{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T01:30:51Z","timestamp":1763343051387,"version":"3.45.0"},"reference-count":24,"publisher":"Tech Science Press","issue":"3","license":[{"start":{"date-parts":[[2025,5,25]],"date-time":"2025-05-25T00:00:00Z","timestamp":1748131200000},"content-version":"vor","delay-in-days":144,"URL":"https:\/\/doi.org\/10.32604\/TSP-CROSSMARKPOLICY"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["CMC"],"published-print":{"date-parts":[[2025]]},"DOI":"10.32604\/cmc.2025.061902","type":"journal-article","created":{"date-parts":[[2025,4,9]],"date-time":"2025-04-09T06:47:21Z","timestamp":1744181241000},"page":"5747-5760","update-policy":"https:\/\/doi.org\/10.32604\/tsp-crossmarkpolicy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-Modal Named Entity Recognition with Auxiliary Visual Knowledge and Word-Level Fusion"],"prefix":"10.32604","volume":"83","author":[{"given":"Huansha","family":"Wang","sequence":"first","affiliation":[]},{"given":"Ruiyang","family":"Huang","sequence":"additional","affiliation":[]},{"given":"Qinrang","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Xinghao","family":"Wang","sequence":"additional","affiliation":[]}],"member":"17807","published-online":{"date-parts":[[2025]]},"reference":[{"key":"ref1","series-title":"Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics","first-page":"1990","article-title":"Visual attention model for name tagging in multimodal social media","author":"Lu","year":"2018"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"3556","DOI":"10.3390\/electronics11213556","article-title":"Research progress on vision-language multimodal pretraining model technology","volume":"11","author":"Wang","year":"2022","journal-title":"Electronics"},{"key":"ref3","series-title":"2009 IEEE Conference on Computer Vision and Pattern Recognition","first-page":"248","article-title":"ImageNet: a large-scale hierarchical image database","author":"Deng","year":"2009 Jun 20\u201325"},{"key":"ref4","series-title":"Computer vision\u2014ECCV 2014: 13th European conference","first-page":"740","article-title":"Microsoft coco: common objects in context","author":"Lin","year":"2014"},{"key":"ref5","series-title":"Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","first-page":"3176","article-title":"ITA: image-text alignments for multi-modal named entity recognition","author":"Wang","year":"2022"},{"key":"ref6","series-title":"Findings of the Association for Computational Linguistics: EMNLP 2022","first-page":"5925","article-title":"Named entity and relation extraction with multi-modal retrieval","author":"Wang","year":"2022"},{"key":"ref7","series-title":"Findings of the Association for Computational Linguistics: EMNLP 2023","first-page":"2787","article-title":"Prompting ChatGPT in MNER: enhanced multimodal named entity recognition with auxiliary refined knowledge","author":"Li","year":"2023"},{"key":"ref8","series-title":"Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","first-page":"852","article-title":"Multimodal named entity recognition for short social media posts","author":"Moon","year":"2018"},{"key":"ref9","series-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics","first-page":"3342","article-title":"Improving multimodal named entity recognition via entity span detection with unified multimodal transformer","author":"Yu","year":"2020 Jul 5\u201310"},{"key":"ref10","first-page":"14347","article-title":"Multi-modal graph fusion for named entity recognition with targeted visual guidance","volume":"35","author":"Zhang","year":"2021","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref11","first-page":"8032","article-title":"MNER-QG: an end-to-end MRC framework for multimodal named entity recognition with query grounding","volume":"37","author":"Jia","year":"2023","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref12","series-title":"2022 IEEE International Conference on Multimedia and Expo (ICME)","first-page":"1","article-title":"CAT-MNER: multimodal named entity recognition with knowledge-refined cross-modal attention","author":"Wang","year":"2022 Jul 18\u201322"},{"key":"ref13","series-title":"Proceedings of the 38 th International Conference on Machine Learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021 Jul 18\u201324"},{"key":"ref14","first-page":"5674","article-title":"Adaptive co-attention network for named entity recognition in tweets","volume":"32","author":"Zhang","year":"2018","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"e1856","DOI":"10.7717\/peerj-cs.1856","article-title":"RSRNeT: a novel multi-modal network framework for named entity recognition and relation extraction","volume":"10","author":"Wang","year":"2024","journal-title":"PeerJ Comput Sci"},{"key":"ref16","unstructured":"Bai J, Bai S, Chu Y, Cui Z, Dang K, Deng X, et al. Qwen technical report. arXiv:2309.16609. 2023."},{"key":"ref17","series-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics","first-page":"8440","article-title":"Unsupervised cross-lingual representation learning at scale","author":"Conneau","year":"2020 Jul 5\u201310"},{"key":"ref18","series-title":"Database Systems for Advanced Applications: 27th International Conference, DASFAA 2022","first-page":"297","article-title":"Promptmner: prompt-based entity-related visual clue extraction and integration for multimodal named entity recognition","author":"Wang","year":"2022 Apr 11\u201314"},{"key":"ref19","series-title":"Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics","first-page":"1064","article-title":"End-to-end sequence labeling via bi-directional LSTM-CNNS-CRF","author":"Ma","year":"2016"},{"key":"ref20","series-title":"Proceedings of HLT-NAACL 2016","first-page":"260","article-title":"Neural architectures for named entity recognition","author":"Lample","year":"2016"},{"key":"ref21","unstructured":"Huang Z, Xu W, Yu K. Bidirectional LSTM-CRF models for sequence tagging. arXiv:1508.01991. 2015."},{"key":"ref22","series-title":"NAACL-HLT","first-page":"4171","article-title":"BERT: pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019 Jun 2\u20137"},{"key":"ref23","series-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)","first-page":"6442","article-title":"LUKE: deep contextualized entity representations with entity-aware self-attention","author":"Yamada","year":"2020 Nov 16\u201320"},{"key":"ref24","series-title":"Proceedings of the 30th ACM International Conference on Multimedia","first-page":"3983","article-title":"Learning from different text-image pairs: a relation-enhanced graph convolutional network for multimodal NER","author":"Zhao","year":"2022 Oct 10\u201314"}],"container-title":["Computers, Materials & Continua"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/cdn.techscience.cn\/files\/cmc\/2025\/TSP_CMC-83-3\/TSP_CMC_61902\/TSP_CMC_61902.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T01:28:29Z","timestamp":1763342909000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.techscience.com\/cmc\/v83n3\/61001"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":24,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2025]]},"published-print":{"date-parts":[[2025]]}},"URL":"https:\/\/doi.org\/10.32604\/cmc.2025.061902","relation":{},"ISSN":["1546-2226"],"issn-type":[{"type":"electronic","value":"1546-2226"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"2024-12-05","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-03-26","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-05-19","order":2,"name":"published","label":"Published Online","group":{"name":"publication_history","label":"Publication History"}}]}}