{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T19:39:18Z","timestamp":1773949158147,"version":"3.50.1"},"reference-count":32,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"9","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Trans. Inf. & Syst."],"published-print":{"date-parts":[[2025,9,1]]},"DOI":"10.1587\/transinf.2024edp7173","type":"journal-article","created":{"date-parts":[[2025,3,18]],"date-time":"2025-03-18T18:11:39Z","timestamp":1742321499000},"page":"1072-1081","source":"Crossref","is-referenced-by-count":1,"title":["Multi-Modal Entity Alignment Based on Multidimensional Semantic Extraction"],"prefix":"10.1587","volume":"E108.D","author":[{"given":"Huansha","family":"WANG","sequence":"first","affiliation":[{"name":"Information Engineering University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qinrang","family":"LIU","sequence":"additional","affiliation":[{"name":"Information Engineering University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruiyang","family":"HUANG","sequence":"additional","affiliation":[{"name":"Information Engineering University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianpeng","family":"ZHANG","sequence":"additional","affiliation":[{"name":"Information Engineering University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongji","family":"LIU","sequence":"additional","affiliation":[{"name":"Information Engineering University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"532","reference":[{"key":"1","doi-asserted-by":"crossref","unstructured":"[1] Y. Liu, H. Li, A. Garc\u00eda-Dur\u00e1n, M. Niepert, D. O\u00f1oro-Rubio, and D.S. Rosenblum, \u201cMMKG: Multi-modal Knowledge Graphs,\u201d ESWC, pp.459-474, 2019. 10.1007\/978-3-030-21348-0_30","DOI":"10.1007\/978-3-030-21348-0_30"},{"key":"2","unstructured":"[2] X. Zhao, W. Zeng, and J. Tang, Entity Alignment - Concepts, Recent Advances and Novel Approaches, Springer 2023, ISBN 978-981-99-4249-7, pp.3-247, 2023. 10.1007\/978-981-99-4250-3"},{"key":"3","doi-asserted-by":"crossref","unstructured":"[3] L. Chen, Z. Li, Y. Wang, T. Xu, Z. Wang, and E. Chen, \u201cMMEA: Entity Alignment for Multi-modal Knowledge Graph,\u201d KSEM 2020, pp.134-147, 2020. 10.1007\/978-3-030-55130-8_12","DOI":"10.1007\/978-3-030-55130-8_12"},{"key":"4","doi-asserted-by":"crossref","unstructured":"[4] Y. Liu, H. Li, A. Garcia-Duran, M. Niepert, D. Onoro-Rubio, and D.S. Rosenblum, \u201cMMKG: Multi-modal Knowledge Graphs,\u201d The Semantic Web, Cham. Springer International Publishing., pp.459-474, 2019. 10.1007\/978-3-030-21348-0_30","DOI":"10.1007\/978-3-030-21348-0_30"},{"key":"5","doi-asserted-by":"crossref","unstructured":"[5] M. Chen, Y. Tian, M. Yang, and C. Zaniolo, \u201cMultilingual knowledge graph embeddings for cross-lingual knowledge alignment,\u201d Proc. 26th International Joint Conference on Artificial Intelligence, pp.1511-1517, 2017. 10.24963\/ijcai.2017\/209","DOI":"10.24963\/ijcai.2017\/209"},{"key":"6","unstructured":"[6] A. Bordes, N. Usunier, A. Garcia-Dur\u00e1n, J. Weston, and O. Yakhnenko, \u201cTranslating embeddings for modeling multi relational data,\u201d Advances in Neural Information Processing Systems (NIPS), pp.2787-2795, 2013."},{"key":"7","doi-asserted-by":"crossref","unstructured":"[7] Z. Sun, W. Hu, Q. Zhang, and Y. Qu, \u201cBootstrapping entity alignment with knowledge graph embedding,\u201d IJCAI 2018, pp.4396-4402, 2018.","DOI":"10.24963\/ijcai.2018\/611"},{"key":"8","doi-asserted-by":"publisher","unstructured":"[8] B.D. Trisedya, J. Qi, and R. Zhang, \u201cEntity alignment between knowledge graphs using attribute embeddings,\u201d Proc. AAAI Conference on Artificial Intelligence 2019, vol.33, no.1, pp.297-304, 2019. 10.1609\/aaai.v33i01.3301297","DOI":"10.1609\/aaai.v33i01.3301297"},{"key":"9","doi-asserted-by":"crossref","unstructured":"[9] X. Tang, J. Zhang, B. Chen, Y. Yang, H. Chen, and C. Li, \u201cBERT-INT: A BERT-based Interaction Model For Knowledge Graph Alignment,\u201d IJCAI 2020, pp.3174-3180, 2020. 10.24963\/ijcai.2020\/439","DOI":"10.24963\/ijcai.2020\/439"},{"key":"10","unstructured":"[10] J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, \u201cBERT: Pre-training of Deep Bidirectional Transformers for Language Understanding,\u201d Proc. 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp.4171-4186, 2019. 10.18653\/v1\/N19-1423"},{"key":"11","doi-asserted-by":"crossref","unstructured":"[11] Z. Wang, Q. Lv, X. Lan, and Y. Zhang, \u201cCross-lingual Knowledge Graph Alignment via Graph Convolutional Networks,\u201d EMNLP 2018, pp.349-357, 2018. 10.18653\/v1\/d18-1032","DOI":"10.18653\/v1\/D18-1032"},{"key":"12","doi-asserted-by":"publisher","unstructured":"[12] Z. Sun, C. Wang, W. Hu, M. Chen, J. Dai, W. Zhang, and Y. Qu, \u201cKnowledge Graph Alignment Network with Gated Multi-Hop Neighborhood Aggregation,\u201d AAAI 2020, vol.34, no.1, pp.222-229, 2020. 10.1609\/aaai.v34i01.5354","DOI":"10.1609\/aaai.v34i01.5354"},{"key":"13","doi-asserted-by":"crossref","unstructured":"[13] X. Mao, W. Wang, Y. Wu, and M. Lan, \u201cFrom Alignment to Assignment: Frustratingly Simple Unsupervised Entity Alignment,\u201d EMNLP 2021, pp.2843-2853, 2021. 10.18653\/v1\/2021.emnlp-main.226","DOI":"10.18653\/v1\/2021.emnlp-main.226"},{"key":"14","doi-asserted-by":"crossref","unstructured":"[14] W. Ni, Q. Xu, Y. Jiang, Z. Cao, X. Cao, and Q. Huang, \u201cPSNEA: Pseudo-Siamese Network for Entity Alignment between Multi-modal Knowledge Graphs,\u201d ACM Multimedia 2023, pp.3489-3497, 2023. 10.1145\/3581783.3611778","DOI":"10.1145\/3581783.3611778"},{"key":"15","unstructured":"[15] Z. Lin, Z. Zhang, M. Wang, Y. Shi, X. Wu, and Y. Zheng, \u201cMulti-modal contrastive representation learning for entity alignment,\u201d COLING 2022, pp.2572-2584,2022."},{"key":"16","doi-asserted-by":"publisher","unstructured":"[16] H. Wang, Q. Liu, R. Huang, and J. Zhang, \u201cMulti-Modal Entity Alignment Method Based on Feature Enhancement,\u201d Applied Sciences, vol.13, no.11, p.6747, https:\/\/doi.org\/10.3390\/app13116747, 2023. 10.3390\/app13116747","DOI":"10.3390\/app13116747"},{"key":"17","unstructured":"[17] S. Brody, U. Alon, and E. Yahav, \u201cHow Attentive are Graph Attention Networks?,\u201d The tenth international conference on learning representations, ICLR 2022, Virtual Event, April 25-29, 2022."},{"key":"18","unstructured":"[18] P. Velickovic, G. Cucurull, A. Casanova, A. Romero, P. Li\u00f2, and Y. Bengio, \u201cGraph attention networks,\u201d ICLR (Poster), 2018."},{"key":"19","doi-asserted-by":"crossref","unstructured":"[19] H.-W. Yang, Y. Zou, P. Shi, W. Lu, J. Lin, and X. Sun, \u201cAligning Cross-Lingual Entities with Multi-aspect Information,\u201d Proc. 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pp.4431-4441, 2019. 10.18653\/v1\/D19-1451","DOI":"10.18653\/v1\/D19-1451"},{"key":"20","unstructured":"[20] J. Bai, S. Bai, Y. Chu, Z. Cui, K. Dang, X. Deng, Y. Fan, W. Ge, Y. Han, F. Huang, B. Hui, L. Ji, M. Li, J. Lin, R. Lin, D. Liu, G. Liu, C. Lu, K. Lu, J. Ma, R. Men, X. Ren, X. Ren, C. Tan, S. Tan, J. Tu, P. Wang, S. Wang, W. Wang, S. Wu, B. Xu, J. Xu, A. Yang, H. Yang, J. Yang, S. Yang, Y. Yao, B. Yu, H. Yuan, Z. Yuan, J. Zhang, X. Zhang, Y. Zhang, Z. Zhang, C. Zhou, J. Zhou, X. Zhou, and T. Zhu, \u201cQwen technical report,\u201d CoRR abs\/2309.16609, 2023."},{"key":"21","unstructured":"[21] J. Li, D. Li, S. Savarese, and S. Hoi, \u201cBlip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models,\u201d International Conference on Machine Learning, ICML 2023, pp.19730-19742, 2023."},{"key":"22","doi-asserted-by":"crossref","unstructured":"[22] Z. Li, B. Yang, Q. Liu, Z. Ma, S. Zhang, J. Yang, Y. Sun, Y. Liu, and X. Bai, \u201cMonkey: Image Resolution and Text Label Are Important Things for Large Multi-modal Models,\u201d CVPR, pp.26753-26763, 2024. 10.1109\/cvpr52733.2024.02527","DOI":"10.1109\/CVPR52733.2024.02527"},{"key":"23","doi-asserted-by":"crossref","unstructured":"[23] J. Wu, J. Wang, Z. Yang, Z. Gan, Z. Liu, J. Yuan, and L. Wang, \u201cGrit: A generative region-to-text transformer for object understanding,\u201d Lecture Notes in Computer Science, vol.15138, pp.207-224, 2024. 10.1007\/978-3-031-72989-8_12","DOI":"10.1007\/978-3-031-72989-8_12"},{"key":"24","unstructured":"[24] A. Radford, J.W. Kim, C. Hallacy, A. Ramesh, G. Goh, S. Agarwal, G. Sastry, A. Askell, P. Mishkin, J. Clark, G. Krueger, and I. Sutskever, \u201cLearning transferable visual models from natural language supervision,\u201d ICML 2021, pp.8748-8763, 2021."},{"key":"25","unstructured":"[25] X. Zhao, W. Ding, Y. An, Y. Du, T. Yu, M. Li, M. Tang, and J. Wang, \u201cFast segment anything,\u201d CoRR abs\/2306.12156, 2023."},{"key":"26","unstructured":"[26] Y. Du, C. Li, R. Guo, X. Yin, W. Liu, J. Zhou, Y. Bai, Z. Yu, Y. Yang, Q. Dang, and H. Wang, \u201cPp-ocr: A practical ultra lightweight ocr system,\u201d arXiv preprint arXiv:2009.09941, 2020."},{"key":"27","unstructured":"[27] K. Simonyan and A. Zisserman, \u201cVery deep convolutional networks for large-Scale image recognition,\u201d ICLR, 2015."},{"key":"28","doi-asserted-by":"publisher","unstructured":"[28] H. Guo, J. Tang, W. Zeng, X. Zhao, and L. Liu, \u201cMulti-modal Entity Alignment in Hyperbolic Space,\u201d Neurocomputing, vol.461, pp.598-607, 2021. 10.1016\/j.neucom.2021.03.132","DOI":"10.1016\/j.neucom.2021.03.132"},{"key":"29","doi-asserted-by":"publisher","unstructured":"[29] F. Liu, M. Chen, D. Roth, and N. Collier, \u201cVisual Pivoting for (Unsupervised) Entity Alignment,\u201d Proc. AAAI Conference on Artificial Intelligence, vol.35, no.5, pp.4257-4266, 2021. 10.1609\/aaai.v35i5.16550","DOI":"10.1609\/aaai.v35i5.16550"},{"key":"30","doi-asserted-by":"crossref","unstructured":"[30] Q. Li, C. Ji, S. Guo, Z. Liang, L. Wang, and J. Li, \u201cMulti-Modal Knowledge Graph Transformer Framework for Multi-Modal Entity Alignment,\u201d EMNLP (Findings) 2023, pp.987-999, 2023. 10.18653\/v1\/2023.findings-emnlp.70","DOI":"10.18653\/v1\/2023.findings-emnlp.70"},{"key":"31","doi-asserted-by":"crossref","unstructured":"[31] Y. Wang, H. Sun, J. Wang, J. Wang, W. Tang, Q. Qi, S. Sun, and J. Liao, \u201cTowards semantic consistency: Dirichlet energy driven robust multi-Modal entity alignment,\u201d CoRR abs\/2401.17859, 2024.","DOI":"10.1109\/ICDE60146.2024.00274"},{"key":"32","unstructured":"[32] A. Madry, A. Makelov, L. Schmidt, D. Tsipras, and A. Vladu,\u201cTowards deep learning models resistant to adversarial attacks,\u201d ICLR (Poster), 2018."}],"container-title":["IEICE Transactions on Information and Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E108.D\/9\/E108.D_2024EDP7173\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T03:25:11Z","timestamp":1757129111000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E108.D\/9\/E108.D_2024EDP7173\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,1]]},"references-count":32,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2025]]}},"URL":"https:\/\/doi.org\/10.1587\/transinf.2024edp7173","relation":{},"ISSN":["0916-8532","1745-1361"],"issn-type":[{"value":"0916-8532","type":"print"},{"value":"1745-1361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,1]]},"article-number":"2024EDP7173"}}