{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T06:16:34Z","timestamp":1783318594281,"version":"3.54.6"},"reference-count":59,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T00:00:00Z","timestamp":1776988800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T00:00:00Z","timestamp":1776988800000},"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":["Int. J. Mach. Learn. & Cyber."],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1007\/s13042-026-03062-z","type":"journal-article","created":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T08:33:48Z","timestamp":1777019628000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Shared-private vision-to-text connector for grounded multimodal named entity recognition with synergistic global\u2013local alignment"],"prefix":"10.1007","volume":"17","author":[{"given":"Zihao","family":"Zheng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chen","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dandan","family":"Tu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ming","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bing","family":"Qin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,4,24]]},"reference":[{"key":"3062_CR1","doi-asserted-by":"crossref","unstructured":"Yu J, Jiang J, Yang L, Xia R (2020) Improving multimodal named entity recognition via entity span detection with unified multimodal transformer. In: Jurafsky D, Chai J, Schluter N, Tetreault J (eds) Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp 3342\u20133352. Association for Computational Linguistics, Online. https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.306. https:\/\/aclanthology.org\/2020.acl-main.306","DOI":"10.18653\/v1\/2020.acl-main.306"},{"key":"3062_CR2","doi-asserted-by":"crossref","unstructured":"Zheng C, Wu Z, Feng J, Fu Z, Cai Y (2021) Mnre: a challenge multimodal dataset for neural relation extraction with visual evidence in social media posts. In: Proc. of ICME","DOI":"10.1109\/ICME51207.2021.9428274"},{"key":"3062_CR3","doi-asserted-by":"crossref","unstructured":"Wang X, Cai J, Jiang Y, Xie P, Tu K, Lu W (2022) Named entity and relation extraction with multi-modal retrieval. In: Goldberg Y, Kozareva Z, Zhang Y (eds) Findings of the Association for Computational Linguistics: EMNLP 2022, pp 5925\u20135936. Association for Computational Linguistics, Abu Dhabi, United Arab Emirates. https:\/\/doi.org\/10.18653\/v1\/2022.findings-emnlp.437. https:\/\/aclanthology.org\/2022.findings-emnlp.437","DOI":"10.18653\/v1\/2022.findings-emnlp.437"},{"key":"3062_CR4","doi-asserted-by":"publisher","first-page":"561","DOI":"10.1109\/TCSVT.2023.3284474","volume":"34","author":"J Feng","year":"2024","unstructured":"Feng J, Wang G, Zheng C, Cai Y, Fu Z, Wang Y, Wei X, Li Q (2024) Towards bridged vision and language: learning cross-modal knowledge representation for relation extraction. IEEE Trans Circ Syst Video Technol (TCSVT) 34:561\u2013575","journal-title":"IEEE Trans Circ Syst Video Technol (TCSVT)"},{"key":"3062_CR5","doi-asserted-by":"publisher","first-page":"3199","DOI":"10.1109\/TCSVT.2022.3231437","volume":"33","author":"Z Fu","year":"2023","unstructured":"Fu Z, Zheng C, Feng J, Cai Y, Wei X, Wang Y, Li Q (2023) Drake: Deep pair-wise relation alignment for knowledge-enhanced multimodal scene graph generation in social media posts. IEEE Trans Circ Syst Video Technol (TCSVT) (TCSVT) 33:3199\u20133213","journal-title":"IEEE Trans Circ Syst Video Technol (TCSVT) (TCSVT)"},{"issue":"9","key":"3062_CR6","doi-asserted-by":"publisher","first-page":"8983","DOI":"10.1109\/TKDE.2022.3220625","volume":"35","author":"Q Fang","year":"2022","unstructured":"Fang Q, Zhang X, Hu J, Wu X, Xu C (2022) Contrastive multi-modal knowledge graph representation learning. IEEE Trans Knowl Data Eng 35(9):8983\u20138996","journal-title":"IEEE Trans Knowl Data Eng"},{"issue":"11","key":"3062_CR7","doi-asserted-by":"publisher","first-page":"6628","DOI":"10.1109\/TKDE.2024.3384270","volume":"36","author":"N Xu","year":"2024","unstructured":"Xu N, Gao Y, Liu A-A, Tian H, Zhang Y (2024) Multi-modal validation and domain interaction learning for knowledge-based visual question answering. IEEE Trans Knowl Data Eng 36(11):6628\u20136640","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"3062_CR8","doi-asserted-by":"crossref","unstructured":"Wang J, Li Z, Yu J, Yang L, Xia R (2023) Fine-grained multimodal named entity recognition and grounding with a generative framework. In: ACM Multimedia","DOI":"10.1145\/3581783.3612322"},{"key":"3062_CR9","doi-asserted-by":"crossref","unstructured":"Yu J, Li Z, Wang J, Xia R (2023) Grounded multimodal named entity recognition on social media. In: Rogers A, Boyd-Graber J, Okazaki N (eds) Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp 9141\u20139154. Association for Computational Linguistics, Toronto, Canada. https:\/\/doi.org\/10.18653\/v1\/2023.acl-long.508. https:\/\/aclanthology.org\/2023.acl-long.508","DOI":"10.18653\/v1\/2023.acl-long.508"},{"key":"3062_CR10","doi-asserted-by":"crossref","unstructured":"He L, Wang H, Cao Y, Wu Z, Zhang J, Dai X (2023) More: a multimodal object-entity relation extraction dataset with a benchmark evaluation. In: Proc. of ACM MM","DOI":"10.1145\/3581783.3612209"},{"issue":"2","key":"3062_CR11","doi-asserted-by":"publisher","first-page":"715","DOI":"10.1109\/TKDE.2022.3224228","volume":"36","author":"X Zhu","year":"2022","unstructured":"Zhu X, Li Z, Wang X, Jiang X, Sun P, Wang X, Xiao Y, Yuan NJ (2022) Multi-modal knowledge graph construction and application: a survey. IEEE Trans Knowl Data Eng 36(2):715\u2013735","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"3062_CR12","doi-asserted-by":"publisher","unstructured":"Ding Y, Yu J, Liu B, Hu Y, Cui M, Wu Q (2022) Mukea: multimodal knowledge extraction and accumulation for knowledge-based visual question answering. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, LA, USA, June 18-24, 2022, pp 5079\u20135088. IEEE, New Orleans. https:\/\/doi.org\/10.1109\/CVPR52688.2022.00503","DOI":"10.1109\/CVPR52688.2022.00503"},{"key":"3062_CR13","doi-asserted-by":"publisher","unstructured":"Sun R, Cao X, Zhao Y, Wan J, Zhou K, Zhang F, Wang Z, Zheng K (2020) Multi-modal knowledge graphs for recommender systems. In: d\u2019Aquin M, Dietze S, Hauff C, Curry E, Cudr\u00e9-Mauroux P. (eds) CIKM \u201920: The 29th ACM International Conference on Information and Knowledge Management, Virtual Event, October 19-23, 2020, pp 1405\u20131414. ACM, Ireland. https:\/\/doi.org\/10.1145\/3340531.3411947","DOI":"10.1145\/3340531.3411947"},{"issue":"11","key":"3062_CR14","doi-asserted-by":"publisher","first-page":"6962","DOI":"10.1109\/TKDE.2024.3399746","volume":"36","author":"Y Song","year":"2024","unstructured":"Song Y, Sun P, Liu H, Li Z, Song W, Xiao Y, Zhou X (2024) Scene-driven multimodal knowledge graph construction for embodied ai. IEEE Trans Knowl Data Eng 36(11):6962\u20136976","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"3062_CR15","doi-asserted-by":"crossref","unstructured":"Agrawal G, Kumarage T, Alghamdi Z, Liu H (2024) Can knowledge graphs reduce hallucinations in LLMs? : A survey. In: Duh K, Gomez H, Bethard S (eds) Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pp 3947\u20133960. Association for Computational Linguistics, Mexico City, Mexico. https:\/\/aclanthology.org\/2024.naacl-long.219","DOI":"10.18653\/v1\/2024.naacl-long.219"},{"key":"3062_CR16","unstructured":"Hyung Won\u00a0C (2022) Scaling instruction-finetuned language models"},{"key":"3062_CR17","doi-asserted-by":"crossref","unstructured":"Bao X, Tian M, Wang L, Zha Z, Qin B (2024) Contrastive pre-training with multi-level alignment for grounded multimodal named entity recognition. In: Proceedings of the 2024 International Conference on Multimedia Retrieval","DOI":"10.1145\/3652583.3658011"},{"key":"3062_CR18","doi-asserted-by":"crossref","unstructured":"Luo W, Xia Y, Tianshu S, Li S (2024) Shapley value-based contrastive alignment for multimodal information extraction","DOI":"10.1145\/3664647.3681367"},{"key":"3062_CR19","doi-asserted-by":"publisher","unstructured":"Wei Y, Yuan S, Zhou H, Wang L, Yan Z, Yang R, Chen M (2024) G2SAM: graph-based global semantic awareness method for multimodal sarcasm detection. In: Wooldridge MJ, Dy JG, Natarajan S (eds) Thirty-Eighth AAAI Conference on Artificial Intelligence AAAI 2024, Thirty-Sixth Conference on Innovative Applications of Artificial Intelligence, IAAI 2024, Fourteenth Symposium on Educational Advances in Artificial Intelligence, EAAI 2014, February 20-27, 2024, Canada, pp 9151\u20139159. AAAI Press, Vancouver. https:\/\/doi.org\/10.1609\/AAAI.V38I8.28766","DOI":"10.1609\/AAAI.V38I8.28766"},{"key":"3062_CR20","doi-asserted-by":"crossref","unstructured":"Zhang Q, Fu J, Liu X, Huang X (2018) Adaptive co-attention network for named entity recognition in tweets. In: McIlraith SA, Weinberger KQ (eds) Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, (AAAI-18), the 30th Innovative Applications of Artificial Intelligence (IAAI-18), and the 8th AAAI Symposium on Educational Advances in Artificial Intelligence (EAAI-18), Louisiana, USA, February 2-7, 2018, pp 5674\u20135681. AAAI Press, New Orleans. https:\/\/www.aaai.org\/ocs\/index.php\/AAAI\/AAAI18\/paper\/view\/16432","DOI":"10.1609\/aaai.v32i1.11962"},{"key":"3062_CR21","doi-asserted-by":"crossref","unstructured":"Moon S, Neves L, Carvalho V (2018) Multimodal named entity recognition for short social media posts. In: Walker M, Ji H, Stent A (eds) 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, New Orleans, Louisiana. https:\/\/doi.org\/10.18653\/v1\/N18-1078. https:\/\/aclanthology.org\/N18-1078","DOI":"10.18653\/v1\/N18-1078"},{"issue":"1","key":"3062_CR22","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2023.103546","volume":"61","author":"P Liu","year":"2024","unstructured":"Liu P, Wang G, Li H, Liu J, Ren Y, Zhu H, Sun L (2024) Multi-granularity cross-modal representation learning for named entity recognition on social media. Inform Process Manag 61(1):103546. https:\/\/doi.org\/10.1016\/j.ipm.2023.103546","journal-title":"Inform Process Manag"},{"key":"3062_CR23","doi-asserted-by":"crossref","unstructured":"Chen X, Zhang N, Li L, Yao Y, Deng S, Tan C, Huang F, Si L, Chen H (2022) Good visual guidance make a better extractor: hierarchical visual prefix for multimodal entity and relation extraction. In: Carpuat M, Marneffe M-C, Meza\u00a0Ruiz IV (eds) Findings of the Association for Computational Linguistics: NAACL 2022, pp. 1607\u20131618. Association for Computational Linguistics, Seattle, United States. https:\/\/doi.org\/10.18653\/v1\/2022.findings-naacl.121. https:\/\/aclanthology.org\/2022.findings-naacl.121","DOI":"10.18653\/v1\/2022.findings-naacl.121"},{"key":"3062_CR24","doi-asserted-by":"crossref","unstructured":"Zheng Z, He T, Liu M, Wang Z, Fu R, Qin B (2024) Relational graph-bridged image-text interaction: A novel method for multi-modal relation extraction. In: Proc. of ICASSP","DOI":"10.1109\/ICASSP48485.2024.10448507"},{"key":"3062_CR25","doi-asserted-by":"crossref","unstructured":"Wang X, Meng B, Chen H, Meng Y, Lv K, Zhu W (2023) TIVA-KG: a multimodal knowledge graph with text, image, video and audio. In: ACM Multimedia","DOI":"10.1145\/3581783.3612266"},{"key":"3062_CR26","doi-asserted-by":"crossref","unstructured":"Chen Z, Zhang Y, Fang Y, Geng Y, Guo L, Chen X, Li Q, Zhang W, Chen J, Zhu Y, Li J, Liu X, Pan JZ, Zhang N, Chen H (2024) Knowledge graphs meet multi-modal learning: a comprehensive survey","DOI":"10.2139\/ssrn.5044404"},{"issue":"1","key":"3062_CR27","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2024.103875","volume":"62","author":"X He","year":"2025","unstructured":"He X, Li S, Zhang Y, Li B, Xu S, Zhou Y (2025) The more quality information the better: hierarchical generation of multi-evidence alignment and fusion model for multimodal entity and relation extraction. Inform Process Manag 62(1):103875. https:\/\/doi.org\/10.1016\/j.ipm.2024.103875","journal-title":"Inform Process Manag"},{"key":"3062_CR28","doi-asserted-by":"crossref","unstructured":"Tang J, Wang Z, Gong Z, Yu J, Zhu X, Yin J (2024) Multi-grained query-guided set prediction network for grounded multimodal named entity recognition","DOI":"10.1609\/aaai.v39i24.34711"},{"key":"3062_CR29","doi-asserted-by":"publisher","unstructured":"Li Z, Yu J, Yang J, Wang W, Yang L, Xia R (2024) Generative multimodal data augmentation for low-resource multimodal named entity recognition. In: Proceedings of the 32nd ACM International Conference on Multimedia. MM \u201924, pp 7336\u20137345. Association for Computing Machinery, New York, NY, USA. https:\/\/doi.org\/10.1145\/3664647.3681598","DOI":"10.1145\/3664647.3681598"},{"key":"3062_CR30","doi-asserted-by":"crossref","unstructured":"Tang J, Wang S, Wang Z, Yu J, Yin J (2025) Refineg: synergizing small supervised models and llms for low-resource grounded multimodal ner. arXiv preprint arXiv:2509.10975","DOI":"10.1007\/978-981-95-8525-0_22"},{"issue":"3","key":"3062_CR31","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2023.103264","volume":"60","author":"Q Zhao","year":"2023","unstructured":"Zhao Q, Gao T, Guo N (2023) Tsvfn: two-stage visual fusion network for multimodal relation extraction. Inform Process Manag 60(3):103264. https:\/\/doi.org\/10.1016\/j.ipm.2023.103264","journal-title":"Inform Process Manag"},{"key":"3062_CR32","doi-asserted-by":"publisher","unstructured":"Li D, Li J, Li H, Niebles JC, Hoi SCH (2022) Align and prompt: video-and-language pre-training with entity prompts. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, LA, USA, June 18-24, 2022, pp 4943\u20134953. IEEE, New Orleans. https:\/\/doi.org\/10.1109\/CVPR52688.2022.00490","DOI":"10.1109\/CVPR52688.2022.00490"},{"issue":"3","key":"3062_CR33","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2024.103697","volume":"61","author":"Z Lin","year":"2024","unstructured":"Lin Z, Xie J, Li Q (2024) Multi-modal news event detection with external knowledge. Inform Process Manag 61(3):103697. https:\/\/doi.org\/10.1016\/j.ipm.2024.103697","journal-title":"Inform Process Manag"},{"key":"3062_CR34","doi-asserted-by":"crossref","unstructured":"Peng K, Fu J, Yang K, Wen D, Chen Y, Liu R, Zheng J, Zhang J, Sarfraz MS, Stiefelhagen R, et al (2024) Referring atomic video action recognition. In: European Conference on Computer Vision, pp 166\u2013185. Springer","DOI":"10.1007\/978-3-031-72655-2_10"},{"key":"3062_CR35","doi-asserted-by":"crossref","unstructured":"Wu D, Han W, Wang T, Dong X, Zhang X, Shen J (2023) Referring multi-object tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 14633\u201314642","DOI":"10.1109\/CVPR52729.2023.01406"},{"key":"3062_CR36","unstructured":"Peng K, Huang J, Huang X, Wen D, Zheng J, Chen Y, Yang K, Wu J, Hao C, Stiefelhagen R (2025) Hopadiff: holistic-partial aware fourier conditioned diffusion for referring human action segmentation in multi-person scenarios. arXiv preprint arXiv:2506.09650"},{"key":"3062_CR37","doi-asserted-by":"crossref","unstructured":"Peng K, Wen D, Fu J, Wu J, Yang K, Zheng J, Liu R, Chen Y, Fu Y, Paudel DP, et al (2025) Refatomnet++: advancing referring atomic video action recognition using semantic retrieval based multi-trajectory mamba. arXiv preprint arXiv:2510.16444","DOI":"10.1007\/978-3-031-72655-2_10"},{"key":"3062_CR38","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2025.114334","volume":"329","author":"G Yue","year":"2025","unstructured":"Yue G, Jiao G, Wang F (2025) Indrect: intra-domain dual reconstruction for cross-domain transfer in camouflaged object detection. Knowl-Based Syst 329:114334. https:\/\/doi.org\/10.1016\/j.knosys.2025.114334","journal-title":"Knowl-Based Syst"},{"key":"3062_CR39","doi-asserted-by":"publisher","unstructured":"Yue G, Jiao G, Xiang J (2025) Semi-supervised iterative learning network for camouflaged object detection. In: Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). https:\/\/doi.org\/10.1109\/ICASSP49660.2025.10890224","DOI":"10.1109\/ICASSP49660.2025.10890224"},{"issue":"6","key":"3062_CR40","doi-asserted-by":"publisher","first-page":"3957","DOI":"10.1007\/s00371-024-03640-8","volume":"41","author":"G Yue","year":"2025","unstructured":"Yue G, Jiao G, Li C, Xiang J (2025) When cnn meet with vit: decision-level feature fusion for camouflaged object detection. Vis Comput 41(6):3957\u20133972. https:\/\/doi.org\/10.1007\/s00371-024-03640-8","journal-title":"Vis Comput"},{"key":"3062_CR41","unstructured":"Radford A, Kim JW, Hallacy C, Ramesh A, Goh G, Agarwal S, Sastry G, Askell A, Mishkin P, Clark J, Krueger G, Sutskever I (2021) Learning transferable visual models from natural language supervision. In: Meila M, Zhang T (eds) Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18-24 July 2021, Virtual Event. In: Proceedings of Machine Learning Research, vol 139, pp 8748\u20138763. PMLR, Online. http:\/\/proceedings.mlr.press\/v139\/radford21a.html"},{"key":"3062_CR42","doi-asserted-by":"crossref","unstructured":"Xu B, Huang S, Du M, Wang H, Song H, Xiao Y, Lin X (2023) A unified visual prompt tuning framework with mixture-of-experts for multimodal information extraction. In: Proc. of DASFAA","DOI":"10.1007\/978-3-031-30675-4_40"},{"key":"3062_CR43","unstructured":"Li J, Li D, Savarese S, Hoi SCH (2023) BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models. In: Krause A, Brunskill E, Cho K, Engelhardt B, Sabato S, Scarlett J (eds.) International Conference on Machine Learning, ICML 2023, 23-29 July 2023, Hawaii, USA. In: Proceedings of Machine Learning Research, vol 202, pp 19730\u201319742. PMLR, Honolulu. https:\/\/proceedings.mlr.press\/v202\/li23q.html"},{"key":"3062_CR44","doi-asserted-by":"publisher","unstructured":"Liu P, Li H, Ren Y, Liu J, Si S, Zhu H, Sun L (2024) Hierarchical aligned multimodal learning for NER on tweet posts. In: Wooldridge MJ, Dy JG, Natarajan S (eds) Thirty-Eighth AAAI Conference on Artificial Intelligence, AAAI 2024, Thirty-Sixth Conference on Innovative Applications of Artificial Intelligence, IAAI 2024, Fourteenth Symposium on Educational Advances in Artificial Intelligence, EAAI 2014, February 20-27, 2024, Canada, pp. 18680\u201318688. AAAI Press, Vancouver. https:\/\/doi.org\/10.1609\/AAAI.V38I17.29831","DOI":"10.1609\/AAAI.V38I17.29831"},{"key":"3062_CR45","unstructured":"Velickovic P, Cucurull G, Casanova A, Romero A, Li\u00f2 P, Bengio Y (2018) Graph attention networks. In: 6th International Conference on Learning Representations, ICLR 2018, Vancouver, BC, Canada, April 30 - May 3, 2018, Conference Track Proceedings. OpenReview.net, Online. https:\/\/openreview.net\/forum?id=rJXMpikCZ"},{"key":"3062_CR46","doi-asserted-by":"crossref","unstructured":"Wang Q, Tan H, Shen S, Mahoney M, Yao Z (2020) MAF: multimodal alignment framework for weakly-supervised phrase grounding. In: Webber B, Cohn T, He Y, Liu Y (eds) Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 2030\u20132038. Association for Computational Linguistics, Online. https:\/\/doi.org\/10.18653\/v1\/2020.emnlp-main.159 . https:\/\/aclanthology.org\/2020.emnlp-main.159","DOI":"10.18653\/v1\/2020.emnlp-main.159"},{"key":"3062_CR47","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: ICME","DOI":"10.1109\/ICME52920.2022.9859972"},{"key":"3062_CR48","doi-asserted-by":"crossref","unstructured":"Zhang Q, Fu J, Liu X, Huang X (2018) Adaptive co-attention network for named entity recognition in tweets. In: McIlraith SA, Weinberger KQ (eds) Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, (AAAI-18), the 30th Innovaive Applications of Artificial Intelligence (IAAI-18), and the 8th AAI Symposium on Educational Advances in Artificial Intelligence (EAAI-18), New Orleans, Louisiana, USA, February 2-7, 2018, pp. 5674\u20135681. AAAI Press, New Orleans. https:\/\/www.aaai.org\/ocs\/index.php\/AAAI\/AAAI18\/paper\/view\/16432","DOI":"10.1609\/aaai.v32i1.11962"},{"key":"3062_CR49","doi-asserted-by":"crossref","unstructured":"Lu D, Neves L, Carvalho V, Zhang N, Ji H (2018) Visual attention model for name tagging in multimodal social media. In: Gurevych I, Miyao Y (eds) Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 1990\u20131999. Association for Computational Linguistics, Melbourne, Australia. https:\/\/doi.org\/10.18653\/v1\/P18-1185. https:\/\/aclanthology.org\/P18-1185","DOI":"10.18653\/v1\/P18-1185"},{"key":"3062_CR50","doi-asserted-by":"crossref","unstructured":"Yang L, Kang B, Huang Z, Xu X, Feng J, Zhao H (2024) Depth anything: unleashing the power of large-scale unlabeled data. In: CVPR","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"3062_CR51","doi-asserted-by":"crossref","unstructured":"Ansel J, Yang e.a (2024) PyTorch 2: faster machine learning through dynamic python bytecode transformation and graph compilation. In: Proc. of ASPLOS","DOI":"10.1145\/3620665.3640366"},{"key":"3062_CR52","unstructured":"Loshchilov I, Hutter F (2019) Decoupled weight decay regularization. In: 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, May 6-9, 2019. OpenReview.net, Online. https:\/\/openreview.net\/forum?id=Bkg6RiCqY7"},{"key":"3062_CR53","unstructured":"Lu J, Batra D, Parikh D, Lee S (2019) Vilbert: pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. Adv Neural Inform Process syst 32"},{"key":"3062_CR54","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: Thirty-Fifth AAAI Conference on Artificial Intelligence, AAAI 2021, Thirty-Third Conference on Innovative Applications of Artificial Intelligence, IAAI 2021, The Eleventh Symposium on Educational Advances in Artificial Intelligence, EAAI 2021, Virtual Event, February 2-9, 2021, pp 14347\u201314355. AAAI Press, Online. https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/17687","DOI":"10.1609\/aaai.v35i16.17687"},{"key":"3062_CR55","doi-asserted-by":"crossref","unstructured":"Wang X, Gui M, Jiang Y, Jia Z, Bach N, Wang T, Huang Z, Tu K (2022) ITA: image-text alignments for multi-modal named entity recognition. In: Carpuat M, Marneffe M-C, Meza\u00a0Ruiz IV (eds) 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, Seattle, United States. https:\/\/doi.org\/10.18653\/v1\/2022.naacl-main.232 . https:\/\/aclanthology.org\/2022.naacl-main.232","DOI":"10.18653\/v1\/2022.naacl-main.232"},{"key":"3062_CR56","doi-asserted-by":"crossref","unstructured":"Liu S, Zhang Z, Jiang H, Guan X (2025) Dlgp: grounded multimodal named entity recognition based on dynamic learnable graph prompt. In: Fourth International Conference on Electronics Technology and Artificial Intelligence (ETAI 2025), vol 13692, pp 76\u201381. SPIE","DOI":"10.1117\/12.3068319"},{"key":"3062_CR57","unstructured":"Bai S, Chen K, Liu X, Wang J, Ge W, Song S, Dang K, Wang P, Wang S, Tang J, et al (2025) Qwen2. 5-vl technical report. arXiv preprint arXiv:2502.13923"},{"key":"3062_CR58","unstructured":"Hurst A, Lerer A, Goucher AP, Perelman A, Ramesh A, Clark A, Ostrow A, Welihinda A, Hayes A, Radford A, et al (2024) Gpt-4o system card. arXiv preprint arXiv:2410.21276"},{"key":"3062_CR59","doi-asserted-by":"crossref","unstructured":"Li J, Li H, Sun D, Wang J, Zhang W, Wang Z, Pan G (2024) Llms as bridges: reformulating grounded multimodal named entity recognition. In: Proc. of ACL Findings","DOI":"10.18653\/v1\/2024.findings-acl.76"}],"container-title":["International Journal of Machine Learning and Cybernetics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-026-03062-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s13042-026-03062-z","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-026-03062-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T05:57:16Z","timestamp":1783317436000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s13042-026-03062-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,24]]},"references-count":59,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2026,6]]}},"alternative-id":["3062"],"URL":"https:\/\/doi.org\/10.1007\/s13042-026-03062-z","relation":{},"ISSN":["1868-8071","1868-808X"],"issn-type":[{"value":"1868-8071","type":"print"},{"value":"1868-808X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,24]]},"assertion":[{"value":"19 May 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 March 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 April 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"266"}}