{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T13:14:39Z","timestamp":1784207679657,"version":"3.55.0"},"publisher-location":"Singapore","reference-count":23,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819234349","type":"print"},{"value":"9789819234356","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T00:00:00Z","timestamp":1784246400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T00:00:00Z","timestamp":1784246400000},"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":[[2027]]},"DOI":"10.1007\/978-981-92-3435-6_17","type":"book-chapter","created":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T12:30:44Z","timestamp":1784205044000},"page":"195-206","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["RAVE-MNER: Relevance-Aware Visual Evidence for Multimodal Named Entity Recognition"],"prefix":"10.1007","author":[{"given":"Kexin","family":"Jiang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Danni","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoqin","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yue","family":"Qin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,17]]},"reference":[{"key":"17_CR1","unstructured":"Bai, Y., Wang, L., Liu, X., Chi, H., Zhang, G.: VCRMNER: visual cue refinement in multimodal NER using CLIP prompts. In: Bridging Neurons and Symbols for Natural Language Processing and Knowledge Graphs Reasoning@ COLING 2025 61 (2025)"},{"key":"17_CR2","doi-asserted-by":"crossref","unstructured":"Chen, F., Liu, J., Ji, K., Ren, W., Wang, J., Chen, J.: Learning implicit entity-object relations by bidirectional generative alignment for multimodal NER. In: Proceedings of the 31st ACM International Conference on Multimedia. pp. 4555\u20134563 (2023)","DOI":"10.1145\/3581783.3612095"},{"key":"17_CR3","doi-asserted-by":"crossref","unstructured":"Devlin, J., Chang, M.-W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, vol. 1, pp. 4171\u20134186 (2019)","DOI":"10.18653\/v1\/N19-1423"},{"key":"17_CR4","doi-asserted-by":"crossref","unstructured":"Ding, G., Kong, Y., Li, X.: SEPA: an semantic projection alignment framework for multimodal named entity recognition. In: Proceedings of the 2025 International Conference on Multimedia Retrieval. pp. 202\u2013210 (2025)","DOI":"10.1145\/3731715.3733430"},{"key":"17_CR5","doi-asserted-by":"crossref","unstructured":"Huang, S., Xu, B., Li, C., Ye, J., Lin, X.: MNER-MI: a multi-image dataset for multimodal named entity recognition in social media. In: Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pp. 11452\u201311462. ELRA and ICCL (2024)","DOI":"10.63317\/26e4yx7gpgmd"},{"key":"17_CR6","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1007\/s44443-026-00472-5","volume":"38","author":"K Jiang","year":"2026","unstructured":"Jiang, K., Xiao, X., Lu, X., Qin, Y.: SemCap: sentiment-aware semantic captioning for multimodal aspect-based sentiment analysis. J. King Saud Univ. - Comput. Inf. Sci. 38, 81 (2026)","journal-title":"J. King Saud Univ. - Comput. Inf. Sci."},{"key":"17_CR7","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2025.111940","volume":"169","author":"C Jiang","year":"2026","unstructured":"Jiang, C., Wang, Y., Xiong, B.: Dual similarity enhanced hybrid orthogonal fusion for multimodal named entity recognition. Pattern Recogn. 169, 111940 (2026)","journal-title":"Pattern Recogn."},{"key":"17_CR8","doi-asserted-by":"crossref","unstructured":"Liu, P., et al.: Hierarchical aligned multimodal learning for NER on tweet posts. In: Proceedings of the AAAI Conference on Artificial Intelligence. pp. 18680\u201318688. (2024)","DOI":"10.1609\/aaai.v38i17.29831"},{"key":"17_CR9","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, Long Papers, vol. 1, pp. 1990\u20131999 (2018)","DOI":"10.18653\/v1\/P18-1185"},{"key":"17_CR10","unstructured":"Lu, J., Zhang, D., Zhang, J., Zhang, P.: Flat multi-modal interaction transformer for named entity recognition. In: Proceedings of the 29th International Conference on Computational Linguistics, pp. 2055\u20132064. International Committee on Computational Linguistics (2022)"},{"key":"17_CR11","doi-asserted-by":"crossref","unstructured":"Ma, X., Hovy, E.: End-to-end sequence labeling via bi-directional lstm-cnns-crf. In: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, Long Papers, vol. 1, pp. 1064\u20131074. (2016)","DOI":"10.18653\/v1\/P16-1101"},{"key":"17_CR12","doi-asserted-by":"publisher","unstructured":"Moon, S., Neves, L., Carvalho, V.: Multimodal named entity recognition for short social media posts. In: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), pp. 852\u2013860. Association for Computational Linguistics (2018). https:\/\/doi.org\/10.18653\/v1\/N18-1078","DOI":"10.18653\/v1\/N18-1078"},{"key":"17_CR13","doi-asserted-by":"crossref","unstructured":"Wang, X., et al.: ITA: image-text alignments for multi-modal named entity recognition. In: Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 3176\u20133189. Association for Computational Linguistics (2022)","DOI":"10.18653\/v1\/2022.naacl-main.232"},{"key":"17_CR14","doi-asserted-by":"crossref","unstructured":"Wei, P., Ouyang, H., Hu, Q., Zeng, B., Feng, G., Wen, Q.: Vec-mner: hybrid transformer with visual-enhanced cross-modal multi-level interaction for multimodal ner. In: Proceedings of the 2024 International Conference on Multimedia Retrieval, pp. 469\u2013477. (2024)","DOI":"10.1145\/3652583.3658097"},{"key":"17_CR15","unstructured":"Xu, B., et al.: Enhancing multimodal named entity recognition through adaptive mixup image augmentation. In: Proceedings of the 31st International Conference on Computational Linguistics. pp. 1802\u20131812. (2025a)"},{"key":"17_CR16","doi-asserted-by":"crossref","unstructured":"Xu, B., Wei, J., Wang, H., Du, M., Song, H., Xiao, Y.: Bridging the unseen gap: label-enhanced information bottleneck distillation for multimodal named entity recognition. In: Proceedings of the 33rd ACM International Conference on Multimedia, pp. 1500\u20131509. (2025b)","DOI":"10.1145\/3746027.3755210"},{"key":"17_CR17","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, pp. 3342\u20133352. Association for Computational Linguistics (2020)","DOI":"10.18653\/v1\/2020.acl-main.306"},{"key":"17_CR18","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 AAAI Conference on Artificial Intelligence (2018)","DOI":"10.1609\/aaai.v32i1.11962"},{"key":"17_CR19","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s40747-025-02139-6","volume":"12","author":"Q Zhang","year":"2026","unstructured":"Zhang, Q., Song, Z., Wang, D., Cai, Y., Bi, M., Zuo, M.: Named entity recognition and coreference resolution using prompt-based generative multimodal. Complex Intell. Syst. 12, 1\u201318 (2026)","journal-title":"Complex Intell. Syst."},{"key":"17_CR20","doi-asserted-by":"crossref","unstructured":"Zhang, X., Yuan, J., Li, L., Liu, J.: Reducing the bias of visual objects in multimodal named entity recognition, in: Proceedings of the Sixteenth ACM International Conference on Web Search and Data Mining. pp. 958\u2013966 (2023)","DOI":"10.1145\/3539597.3570485"},{"key":"17_CR21","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Mai, W., Xiong, H., Wu, C., Xue, Y.: A token-wise graph-based framework for multimodal named entity recognition. In: 2023 IEEE International Conference on Multimedia and Expo (ICME), pp. 2153\u20132158. IEEE (2023)","DOI":"10.1109\/ICME55011.2023.00368"},{"key":"17_CR22","unstructured":"Zhao, J., Huang, S., Lin, X.: A graph interaction framework on relevance for multimodal named entity recognition with multiple images. In: Proceedings of the 31st International Conference on Computational Linguistics, pp. 1237\u20131246 (2025)"},{"key":"17_CR23","doi-asserted-by":"publisher","first-page":"45047","DOI":"10.1007\/s11042-023-17376-5","volume":"83","author":"X Zhou","year":"2024","unstructured":"Zhou, X., Zhang, Y., Wang, Z., Lu, M., Liu, X.: MAFN: multi-level attention fusion network for multimodal named entity recognition. Multimed. Tools Appl. 83, 45047\u201345058 (2024)","journal-title":"Multimed. Tools Appl."}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-92-3435-6_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T12:30:50Z","timestamp":1784205050000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-3435-6_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,17]]},"ISBN":["9789819234349","9789819234356"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-3435-6_17","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,17]]},"assertion":[{"value":"17 July 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Toronto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Canada","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 July 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2026","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":"icic2026a","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/2026\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}