{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T07:53:25Z","timestamp":1768809205872,"version":"3.49.0"},"reference-count":37,"publisher":"Springer Science and Business Media LLC","issue":"15","license":[{"start":{"date-parts":[[2023,10,20]],"date-time":"2023-10-20T00:00:00Z","timestamp":1697760000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,10,20]],"date-time":"2023-10-20T00:00:00Z","timestamp":1697760000000},"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":["Multimed Tools Appl"],"DOI":"10.1007\/s11042-023-17376-5","type":"journal-article","created":{"date-parts":[[2023,10,20]],"date-time":"2023-10-20T04:02:13Z","timestamp":1697774533000},"page":"45047-45058","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["MAFN: multi-level attention fusion network for multimodal named entity recognition"],"prefix":"10.1007","volume":"83","author":[{"given":"Xiaoying","family":"Zhou","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5843-4675","authenticated-orcid":false,"given":"Yijia","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Zhuang","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Mingyu","family":"Lu","sequence":"additional","affiliation":[]},{"given":"Xiaoxia","family":"Liu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,10,20]]},"reference":[{"key":"17376_CR1","doi-asserted-by":"crossref","unstructured":"Chaudhari S, Mithal V, Polatkan G, Ramanath R (2021) An attentive survey of attention models. Acm Trans Intell Syst Technol (tist) 12(5):1\u201332","DOI":"10.1145\/3465055"},{"issue":"1","key":"17376_CR2","doi-asserted-by":"publisher","first-page":"132","DOI":"10.1111\/coin.12017","volume":"31","author":"F Atefeh","year":"2015","unstructured":"Atefeh F, Khreich W (2015) A survey of techniques for event detection in twitter. Comput Intell 31(1):132\u2013164","journal-title":"Comput Intell"},{"key":"17376_CR3","unstructured":"Athavale V, Bharadwaj S, Pamecha M et\u00a0al. (2016) Towards deep learning in hindi ner: an approach to tackle the labelled data scarcity. arXiv:1610.09756"},{"key":"17376_CR4","doi-asserted-by":"crossref","unstructured":"Cao P, Chen Y, Liu K et\u00a0al (2018) Adversarial transfer learning for chinese named entity recognition with self-attention mechanism. In: Proceedings of the 2018 conference on empirical methods in natural language processing, pp 182\u2013192","DOI":"10.18653\/v1\/D18-1017"},{"key":"17376_CR5","unstructured":"Chinchor N, Robinson P (1997) Muc-7 named entity task definition. In: Proceedings of the 7th conference on message understanding, pp 1\u201321"},{"key":"17376_CR6","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1162\/tacl_a_00104","volume":"4","author":"JP Chiu","year":"2016","unstructured":"Chiu JP, Nichols E (2016) Named entity recognition with bidirectional lstm-cnns. Trans Assoc Comput Linguistics 4:357\u2013370","journal-title":"Trans Assoc Comput Linguistics"},{"key":"17376_CR7","unstructured":"Collobert R, Weston J, Bottou L et\u00a0al (2011) Natural language processing (almost) from scratch. J Mach Learn Res 12(ARTICLE):2493\u20132537"},{"key":"17376_CR8","unstructured":"Cortes C, Lawarence N, Lee D et\u00a0al (2015) Advances in neural information processing systems 28. In: Proceedings of the 29th annual conference on neural information processing systems"},{"key":"17376_CR9","unstructured":"Davis A, Veloso A, Soares A et\u00a0al (2012) Named entity disambiguation in streaming data. In: Proceedings of the 50th annual meeting of the association for computational linguistics (vol 1: Long Papers), pp 815\u2013824"},{"key":"17376_CR10","unstructured":"Devlin J, Chang MW, Lee K et\u00a0al (2018) Bert: pre-training of deep bidirectional transformers for language understanding. arXiv:1810.04805"},{"key":"17376_CR11","doi-asserted-by":"crossref","unstructured":"Fukui A, Park DH, Yang D et\u00a0al (2016) Multimodal compact bilinear pooling for visual question answering and visual grounding. arXiv:1606.01847","DOI":"10.18653\/v1\/D16-1044"},{"key":"17376_CR12","doi-asserted-by":"crossref","unstructured":"Hammerton J (2003) Named entity recognition with long short-term memory. Proceedings of the seventh conference on Natural language learning at HLT-NAACL 2003:172\u2013175","DOI":"10.3115\/1119176.1119202"},{"key":"17376_CR13","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, et\u00a0al. (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"17376_CR14","unstructured":"Huang Z, Xu W, Yu K (2015) Bidirectional lstm-crf models for sequence tagging. arXiv:1508.01991"},{"key":"17376_CR15","doi-asserted-by":"crossref","unstructured":"Ju X, Zhang D, Li J et\u00a0al (2020) Transformer-based label set generation for multi-modal multi-label emotion detection. In: Proceedings of the 28th ACM international conference on multimedia, pp 512\u2013520","DOI":"10.1145\/3394171.3413577"},{"key":"17376_CR16","doi-asserted-by":"crossref","unstructured":"Lample G, Ballesteros M, Subramanian S et\u00a0al (2016) Neural architectures for named entity recognition. arXiv:1603.01360","DOI":"10.18653\/v1\/N16-1030"},{"key":"17376_CR17","doi-asserted-by":"crossref","unstructured":"Liu M, Tu Z, Zhang T et al (2022) Ltp: a new active learning strategy for crf-based named entity recognition. Neural Process Lett 54(3):2433\u20132454","DOI":"10.1007\/s11063-021-10737-x"},{"key":"17376_CR18","doi-asserted-by":"crossref","unstructured":"Lu D, Neves L, Carvalho V et\u00a0al (2018) Visual attention model for name tagging in multimodal social media. In: Proceedings of the 56th annual meeting of the association for computational linguistics (vol 1: Long Papers), pp 1990\u20131999","DOI":"10.18653\/v1\/P18-1185"},{"key":"17376_CR19","unstructured":"Lu J, Batra D, Parikh D et\u00a0al (2019) Vilbert: pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. Adv Neural Inform Process Syst 32"},{"key":"17376_CR20","doi-asserted-by":"crossref","unstructured":"Moon S, Neves L, Carvalho V (2018) Multimodal named entity recognition for short social media posts. arXiv:1802.07862","DOI":"10.18653\/v1\/N18-1078"},{"key":"17376_CR21","doi-asserted-by":"crossref","unstructured":"Ramachandram D, Taylor GW (2017) Deep multimodal learning: a survey on recent advances and trends. IEEE Signal Process Mag 34(6):96\u2013108","DOI":"10.1109\/MSP.2017.2738401"},{"key":"17376_CR22","unstructured":"Santos CNd, Guimaraes V (2015) Boosting named entity recognition with neural character embeddings. arXiv:1505.05008"},{"key":"17376_CR23","unstructured":"Su W, Zhu X, Cao Y et\u00a0al (2019) Vl-bert: pre-training of generic visual-linguistic representations. arXiv:1908.08530"},{"key":"17376_CR24","doi-asserted-by":"crossref","unstructured":"Tan H, Bansal M (2019) Lxmert: learning cross-modality encoder representations from transformers. arXiv:1908.07490","DOI":"10.18653\/v1\/D19-1514"},{"key":"17376_CR25","doi-asserted-by":"crossref","unstructured":"Arshad O, Gallo I, Nawaz S, Calefati A (2019) Aiding intra-text representations with visual context for multimodal named entity recognition. In: Proceeding of the international conference on document analysis and recognition, pp 337\u2013342","DOI":"10.1109\/ICDAR.2019.00061"},{"key":"17376_CR26","doi-asserted-by":"crossref","unstructured":"Ding N, Hu S, Zhao W, Chen Y, Liu Z, Zheng H-T, Sun M (2021) Openprompt: an open-source framework for prompt-learning. arXiv:2111.01998","DOI":"10.18653\/v1\/2022.acl-demo.10"},{"key":"17376_CR27","unstructured":"Goodfellow IJ, Shlens J, Szegedy C (2014) Explaining and harnessing adversarial examples. arXiv:1412.6572"},{"key":"17376_CR28","doi-asserted-by":"crossref","unstructured":"Liu X, Liu K, Li X, Su J, Ge Y, Wang B, Luo J (2020) An iterative multi-source mutual knowledge transfer framework for machine reading comprehension. In: IJCAI, pp 3794\u20133800","DOI":"10.24963\/ijcai.2020\/525"},{"key":"17376_CR29","unstructured":"Nazari M, Oroojlooy A, Snyder L, Tak\u00e1c M (2018) Reinforcement learning for solving the vehicle routing problem. Adv Neural Inform Process Syst 31"},{"key":"17376_CR30","unstructured":"Ritter A, Clark S, Etzioni O (2011) Named entity recognition in tweets: an experimental study. In: Proceedings of the 2011 conference on empirical methods in natural language processing, pp 1524\u20131534"},{"issue":"4","key":"17376_CR31","doi-asserted-by":"publisher","first-page":"e13153","DOI":"10.1111\/exsy.13153","volume":"40","author":"A Sharaff","year":"2023","unstructured":"Sharaff A, Pathak V, Paul SS (2023) Deep learning-based smishing message identification using regular expression feature generation. Expert Syst 40(4):e13153","journal-title":"Expert Syst"},{"key":"17376_CR32","doi-asserted-by":"crossref","unstructured":"Wang X, Ye J, Li Z, Tian J, Jiang Y, Yan M, Zhang J, Xiao Y (2022) CAT-MNER: multimodal named entity recognition with knowledge-refined cross-modal attention. In: 2022 IEEE international conference on multimedia and expo (ICME), IEEE, pp 1\u20136","DOI":"10.1109\/ICME52920.2022.9859972"},{"key":"17376_CR33","doi-asserted-by":"crossref","unstructured":"Zhang D, Wei S, Li S, Wu H, Zhu Q, Zhou G (2021) Multi-modal graph fusion for named entity recognition with targeted visual guidance. In: Proceedings of the AAAI conference on artificial intelligence, pp 14347\u201314355","DOI":"10.1609\/aaai.v35i16.17687"},{"key":"17376_CR34","doi-asserted-by":"crossref","unstructured":"Yu J, Jiang J, Yang L, et\u00a0al. (2020) Improving multimodal named entity recognition via entity span detection with unified multimodal transformer. Association for computational linguistics","DOI":"10.18653\/v1\/2020.acl-main.306"},{"key":"17376_CR35","doi-asserted-by":"crossref","unstructured":"Zadeh A, Chen M, Poria S et\u00a0al (2017) Tensor fusion network for multimodal sentiment analysis. arXiv:1707.07250","DOI":"10.18653\/v1\/D17-1115"},{"key":"17376_CR36","doi-asserted-by":"crossref","unstructured":"Zhang Q, Fu J, Liu X et\u00a0al (2018) Adaptive co-attention network for named entity recognition in tweets. In: Proceedings of the AAAI conference on artificial intelligence","DOI":"10.1609\/aaai.v32i1.11962"},{"key":"17376_CR37","doi-asserted-by":"publisher","first-page":"2520","DOI":"10.1109\/TMM.2020.3013398","volume":"23","author":"C Zheng","year":"2020","unstructured":"Zheng C, Wu Z, Wang T et al (2020) Object-aware multimodal named entity recognition in social media posts with adversarial learning. IEEE Trans Multimedia 23:2520\u20132532","journal-title":"IEEE Trans Multimedia"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-17376-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-023-17376-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-17376-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,29]],"date-time":"2024-04-29T11:40:56Z","timestamp":1714390856000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-023-17376-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,20]]},"references-count":37,"journal-issue":{"issue":"15","published-online":{"date-parts":[[2024,5]]}},"alternative-id":["17376"],"URL":"https:\/\/doi.org\/10.1007\/s11042-023-17376-5","relation":{},"ISSN":["1573-7721"],"issn-type":[{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,10,20]]},"assertion":[{"value":"8 December 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 August 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 October 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 October 2023","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}