., & Tang, J. (2024). CogVLM: Visual expert for pretrained language models. https:\/\/arxiv.org\/abs\/2311.03079.","DOI":"10.52202\/079017-3860"},{"key":"10.1016\/j.eswa.2026.133358_sbref0042","series-title":"Research on the detection and recognition algorithm of dongba character based on deep learning","author":"Wang","year":"2020"},{"key":"10.1016\/j.eswa.2026.133358_bib0044","series-title":"Ecai 2025 - 28th European conference on artificial intelligence","first-page":"2114","article-title":"Sewlt: Semantic enhancement for weak semantics low-resource languages translation","author":"Wu","year":"2025"},{"issue":"15","key":"10.1016\/j.eswa.2026.133358_bib0045","doi-asserted-by":"crossref","DOI":"10.3390\/math11153392","article-title":"A multi-scale hybrid attention network for sentence segmentation line detection in dongba scripture","volume":"11","author":"Xing","year":"2023","journal-title":"Mathematics"},{"key":"10.1016\/j.eswa.2026.133358_bib0046","doi-asserted-by":"crossref","DOI":"10.3724\/SP.J.1089.2023.19681","article-title":"Dongba painting few-shot classification combining spatial information and distribution relationship","volume":"35","author":"Xu","year":"2023","journal-title":"Journal of Computer-Aided Design and Computer Graphics"},{"key":"10.1016\/j.eswa.2026.133358_bib0047","series-title":"2021 14th international symposium on computational intelligence and design (ISCID)","first-page":"412","article-title":"Text line segmentation algorithm for dongba pictograph document","author":"Yang","year":"2021"},{"key":"10.1016\/j.eswa.2026.133358_bib0048","series-title":"2025 8th international conference on computer information science and application technology (CISAT)","first-page":"257","article-title":"Exploiting input space translation and contrastive learning for multimodal sentiment analysis","author":"Yao","year":"2025"},{"key":"10.1016\/j.eswa.2026.133358_bib0049","unstructured":"Yao, Y., Yu, T., Zhang, A. et al. (2024). MiniCPM-v: A GPT-4v level MLLM on your phone. https:\/\/arxiv.org\/abs\/2408.01800."},{"key":"10.1016\/j.eswa.2026.133358_bib0050","series-title":"Studies on Naxi Dongba scripts","author":"Yu","year":"2003"},{"key":"10.1016\/j.eswa.2026.133358_bib0051","series-title":"International conference on learning representations","article-title":"BERTscore: Evaluating text generation with BERT","author":"Zhang","year":"2020"},{"key":"10.1016\/j.eswa.2026.133358_sbref0052","series-title":"Proceedings of the 62nd annual meeting of the association for computational linguistics (volume 3: System demonstrations)","article-title":"Llamafactory: Unified efficient fine-tuning of 100+ language models","author":"Zheng","year":"2024"}],"container-title":["Expert Systems with Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426022670?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426022670?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T07:47:31Z","timestamp":1790322451000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0957417426022670"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":52,"alternative-id":["S0957417426022670"],"URL":"https:\/\/doi.org\/10.1016\/j.eswa.2026.133358","relation":{},"ISSN":["0957-4174"],"issn-type":[{"value":"0957-4174","type":"print"}],"subject":[],"published":{"date-parts":[[2026,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"GC-Fusion: Enhancing Dongba manuscript translation via multimodal LLMs with glyph-coordinate fusion","name":"articletitle","label":"Article Title"},{"value":"Expert Systems with Applications","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.eswa.2026.133358","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"133358"}}