{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T23:52:58Z","timestamp":1782863578911,"version":"3.54.5"},"reference-count":62,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100011347","name":"State Key Laboratory of Software Development Environment","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100011347","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U2433212"],"award-info":[{"award-number":["U2433212"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Knowledge-Based Systems"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.knosys.2026.116474","type":"journal-article","created":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T23:27:04Z","timestamp":1781911624000},"page":"116474","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Modeling latent cross-modal interaction for reliability-aware entity alignment in multimodal relation extraction"],"prefix":"10.1016","volume":"349","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1120-6584","authenticated-orcid":false,"given":"Xiyang","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3473-9703","authenticated-orcid":false,"given":"Chunming","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1207-0300","authenticated-orcid":false,"given":"Richong","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6807-0089","authenticated-orcid":false,"given":"Junfan","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-2717-3377","authenticated-orcid":false,"given":"Baowen","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.knosys.2026.116474_b1","series-title":"Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP","first-page":"1021","article-title":"Unsupervised relation extraction by mining wikipedia texts using information from the web","author":"Yan","year":"2009"},{"key":"10.1016\/j.knosys.2026.116474_b2","series-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","first-page":"3047","article-title":"OpenCeres: When open information extraction meets the semi-structured web","author":"Lockard","year":"2019"},{"key":"10.1016\/j.knosys.2026.116474_b3","series-title":"Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval","first-page":"1149","article-title":"Open relation extraction for support passage retrieval: Merit and open issues","author":"Kadry","year":"2017"},{"key":"10.1016\/j.knosys.2026.116474_b4","series-title":"The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval","first-page":"1387","article-title":"Utilizing knowledge graphs for text-centric information retrieval","author":"Dietz","year":"2018"},{"key":"10.1016\/j.knosys.2026.116474_b5","series-title":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","first-page":"1340","article-title":"Entity-relation extraction as multi-turn question answering","author":"Li","year":"2019"},{"issue":"4","key":"10.1016\/j.knosys.2026.116474_b6","doi-asserted-by":"crossref","DOI":"10.1145\/3345557","article-title":"Question answering in knowledge bases: A verification assisted model with iterative training","volume":"37","author":"Zhang","year":"2019","journal-title":"ACM Trans. Inf. Syst."},{"key":"10.1016\/j.knosys.2026.116474_b7","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.knosys.2026.116474_b8","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","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.knosys.2026.116474_b9","series-title":"Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: System Demonstrations","first-page":"98","article-title":"DeepKE: A deep learning based knowledge extraction toolkit for knowledge base population","author":"Zhang","year":"2022"},{"key":"10.1016\/j.knosys.2026.116474_b10","series-title":"Proceedings of the ACM Web Conference 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.knosys.2026.116474_b11","series-title":"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics","first-page":"9141","article-title":"Grounded multimodal named entity recognition on social media","author":"Yu","year":"2023"},{"key":"10.1016\/j.knosys.2026.116474_b12","series-title":"Proceedings of the 31st ACM International Conference on Multimedia","first-page":"3934","article-title":"Fine-grained multimodal named entity recognition and grounding with a generative framework","author":"Wang","year":"2023"},{"key":"10.1016\/j.knosys.2026.116474_b13","series-title":"Advancing grounded multimodal named entity recognition via LLM-based reformulation and box-based segmentation","author":"Li","year":"2025"},{"key":"10.1016\/j.knosys.2026.116474_b14","series-title":"Shikra: Unleashing multimodal LLM\u2019s referential dialogue magic","author":"Chen","year":"2023"},{"key":"10.1016\/j.knosys.2026.116474_b15","series-title":"Qwen2.5-VL technical report","author":"Bai","year":"2025"},{"key":"10.1016\/j.knosys.2026.116474_b16","series-title":"InternVL3: Exploring advanced training and test-time recipes for open-source multimodal models","author":"Zhu","year":"2025"},{"key":"10.1016\/j.knosys.2026.116474_b17","series-title":"LLaVA-Grounding: Grounded visual chat with large multimodal models","author":"Zhang","year":"2023"},{"key":"10.1016\/j.knosys.2026.116474_b18","series-title":"2021 IEEE International Conference on Multimedia and Expo","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.knosys.2026.116474_b19","series-title":"Proceedings of the 31st ACM International Conference on Multimedia","first-page":"4564","article-title":"MORE: A multimodal object-entity relation extraction dataset with a benchmark evaluation","author":"He","year":"2023"},{"key":"10.1016\/j.knosys.2026.116474_b20","series-title":"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics","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.knosys.2026.116474_b21","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.knosys.2026.116474_b22","series-title":"Proceedings of the 32nd ACM International Conference on Multimedia","first-page":"5270","article-title":"Shapley value-based contrastive alignment for multimodal information extraction","author":"Luo","year":"2024"},{"key":"10.1016\/j.knosys.2026.116474_b23","series-title":"Multimodal question answering for unified information extraction","author":"Sun","year":"2023"},{"key":"10.1016\/j.knosys.2026.116474_b24","series-title":"Web Information Systems and Applications: 21st International Conference, WISA 2024, Yinchuan, China, August 2\u20134, 2024, Proceedings","first-page":"364","article-title":"Instruction tuning large language models for multimodal relation extraction using LoRA","author":"Li","year":"2024"},{"key":"10.1016\/j.knosys.2026.116474_b25","series-title":"Proceedings of the 33rd ACM International Conference on Multimedia","first-page":"121","article-title":"REMOTE: A unified multimodal relation extraction framework with multilevel optimal transport and mixture-of-experts","author":"Lin","year":"2025"},{"key":"10.1016\/j.knosys.2026.116474_b26","series-title":"Advances in Neural Information Processing Systems","first-page":"1877","article-title":"Language models are few-shot learners","volume":"Vol. 33","author":"Brown","year":"2020"},{"key":"10.1016\/j.knosys.2026.116474_b27","series-title":"The llama 3 herd of models","author":"Dubey","year":"2024"},{"key":"10.1016\/j.knosys.2026.116474_b28","series-title":"Advances in Neural Information Processing Systems","first-page":"34892","article-title":"Visual instruction tuning","volume":"Vol. 36","author":"Liu","year":"2023"},{"key":"10.1016\/j.knosys.2026.116474_b29","series-title":"The Twelfth International Conference on Learning Representations","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2024"},{"key":"10.1016\/j.knosys.2026.116474_b30","series-title":"Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics","first-page":"6657","article-title":"GroundingGPT: Language enhanced multi-modal grounding model","author":"Li","year":"2024"},{"key":"10.1016\/j.knosys.2026.116474_b31","series-title":"DetGPT: Detect what you need via reasoning","author":"Pi","year":"2023"},{"key":"10.1016\/j.knosys.2026.116474_b32","series-title":"First Conference on Language Modeling","article-title":"Ferret-v2: An improved baseline for referring and grounding with large language models","author":"Zhang","year":"2024"},{"issue":"2","key":"10.1016\/j.knosys.2026.116474_b33","doi-asserted-by":"crossref","first-page":"423","DOI":"10.1109\/TPAMI.2018.2798607","article-title":"Multimodal machine learning: A survey and taxonomy","volume":"41","author":"Baltrusaitis","year":"2019","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"3","key":"10.1016\/j.knosys.2026.116474_b34","doi-asserted-by":"crossref","first-page":"103","DOI":"10.1007\/s11263-025-02667-1","article-title":"Multimodal alignment and fusion: A survey","volume":"134","author":"Li","year":"2026","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.knosys.2026.116474_b35","series-title":"Multimodal Sensing: Technologies and Applications","article-title":"Research of spatial alignment techniques for multimodal image fusion","volume":"Vol. 11059","author":"Akhmerov","year":"2019"},{"key":"10.1016\/j.knosys.2026.116474_b36","series-title":"Multimodal network alignment","author":"Nassar","year":"2017"},{"issue":"C","key":"10.1016\/j.knosys.2026.116474_b37","article-title":"CiteNet: Cross-modal incongruity perception network for multimodal sentiment prediction","volume":"295","author":"Wang","year":"2024","journal-title":"Know.-Based Syst."},{"issue":"C","key":"10.1016\/j.knosys.2026.116474_b38","doi-asserted-by":"crossref","DOI":"10.1007\/978-981-97-5208-9","article-title":"Cross-modal incongruity aligning and collaborating for multi-modal sarcasm detection","volume":"103","author":"Wang","year":"2024","journal-title":"Inf. Fusion"},{"issue":"6","key":"10.1016\/j.knosys.2026.116474_b39","doi-asserted-by":"crossref","DOI":"10.1007\/s11432-024-4333-7","article-title":"DiagLLM: multimodal reasoning with large language model for explainable bearing fault diagnosis","volume":"68","author":"Wang","year":"2025","journal-title":"Sci. China Inf. Sci."},{"key":"10.1016\/j.knosys.2026.116474_b40","unstructured":"L. Vilnis, A. McCallum, Word Representations via Gaussian Embedding, in: Y. Bengio, Y. LeCun (Eds.), 3rd International Conference on Learning Representations, San Diego, CA, USA, 2015."},{"key":"10.1016\/j.knosys.2026.116474_b41","series-title":"International Conference on Learning Representations","article-title":"Modeling uncertainty with hedged instance embeddings","author":"Oh","year":"2019"},{"key":"10.1016\/j.knosys.2026.116474_b42","series-title":"Thirty-Fifth AAAI Conference on Artificial Intelligence, AAAI 2021, Thirty-Third Conference on Innovative Applications of Artificial Intelligence","first-page":"7545","article-title":"Uncertainty-aware multi-view representation learning","author":"Geng","year":"2021"},{"issue":"8","key":"10.1016\/j.knosys.2026.116474_b43","doi-asserted-by":"crossref","first-page":"7657","DOI":"10.1109\/TCSVT.2024.3376564","article-title":"Trustworthy multimodal fusion for sentiment analysis in ordinal sentiment space","volume":"34","author":"Xie","year":"2024","journal-title":"IEEE Trans. Cir. Sys. Video Technol."},{"key":"10.1016\/j.knosys.2026.116474_b44","series-title":"The Thirteenth International Conference on Learning Representations","article-title":"Towards interpreting visual information processing in vision-language models","author":"Neo","year":"2025"},{"key":"10.1016\/j.knosys.2026.116474_b45","series-title":"Interpreting gpt: The logit lens","author":"Nostalgebraist","year":"2020"},{"key":"10.1016\/j.knosys.2026.116474_b46","doi-asserted-by":"crossref","unstructured":"Z. Lin, Y. Wang, Z. Tang, Training-Free Open-Ended Object Detection and Segmentation via Attention as Prompts, in: A. Globersons, L. Mackey, D. Belgrave, A. Fan, U. Paquet, J.M. Tomczak, C. Zhang (Eds.), Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024.","DOI":"10.52202\/079017-2223"},{"issue":"9","key":"10.1016\/j.knosys.2026.116474_b47","doi-asserted-by":"crossref","first-page":"6945","DOI":"10.1007\/s10994-024-06570-7","article-title":"Spatial entropy as an inductive bias for vision transformers","volume":"113","author":"Peruzzo","year":"2024","journal-title":"Mach. Learn."},{"issue":"6","key":"10.1016\/j.knosys.2026.116474_b48","doi-asserted-by":"crossref","first-page":"1596","DOI":"10.1109\/TIP.2010.2044963","article-title":"Optimized block-based connected components labeling with decision trees","volume":"19","author":"Grana","year":"2010","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.knosys.2026.116474_b49","series-title":"Proceedings of the Sixth Workshop on Computational Models of Reference, Anaphora and Coreference","first-page":"8","article-title":"CAW-coref: Conjunction-aware word-level coreference resolution","author":"D\u2019Oosterlinck","year":"2023"},{"key":"10.1016\/j.knosys.2026.116474_b50","doi-asserted-by":"crossref","first-page":"146","DOI":"10.1016\/j.neucom.2022.07.042","article-title":"Focal and efficient IOU loss for accurate bounding box regression","volume":"506","author":"Zhang","year":"2022","journal-title":"Neurocomputing"},{"key":"10.1016\/j.knosys.2026.116474_b51","series-title":"Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing","first-page":"1753","article-title":"Distant supervision for relation extraction via piecewise convolutional neural networks","author":"Zeng","year":"2015"},{"key":"10.1016\/j.knosys.2026.116474_b52","series-title":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","first-page":"2895","article-title":"Matching the blanks: Distributional similarity for relation learning","author":"Baldini Soares","year":"2019"},{"key":"10.1016\/j.knosys.2026.116474_b53","series-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019"},{"key":"10.1016\/j.knosys.2026.116474_b54","series-title":"GPT-4 technical report","author":"OpenAI","year":"2024"},{"key":"10.1016\/j.knosys.2026.116474_b55","doi-asserted-by":"crossref","first-page":"1274","DOI":"10.1109\/TASLP.2023.3345146","article-title":"Enhancing multimodal entity and relation extraction with variational information bottleneck","volume":"32","author":"Cui","year":"2024","journal-title":"IEEE\/ACM Trans. Audio, Speech Lang. Proc."},{"key":"10.1016\/j.knosys.2026.116474_b56","series-title":"Proceedings of the 2024 International Conference on Multimedia Retrieval","first-page":"524","article-title":"CGI-MRE: A comprehensive genetic-inspired model for multimodal relation extraction","author":"Wei","year":"2024"},{"key":"10.1016\/j.knosys.2026.116474_b57","series-title":"Findings of the Association for Computational Linguistics: NAACL 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.knosys.2026.116474_b58","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.113770","article-title":"ES-MRE: Evidence subgraph enhanced reasoning for multimodal relation extraction","volume":"325","author":"Huang","year":"2025","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2026.116474_b59","series-title":"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics","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.knosys.2026.116474_b60","series-title":"Proceedings of the 32nd ACM International Conference on Multimedia","first-page":"1148","article-title":"Caption-aware multimodal relation extraction with mutual information maximization","author":"Zhang","year":"2024"},{"key":"10.1016\/j.knosys.2026.116474_b61","series-title":"Proceedings of the 32nd ACM International Conference on Multimedia","first-page":"1379","article-title":"Focus & gating: A multimodal approach for unveiling relations in noisy social media","author":"He","year":"2024"},{"key":"10.1016\/j.knosys.2026.116474_b62","unstructured":"A. Paszke, S. Gross, F. Massa, A. Lerer, J. Bradbury, G. Chanan, T. Killeen, Z. Lin, N. Gimelshein, L. Antiga, A. Desmaison, A. K\u00f6pf, E.Z. Yang, Z. DeVito, M. Raison, A. Tejani, S. Chilamkurthy, B. Steiner, L. Fang, J. Bai, S. Chintala, PyTorch: An Imperative Style, High-Performance Deep Learning Library, in: H.M. Wallach, H. Larochelle, A. Beygelzimer, F. d\u2019Alch\u00e9-Buc, E.B. Fox, R. Garnett (Eds.), Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, Vancouver, BC, Canada, 2019, pp. 8024\u20138035, URL: https:\/\/proceedings.neurips.cc\/paper\/2019\/hash\/bdbca288fee7f92f2bfa9f7012727740-Abstract.html."}],"container-title":["Knowledge-Based Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126012001?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126012001?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T23:00:40Z","timestamp":1782860440000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0950705126012001"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":62,"alternative-id":["S0950705126012001"],"URL":"https:\/\/doi.org\/10.1016\/j.knosys.2026.116474","relation":{},"ISSN":["0950-7051"],"issn-type":[{"value":"0950-7051","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Modeling latent cross-modal interaction for reliability-aware entity alignment in multimodal relation extraction","name":"articletitle","label":"Article Title"},{"value":"Knowledge-Based Systems","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.knosys.2026.116474","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":"116474"}}