{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T12:22:34Z","timestamp":1773490954494,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":30,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819570744","type":"print"},{"value":"9789819570751","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-981-95-7075-1_30","type":"book-chapter","created":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T11:14:44Z","timestamp":1773486884000},"page":"460-475","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Multimodal Named Entity Recognition with\u00a0Synthesized SVG Graphics and\u00a0Structural Semantic Consistency Scoring"],"prefix":"10.1007","author":[{"given":"Shujun","family":"Xia","sequence":"first","affiliation":[]},{"given":"Yulong","family":"Zhou","sequence":"additional","affiliation":[]},{"given":"Wei","family":"Li","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,3,15]]},"reference":[{"key":"30_CR1","unstructured":"Bent, B.: Semantic approach to quantifying the consistency of diffusion model image generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, pp. 8218\u20138222 (2024)"},{"key":"30_CR2","unstructured":"Carlier, A., Danelljan, M., Alahi, A., Timofte, R.: Deepsvg: a hierarchical generative network for vector graphics animation. arXiv preprint arXiv:2007.11301 (2020), https:\/\/arxiv.org\/abs\/2007.11301"},{"key":"30_CR3","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2019), https:\/\/arxiv.org\/abs\/1810.04805"},{"issue":"4","key":"30_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3447772","volume":"54","author":"A Hogan","year":"2021","unstructured":"Hogan, A., et al.: Knowledge graphs: survey and research directions. ACM Comput. Surv. 54(4), 1\u201337 (2021)","journal-title":"ACM Comput. Surv."},{"key":"30_CR5","unstructured":"Huang, Z., Zhu, J., Zhou, Q., Chen, X., Fu, Y., Chang, B.: Prompting chatgpt in mner: enhanced multimodal named entity recognition with auxiliary refined knowledge. arXiv preprint arXiv:2305.14178 (2023)"},{"key":"30_CR6","doi-asserted-by":"crossref","unstructured":"Jain, A., Xie, A., Abbeel, P.: Vectorfusion: text-to-svg by abstracting pixel-based diffusion models. arXiv preprint arXiv:2211.11319 (2022)","DOI":"10.1109\/CVPR52729.2023.00190"},{"issue":"2","key":"30_CR7","doi-asserted-by":"publisher","first-page":"494","DOI":"10.1109\/TNNLS.2021.3070843","volume":"33","author":"S Ji","year":"2022","unstructured":"Ji, S., Pan, S., Cambria, E., Marttinen, P., Yu, P.S.: A survey on knowledge graphs: representation, acquisition, and applications. IEEE Trans. Neural Netw. Learn. Syst. 33(2), 494\u2013514 (2022)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"30_CR8","unstructured":"Jia, M., Shen, L., He, X., Li, J.: Mner-mi: a multi-image dataset for multimodal named entity recognition in social media. In: Proceedings of the 30th International Conference on Computational Linguistics (COLING) (2024)"},{"key":"30_CR9","doi-asserted-by":"crossref","unstructured":"Jia, M., et al.: Mner-qg: an end-to-end mrc framework for multimodal named entity recognition with query grounding. In: Proceedings of the 37th AAAI Conference on Artificial Intelligence (AAAI) (2023)","DOI":"10.1609\/aaai.v37i7.25971"},{"issue":"1","key":"30_CR10","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1109\/TKDE.2020.2981314","volume":"34","author":"J Li","year":"2020","unstructured":"Li, J., Sun, A., Han, J., Li, C.: A survey on deep learning for named entity recognition. IEEE Trans. Knowl. Data Eng. 34(1), 50\u201370 (2020)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"30_CR11","unstructured":"Liu, M., Tu, Z., Zhang, T., Su, T., Wang, Z.: Ltp: a new active learning strategy for bert crf based named entity recognition. arXiv preprint arXiv:2001.02524 (2020), https:\/\/arxiv.org\/abs\/2001.02524"},{"key":"30_CR12","doi-asserted-by":"crossref","unstructured":"Lu, D., Neves, L., Carvalho, V., Zhang, N., Ji, H.: Visual attention model for name tagging in multimodal social media. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (ACL 2018), pp. 1990\u20131999 (2018)","DOI":"10.18653\/v1\/P18-1185"},{"key":"30_CR13","doi-asserted-by":"crossref","unstructured":"Moon, S., Neves, L., Carvalho, V.: Multimodal named entity recognition for short social media posts. arXiv preprint arXiv:1802.07862 (2018)","DOI":"10.18653\/v1\/N18-1078"},{"key":"30_CR14","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: Proceedings of the 38th International Conference on Machine Learning (ICML 2021), pp. 8748\u20138763 (2021)"},{"key":"30_CR15","doi-asserted-by":"crossref","unstructured":"Reddy, P., Gharbi, M., Luk\u00e1\u010d, M., Mitra, N.J.: Im2vec: synthesizing vector graphics without vector supervision. arXiv preprint arXiv:2102.02798 (2021), https:\/\/arxiv.org\/abs\/2102.02798","DOI":"10.1109\/CVPR46437.2021.00726"},{"key":"30_CR16","doi-asserted-by":"crossref","unstructured":"Shen, Y., Song, K., Tan, X., Li, D., Lu, W., Zhuang, Y.: Diffusionner: Boundary diffusion for named entity recognition. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (ACL), ACL (2023)","DOI":"10.18653\/v1\/2023.acl-long.215"},{"key":"30_CR17","doi-asserted-by":"crossref","unstructured":"Sun, L., Wang, J., Zhang, K., Su, Y., Weng, F.: Rpbert: a text-image relation propagation-based bert model for multimodal ner. In: Proceedings of the 35th AAAI Conference on Artificial Intelligence (AAAI) (2021)","DOI":"10.1609\/aaai.v35i15.17633"},{"key":"30_CR18","unstructured":"W3C: Xml path language (xpath) version 1.0 (1999), https:\/\/www.w3.org\/TR\/xpath\/, w3C Recommendation"},{"key":"30_CR19","unstructured":"W3C: Extensible markup language (xml) 1.0 (fifth edition) (2008), https:\/\/www.w3.org\/TR\/xml\/, w3C Recommendation"},{"key":"30_CR20","unstructured":"W3C: Scalable vector graphics (svg) 1.1 (second edition) (2011), https:\/\/www.w3.org\/TR\/SVG11\/, w3C Recommendation"},{"key":"30_CR21","unstructured":"W3C: Rdf 1.1 concepts and abstract syntax (2014), https:\/\/www.w3.org\/TR\/rdf11-concepts\/, w3C Recommendation"},{"key":"30_CR22","doi-asserted-by":"crossref","unstructured":"Wu, R., Su, W., Ma, K., Liao, J.: Iconshop: text-guided vector icon synthesis with autoregressive transformers. arXiv preprint arXiv:2304.14400 (2023), https:\/\/arxiv.org\/abs\/2304.14400","DOI":"10.1145\/3618364"},{"key":"30_CR23","doi-asserted-by":"crossref","unstructured":"Xiong, C., Dai, Z., Callan, J., Liu, T.Y.: Towards better text understanding and retrieval through kernel entity salience modeling. In: Proceedings of the 41st International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 575\u2013584 (2018)","DOI":"10.1145\/3209978.3209982"},{"key":"30_CR24","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1007\/978-981-96-2054-8_3","volume":"1","author":"B Xu","year":"2025","unstructured":"Xu, B., Jiang, H., Wei, S., Du, M., Song, H., Wang, H.: A multi-expert collaborative framework for multimodal named entity recognition. MultiMedia Model. 1, 30\u201343 (2025)","journal-title":"MultiMedia Model."},{"key":"30_CR25","doi-asserted-by":"crossref","unstructured":"Yamada, I., Asai, A., Shindo, H., Takeda, H., Matsumoto, Y.: Luke: Deep contextualized entity representations with entity-aware self-attention. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.523"},{"key":"30_CR26","doi-asserted-by":"crossref","unstructured":"Yu, J., Jiang, J., Yang, L., Xia, R.: Improving multimodal named entity recognition via entity span detection with unified multimodal transformer. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (ACL 2020), pp. 306\u2013316. ACL (2020). https:\/\/aclanthology.org\/2020.acl-main.306.pdf","DOI":"10.18653\/v1\/2020.acl-main.306"},{"key":"30_CR27","doi-asserted-by":"crossref","unstructured":"Zhang, D., Wei, S., He, S., Wu, H., Zhu, Q., Zhou, G.: Multi-modal graph fusion for named entity recognition with targeted visual guidance. In: Proceedings of the 35th AAAI Conference on Artificial Intelligence (AAAI) (2021)","DOI":"10.1609\/aaai.v35i16.17687"},{"key":"30_CR28","unstructured":"Zhang, J., Ma, J., Song, Y., Zhou, Q.: Multimodal multi-label named entity recognition via unified cross-modal attention. In: Findings of the Association for Computational Linguistics: ACL 2021 (2021)"},{"key":"30_CR29","doi-asserted-by":"crossref","unstructured":"Zhang, Q., Fu, J., Liu, X., Huang, X.: Adaptive co-attention network for named entity recognition in tweets. In: Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence (2018)","DOI":"10.1609\/aaai.v32i1.11962"},{"key":"30_CR30","unstructured":"Zhang, X., et al.: Text-to-svg generation with structured representation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2021) (2021)"}],"container-title":["Lecture Notes in Computer Science","PRICAI 2025: Trends in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-7075-1_30","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T11:14:47Z","timestamp":1773486887000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-7075-1_30"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819570744","9789819570751"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-7075-1_30","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"15 March 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRICAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific Rim International Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Wellington","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"New Zealand","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 November 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 November 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pricai2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.pricai.org\/2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}