{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T22:08:56Z","timestamp":1790201336392,"version":"4.1.0"},"reference-count":59,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62206267"],"award-info":[{"award-number":["62206267"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2024M763867"],"award-info":[{"award-number":["2024M763867"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neurocomputing"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.neucom.2026.134606","type":"journal-article","created":{"date-parts":[[2026,7,27]],"date-time":"2026-07-27T16:19:46Z","timestamp":1785169186000},"page":"134606","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Multi-grained dynamic feature resorter with curriculum bootstrapping for multimodal entity and relation extraction"],"prefix":"10.1016","volume":"702","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-5752-2132","authenticated-orcid":false,"given":"Wei","family":"Jia","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-7520-7799","authenticated-orcid":false,"given":"Zhicong","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8833-4862","authenticated-orcid":false,"given":"Li","family":"Jin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Linhao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5830-0802","authenticated-orcid":false,"given":"Kaiwen","family":"Wei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0592-171X","authenticated-orcid":false,"given":"Qing","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liang","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanfeng","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neucom.2026.134606_bib0005","series-title":"Proceedings of the 26th Annual International Conference on Machine Learning, ICML 2009","first-page":"41","article-title":"Curriculum learning","author":"Bengio","year":"2009"},{"key":"10.1016\/j.neucom.2026.134606_bib0010","author":"Chen"},{"key":"10.1016\/j.neucom.2026.134606_bib0015","series-title":"SIGIR \u201922: The 45th International ACM SIGIR Conference on Research and Development in Information Retrieval","first-page":"904","article-title":"Hybrid transformer with multi-level fusion for multimodal knowledge graph completion","author":"Chen","year":"2022"},{"key":"10.1016\/j.neucom.2026.134606_bib0020","series-title":"Findings of the Association for Computational Linguistics: NAACL 2022, Seattle, WA, United States, July 10\u201315, 2022","first-page":"1607","article-title":"Good visual guidance make a better extractor: hierarchical visual prefix for multimodal entity and relation extraction","author":"Chen","year":"2022"},{"key":"10.1016\/j.neucom.2026.134606_bib0025","author":"Chung"},{"key":"10.1016\/j.neucom.2026.134606_bib0030","series-title":"Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10\u201316, 2023","article-title":"InstructBLIP: towards general-purpose vision-language models with instruction tuning","author":"Dai","year":"2023"},{"key":"10.1016\/j.neucom.2026.134606_bib0035","series-title":"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2023","first-page":"1862","article-title":"HuCurl: human-induced curriculum discovery","author":"Elgaar","year":"2023"},{"key":"10.1016\/j.neucom.2026.134606_bib0040","doi-asserted-by":"crossref","first-page":"71","DOI":"10.1016\/0010-0277(93)90058-4","article-title":"Learning and development in neural networks: the importance of starting small","volume":"48","author":"Elman","year":"1993","journal-title":"Cognition"},{"key":"10.1016\/j.neucom.2026.134606_bib0045","series-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023, Vancouver, BC, Canada, June 17\u201324, 2023","first-page":"19358","article-title":"EVA: exploring the limits of masked visual representation learning at scale","author":"Fang","year":"2023"},{"key":"10.1016\/j.neucom.2026.134606_bib0050","first-page":"111","article-title":"Why curriculum learning & self-paced learning work in big\/noisy data: a theoretical perspective","volume":"1","author":"Gong","year":"2015","journal-title":"Big Data Inf. Anal."},{"key":"10.1016\/j.neucom.2026.134606_bib0055","series-title":"Supervised Sequence Labelling with Recurrent Neural Networks","first-page":"37","article-title":"Long short-term memory","author":"Graves","year":"2012"},{"key":"10.1016\/j.neucom.2026.134606_bib0060","series-title":"Proceedings of the 32nd ACM International Conference on Information and Knowledge Management, CIKM 2023, Birmingham, United Kingdom, October 21\u201325, 2023","first-page":"639","article-title":"MGICL: multi-grained interaction contrastive learning for multimodal named entity recognition","author":"Guo","year":"2023"},{"key":"10.1016\/j.neucom.2026.134606_bib0065","series-title":"Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL 2022","first-page":"1450","article-title":"Go back in time: generating flashbacks in stories with event temporal prompts","author":"Han","year":"2022"},{"key":"10.1016\/j.neucom.2026.134606_bib0070","series-title":"2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"10.1016\/j.neucom.2026.134606_bib0075","series-title":"spaCy: Industrial-Strength Natural Language Processing in Python","author":"Honnibal","year":"2020"},{"key":"10.1016\/j.neucom.2026.134606_bib0080","series-title":"The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25\u201329, 2022","article-title":"LoRA: low-rank adaptation of large language models","author":"Hu","year":"2022"},{"key":"10.1016\/j.neucom.2026.134606_bib0085","doi-asserted-by":"crossref","DOI":"10.1016\/j.ipm.2024.104033","article-title":"A knowledge-enhanced network for joint multimodal entity-relation extraction","volume":"62","author":"Huang","year":"2025","journal-title":"Inf. Process. Manag."},{"key":"10.1016\/j.neucom.2026.134606_bib0090","series-title":"Proceedings of the 33rd ACM International Conference on Multimedia","first-page":"4349","article-title":"U-MERE: unconstrained multimodal entity and relation extraction with collaborative modeling and order-sensitive optimization","author":"Jia","year":"2025"},{"key":"10.1016\/j.neucom.2026.134606_bib0095","series-title":"Advances in Neural Information Processing Systems 25: 26th Annual Conference on Neural Information Processing Systems 2012. Proceedings of a Meeting Held December 3\u20136, 2012, Lake Tahoe, Nevada, United States","first-page":"1106","article-title":"ImageNet classification with deep convolutional neural networks","author":"Krizhevsky","year":"2012"},{"key":"10.1016\/j.neucom.2026.134606_bib0100","series-title":"Advances in Neural Information Processing Systems 23: 24th Annual Conference on Neural Information Processing Systems 2010. Proceedings of a Meeting Held 6\u20139 December 2010","first-page":"1189","article-title":"Self-paced learning for latent variable models","author":"Kumar","year":"2010"},{"key":"10.1016\/j.neucom.2026.134606_bib0105","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":"10.1016\/j.neucom.2026.134606_bib0110","series-title":"Thirty-Seventh AAAI Conference on Artificial Intelligence, AAAI 2023","first-page":"16254","article-title":"On analyzing the role of image for visual-enhanced relation extraction (student abstract)","author":"Li","year":"2023"},{"key":"10.1016\/j.neucom.2026.134606_bib0115","series-title":"Findings of the Association for Computational Linguistics: ACL 2023","first-page":"8982","article-title":"Dual-gated fusion with prefix-tuning for multi-modal relation extraction","author":"Li","year":"2023"},{"key":"10.1016\/j.neucom.2026.134606_bib0120","series-title":"Thirty-Eighth AAAI Conference on Artificial Intelligence, AAAI 2024","first-page":"18680","article-title":"Hierarchical aligned multimodal learning for NER on tweet posts","author":"Liu","year":"2024"},{"key":"10.1016\/j.neucom.2026.134606_bib0125","series-title":"Proceedings of the ACM on Web Conference 2024, WWW 2024","first-page":"4283","article-title":"Multimodal relation extraction via a mixture of hierarchical visual context learners","author":"Liu","year":"2024"},{"key":"10.1016\/j.neucom.2026.134606_bib0130","series-title":"Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, ACL 2018","first-page":"1990","article-title":"Visual attention model for name tagging in multimodal social media","author":"Lu","year":"2018"},{"key":"10.1016\/j.neucom.2026.134606_bib0135","series-title":"Proceedings of the 29th International Conference on Computational Linguistics, COLING 2022, Gyeongju, Republic of Korea, October 12\u201317, 2022","first-page":"2055","article-title":"Flat multi-modal interaction transformer for named entity recognition","author":"Lu","year":"2022"},{"key":"10.1016\/j.neucom.2026.134606_bib0140","series-title":"Findings of the Association for Computational Linguistics: EMNLP 2023","first-page":"6274","article-title":"Narrative order aware story generation via bidirectional pretraining model with optimal transport reward","author":"Lu","year":"2023"},{"key":"10.1016\/j.neucom.2026.134606_bib0145","author":"Mai"},{"key":"10.1016\/j.neucom.2026.134606_bib0150","series-title":"Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation, LREC\/COLING 2024","first-page":"4259","article-title":"Curriculum learning meets directed acyclic graph for multimodal emotion recognition","author":"Nguyen","year":"2024"},{"key":"10.1016\/j.neucom.2026.134606_bib0155","series-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2019","first-page":"1162","article-title":"Competence-based curriculum learning for neural machine translation","author":"Platanios","year":"2019"},{"key":"10.1016\/j.neucom.2026.134606_bib0160","series-title":"Proceedings of the 38th International Conference on Machine Learning, ICML 2021","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.neucom.2026.134606_bib0165","series-title":"Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015, December 7\u201312, 2015, Montreal, Quebec, Canada","first-page":"91","article-title":"Faster R-CNN: towards real-time object detection with region proposal networks","author":"Ren","year":"2015"},{"key":"10.1016\/j.neucom.2026.134606_bib0170","series-title":"EACL 1999, 9th Conference of the European Chapter of the Association for Computational Linguistics, June 8\u201312, 1999","first-page":"173","article-title":"Representing text chunks","author":"Sang","year":"1999"},{"key":"10.1016\/j.neucom.2026.134606_bib0175","series-title":"Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4\u20139, 2017","first-page":"5998","article-title":"Attention is all you need","author":"Vaswani","year":"2017"},{"key":"10.1016\/j.neucom.2026.134606_bib0180","series-title":"Proceedings of the 57th Conference of the Association for Computational Linguistics, ACL 2019","first-page":"2830","article-title":"Categorizing and inferring the relationship between the text and image of twitter posts","author":"Vempala","year":"2019"},{"key":"10.1016\/j.neucom.2026.134606_bib0185","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.112504","article-title":"Joint multimodal entity-relation extraction based on temporal enhancement and similarity-gated attention","volume":"304","author":"Wang","year":"2024","journal-title":"Knowl. Based Syst."},{"key":"10.1016\/j.neucom.2026.134606_bib0190","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1109\/TASLP.2022.3221017","article-title":"M3S: scene graph driven multi-granularity multi-task learning for multi-modal NER","volume":"31","author":"Wang","year":"2023","journal-title":"IEEE ACM Trans. Audio Speech Lang. Process."},{"key":"10.1016\/j.neucom.2026.134606_bib0195","first-page":"4555","article-title":"A survey on curriculum learning","volume":"44","author":"Wang","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.neucom.2026.134606_bib0200","doi-asserted-by":"crossref","first-page":"1640","DOI":"10.1109\/TBDATA.2024.3407594","article-title":"Denoising neural relation extraction for spatio-temporal recommendation system","volume":"11","author":"Wang","year":"2025","journal-title":"IEEE Trans. Big Data"},{"key":"10.1016\/j.neucom.2026.134606_bib0205","series-title":"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2023","first-page":"14734","article-title":"Information screening whilst exploiting! Multimodal relation extraction with feature denoising and multimodal topic modeling","author":"Wu","year":"2023"},{"key":"10.1016\/j.neucom.2026.134606_bib0210","series-title":"WSDM \u201922: The Fifteenth ACM International Conference on Web Search and Data Mining, Virtual Event","first-page":"1215","article-title":"MAF: a general matching and alignment framework for multimodal named entity recognition","author":"Xu","year":"2022"},{"key":"10.1016\/j.neucom.2026.134606_bib0215","doi-asserted-by":"crossref","first-page":"10779","DOI":"10.1109\/TNNLS.2025.3528567","article-title":"FRCL-MNER: a finer grained rank-based contrastive learning framework for multimodal NER","volume":"36","author":"Yan","year":"2025","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.neucom.2026.134606_bib0220","series-title":"2019 IEEE\/CVF International Conference on Computer Vision, ICCV 2019, Seoul, Korea (South), October 27\u2013November 2, 2019","first-page":"4682","article-title":"A fast and accurate one-stage approach to visual grounding","author":"Yang","year":"2019"},{"key":"10.1016\/j.neucom.2026.134606_bib0225","series-title":"Thirty-Seventh AAAI Conference on Artificial Intelligence, AAAI 2023","first-page":"11051","article-title":"Joint multimodal entity-relation extraction based on edge-enhanced graph alignment network and word-pair relation tagging","author":"Yuan","year":"2023"},{"key":"10.1016\/j.neucom.2026.134606_bib0230","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TKDE.2024.3485107","article-title":"A fine-grained network for joint multimodal entity-relation extraction","volume":"37","author":"Yuan","year":"2025","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"10.1016\/j.neucom.2026.134606_bib0235","series-title":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), ACL 2022","first-page":"1","article-title":"BitFit: simple parameter-efficient fine-tuning for transformer-based masked language-models","author":"Zaken","year":"2022"},{"key":"10.1016\/j.neucom.2026.134606_bib0240","doi-asserted-by":"crossref","first-page":"2430","DOI":"10.1109\/TMM.2022.3147064","article-title":"Multimodal topic modeling by exploring characteristics of short text social media","volume":"25","author":"Zhang","year":"2022","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.neucom.2026.134606_bib0245","doi-asserted-by":"crossref","first-page":"245","DOI":"10.1016\/j.neucom.2019.06.087","article-title":"Multi-task and multi-view training for end-to-end relation extraction","volume":"364","author":"Zhang","year":"2019","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.134606_bib0250","series-title":"Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, (AAAI-18)","first-page":"5674","article-title":"Adaptive co-attention network for named entity recognition in tweets","author":"Zhang","year":"2018"},{"key":"10.1016\/j.neucom.2026.134606_bib0255","series-title":"Proceedings of the 32nd ACM International Conference on Multimedia, MM 2024, Melbourne, VIC, Australia, 28 October 2024\u20131 November 2024","first-page":"1148","article-title":"Caption-aware multimodal relation extraction with mutual information maximization","author":"Zhang","year":"2024"},{"key":"10.1016\/j.neucom.2026.134606_bib0260","series-title":"Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, EMNLP 2023","first-page":"9057","article-title":"M2DF: multi-grained multi-curriculum denoising framework for multimodal aspect-based sentiment analysis","author":"Zhao","year":"2023"},{"key":"10.1016\/j.neucom.2026.134606_bib0265","series-title":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, IJCAI 2020","first-page":"4032","article-title":"Modeling dense cross-modal interactions for joint entity-relation extraction","author":"Zhao","year":"2020"},{"key":"10.1016\/j.neucom.2026.134606_bib0270","series-title":"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2023","first-page":"6810","article-title":"Rethinking multimodal entity and relation extraction from a translation point of view","author":"Zheng","year":"2023"},{"key":"10.1016\/j.neucom.2026.134606_bib0275","series-title":"MM \u201921: ACM Multimedia Conference","first-page":"5298","article-title":"Multimodal relation extraction with efficient graph alignment","author":"Zheng","year":"2021"},{"key":"10.1016\/j.neucom.2026.134606_bib0280","series-title":"2021 IEEE International Conference on Multimedia and Expo, ICME 2021","first-page":"1","article-title":"MNRE: a challenge multimodal dataset for neural relation extraction with visual evidence in social media posts","author":"Zheng","year":"2021"},{"key":"10.1016\/j.neucom.2026.134606_bib0285","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1016\/j.neucom.2016.12.075","article-title":"Joint entity and relation extraction based on a hybrid neural network","volume":"257","author":"Zheng","year":"2017","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.134606_bib0290","series-title":"Forty-First International Conference on Machine Learning, ICML 2024, Vienna, Austria, July 21\u201327, 2024","article-title":"CurBench: curriculum learning benchmark","author":"Zhou","year":"2024"},{"key":"10.1016\/j.neucom.2026.134606_bib0295","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.128994","article-title":"RTA: a reinforcement learning-based temporal knowledge graph question answering model","volume":"617","author":"Zhu","year":"2025","journal-title":"Neurocomputing"}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226020047?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226020047?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T21:23:01Z","timestamp":1790198581000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0925231226020047"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":59,"alternative-id":["S0925231226020047"],"URL":"https:\/\/doi.org\/10.1016\/j.neucom.2026.134606","relation":{},"ISSN":["0925-2312"],"issn-type":[{"value":"0925-2312","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Multi-grained dynamic feature resorter with curriculum bootstrapping for multimodal entity and relation extraction","name":"articletitle","label":"Article Title"},{"value":"Neurocomputing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neucom.2026.134606","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"134606"}}