{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T19:37:23Z","timestamp":1780774643983,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":49,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Natural Science Foundation of China under Grant","award":["62302130"],"award-info":[{"award-number":["62302130"]}]},{"name":"National Key Research and Development Program of China under Grant","award":["2022ZD0118300"],"award-info":[{"award-number":["2022ZD0118300"]}]},{"name":"National Natural Science Foundation of China under Grant","award":["62302131"],"award-info":[{"award-number":["62302131"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681696","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:33Z","timestamp":1729925973000},"page":"8374-8382","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Multimodal Contextual Interactions of Entities: A Modality Circular Fusion Approach for Link Prediction"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-4682-4839","authenticated-orcid":false,"given":"Jing","family":"Yang","sequence":"first","affiliation":[{"name":"Hainan University, Hainan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4454-9889","authenticated-orcid":false,"given":"Shundong","family":"Yang","sequence":"additional","affiliation":[{"name":"Hainan University, Hainan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4096-9134","authenticated-orcid":false,"given":"Yuan","family":"Gao","sequence":"additional","affiliation":[{"name":"Hainan University, Hainan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9584-2160","authenticated-orcid":false,"given":"Jieming","family":"Yang","sequence":"additional","affiliation":[{"name":"Hainan University, Hainan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7986-4244","authenticated-orcid":false,"given":"Laurence T.","family":"Yang","sequence":"additional","affiliation":[{"name":"Zhengzhou University & St. Francis Xavier University, Zhengzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"crossref","unstructured":"Ivana Balavzevi\u0107 Carl Allen and Timothy Hospedales. 2019. TuckER: Tensor Factorization for Knowledge Graph Completion. In EMNLP. 5185--5194.","DOI":"10.18653\/v1\/D19-1522"},{"key":"e_1_3_2_1_2_1","volume-title":"Proc. of NeurIPS","volume":"26","author":"Bordes Antoine","year":"2013","unstructured":"Antoine Bordes, Nicolas Usunier, Alberto Garcia-Duran, Jason Weston, and Oksana Yakhnenko. 2013. Translating embeddings for modeling multi-relational data. Proc. of NeurIPS, Vol. 26 (2013)."},{"key":"e_1_3_2_1_3_1","volume-title":"KBGAN: Adversarial Learning for Knowledge Graph Embeddings. In NAACL. 1470--1480.","author":"Cai Liwei","year":"2018","unstructured":"Liwei Cai and William Yang Wang. 2018. KBGAN: Adversarial Learning for Knowledge Graph Embeddings. In NAACL. 1470--1480."},{"key":"e_1_3_2_1_4_1","volume-title":"Otkge: Multi-modal knowledge graph embeddings via optimal transport. Advances in Neural Information Processing Systems","author":"Cao Zongsheng","year":"2022","unstructured":"Zongsheng Cao, Qianqian Xu, Zhiyong Yang, Yuan He, Xiaochun Cao, and Qingming Huang. 2022. Otkge: Multi-modal knowledge graph embeddings via optimal transport. Advances in Neural Information Processing Systems (2022)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.336"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i4.25535"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"crossref","unstructured":"Xiang Chen Ningyu Zhang Lei Li Shumin Deng Chuanqi Tan Changliang Xu Fei Huang Luo Si and Huajun Chen. 2022. Hybrid transformer with multi-level fusion for multimodal knowledge graph completion. In ACM SIGIR. 904--915.","DOI":"10.1145\/3477495.3531992"},{"key":"e_1_3_2_1_8_1","volume-title":"Imagenet: A large-scale hierarchical image database. In CVPR.","author":"Deng Jia","year":"2009","unstructured":"Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, and Li Fei-Fei. 2009. Imagenet: A large-scale hierarchical image database. In CVPR."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"crossref","unstructured":"Tim Dettmers Pasquale Minervini Pontus Stenetorp and Sebastian Riedel. 2018. Convolutional 2d knowledge graph embeddings. In AAAI.","DOI":"10.1609\/aaai.v32i1.11573"},{"key":"e_1_3_2_1_10_1","volume-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In NAACL-HLT. 4171--4186.","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In NAACL-HLT. 4171--4186."},{"key":"e_1_3_2_1_11_1","volume-title":"International Conference on Learning Representations.","author":"Dosovitskiy Alexey","year":"2020","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, et al. 2020. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_12_1","volume-title":"Contrastive multi-modal knowledge graph representation learning","author":"Fang Quan","year":"2022","unstructured":"Quan Fang, Xiaowei Zhang, Jun Hu, Xian Wu, and Changsheng Xu. 2022. Contrastive multi-modal knowledge graph representation learning. IEEE Transactions on Knowledge and Data Engineering (2022), 8983--8996."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","unstructured":"Sebasti\u00e1n Ferrada Benjamin Bustos and Aidan Hogan. 2017. IMGpedia: a linked dataset with content-based analysis of Wikimedia images. In ISWC.","DOI":"10.1007\/978-3-319-68204-4_8"},{"key":"e_1_3_2_1_14_1","first-page":"1258","article-title":"MR-GCN: Multi-Relational Graph Convolutional Networks based on Generalized Tensor Product","volume":"20","author":"Huang Zhichao","year":"2020","unstructured":"Zhichao Huang, Xutao Li, Yunming Ye, and Michael K Ng. 2020. MR-GCN: Multi-Relational Graph Convolutional Networks based on Generalized Tensor Product.. In IJCAI, Vol. 20. 1258--1264.","journal-title":"IJCAI"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"crossref","unstructured":"Ranjay Krishna Yuke Zhu Oliver Groth Justin Johnson Kenji Hata Joshua Kravitz Stephanie Chen Yannis Kalantidis Li-Jia Li David A Shamma et al. 2017. Visual genome: Connecting language and vision using crowdsourced dense image annotations. International journal of computer vision (2017).","DOI":"10.1007\/s11263-016-0981-7"},{"key":"e_1_3_2_1_16_1","volume-title":"International Conference on Machine Learning. PMLR, 2863--2872","author":"Lacroix Timoth\u00e9e","year":"2018","unstructured":"Timoth\u00e9e Lacroix, Nicolas Usunier, and Guillaume Obozinski. 2018. Canonical tensor decomposition for knowledge base completion. In International Conference on Machine Learning. PMLR, 2863--2872."},{"key":"e_1_3_2_1_17_1","volume-title":"VISTA: Visual-Textual Knowledge Graph Representation Learning. In EMNLP.","author":"Lee Jaejun","year":"2023","unstructured":"Jaejun Lee, Chanyoung Chung, Hochang Lee, Sungho Jo, and Joyce Whang. 2023. VISTA: Visual-Textual Knowledge Graph Representation Learning. In EMNLP."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583554"},{"key":"e_1_3_2_1_19_1","volume-title":"Hyper-node relational graph attention network for multi-modal knowledge graph completion. ACM Transactions on Multimedia Computing, Communications and Applications","author":"Liang Shuang","year":"2023","unstructured":"Shuang Liang, Anjie Zhu, Jiasheng Zhang, and Jie Shao. 2023. Hyper-node relational graph attention network for multi-modal knowledge graph completion. ACM Transactions on Multimedia Computing, Communications and Applications (2023)."},{"key":"e_1_3_2_1_20_1","volume-title":"International conference on machine learning. PMLR.","author":"Liu Hanxiao","year":"2017","unstructured":"Hanxiao Liu, Yuexin Wu, and Yiming Yang. 2017. Analogical inference for multi-relational embeddings. In International conference on machine learning. PMLR."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"crossref","unstructured":"Ye Liu Hui Li Alberto Garcia-Duran Mathias Niepert Daniel Onoro-Rubio and David S Rosenblum. 2019. MMKG: multi-modal knowledge graphs. In ESWC.","DOI":"10.1007\/978-3-030-21348-0_30"},{"key":"e_1_3_2_1_22_1","volume-title":"MMKRL: A robust embedding approach for multi-modal knowledge graph representation learning. Applied Intelligence","author":"Lu Xinyu","year":"2022","unstructured":"Xinyu Lu, Lifang Wang, Zejun Jiang, Shichang He, and Shizhong Liu. 2022. MMKRL: A robust embedding approach for multi-modal knowledge graph representation learning. Applied Intelligence (2022), 1--18."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"crossref","unstructured":"Hatem Mousselly-Sergieh Teresa Botschen Iryna Gurevych and Stefan Roth. 2018. A multimodal translation-based approach for knowledge graph representation learning. In SEMEAVL. 225--234.","DOI":"10.18653\/v1\/S18-2027"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"crossref","unstructured":"Hatem Mousselly-Sergieh Teresa Botschen Iryna Gurevych and Stefan Roth. 2018. A multimodal translation-based approach for knowledge graph representation learning. In AACL. 225--234.","DOI":"10.18653\/v1\/S18-2027"},{"key":"e_1_3_2_1_25_1","volume-title":"A review of relational machine learning for knowledge graphs. Proc","author":"Nickel Maximilian","year":"2015","unstructured":"Maximilian Nickel, Kevin Murphy, Volker Tresp, and Evgeniy Gabrilovich. 2015. A review of relational machine learning for knowledge graphs. Proc. IEEE (2015)."},{"key":"e_1_3_2_1_26_1","unstructured":"Daniel O noro-Rubio Mathias Niepert Alberto Garc\u00eda-Dur\u00e1n Roberto Gonz\u00e1lez-S\u00e1nchez and Roberto J L\u00f3pez-Sastre. 2019. Answering Visual-Relational Queries in Web-Extracted Knowledge Graphs. (2019)."},{"key":"e_1_3_2_1_27_1","volume-title":"Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, et al. 2019. Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems, Vol. 32 (2019)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"crossref","unstructured":"Pouya Pezeshkpour Liyan Chen and Sameer Singh. 2018. Embedding Multimodal Relational Data for Knowledge Base Completion. In EMNLP.","DOI":"10.18653\/v1\/D18-1359"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"crossref","unstructured":"Chao Shang Yun Tang Jing Huang Jinbo Bi Xiaodong He and Bowen Zhou. 2019. End-to-end structure-aware convolutional networks for knowledge base completion. In AAAI.","DOI":"10.1609\/aaai.v33i01.33013060"},{"key":"e_1_3_2_1_30_1","volume-title":"Very deep convolutional networks for large-scale image recognition. ICLR","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. ICLR (2014)."},{"key":"e_1_3_2_1_31_1","volume-title":"International Conference on Learning Representations.","author":"Sun Zhiqing","year":"2019","unstructured":"Zhiqing Sun, Zhi-Hong Deng, Jian-Yun Nie, and Jian Tang. 2019. RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"crossref","unstructured":"Yun Tang Jing Huang Guangtao Wang Xiaodong He and Bowen Zhou. 2020. Orthogonal Relation Transforms with Graph Context Modeling for Knowledge Graph Embedding. In ACL. 2713--2722.","DOI":"10.18653\/v1\/2020.acl-main.241"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.bdr.2020.100159"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475470"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"crossref","unstructured":"Xin Wang Benyuan Meng Hong Chen Yuan Meng Ke Lv and Wenwu Zhu. 2023. TIVA-KG: A multimodal knowledge graph with text image video and audio. In ACM MM. 2391--2399.","DOI":"10.1145\/3581783.3612266"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"crossref","unstructured":"Zikang Wang Linjing Li Qiudan Li and Daniel Zeng. 2019. Multimodal data enhanced representation learning for knowledge graphs. In IJCNN. 1--8.","DOI":"10.1109\/IJCNN.2019.8852079"},{"key":"e_1_3_2_1_37_1","volume-title":"Mmpedia: A large-scale multi-modal knowledge graph. In ISWC.","author":"Wu Yinan","year":"2023","unstructured":"Yinan Wu, Xiaowei Wu, Junwen Li, Yue Zhang, Haofen Wang, Wen Du, Zhidong He, Jingping Liu, and Tong Ruan. 2023. Mmpedia: A large-scale multi-modal knowledge graph. In ISWC."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"crossref","unstructured":"Zhebin Wu Lin Shu Ziyue Xu Yaomin Chang Chuan Chen and Zibin Zheng. 2022. Robust tensor graph convolutional networks via t-svd based graph augmentation. In KDD. 2090--2099.","DOI":"10.1145\/3534678.3539436"},{"key":"e_1_3_2_1_39_1","unstructured":"Ruobing Xie Zhiyuan Liu Huanbo Luan and Maosong Sun. 2017. Image-embodied Knowledge Representation Learning. In IJCAI."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"crossref","unstructured":"Derong Xu Tong Xu Shiwei Wu Jingbo Zhou and Enhong Chen. 2022. Relation-enhanced negative sampling for multimodal knowledge graph completion. In ACM MM. 3857--3866.","DOI":"10.1145\/3503161.3548388"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"crossref","unstructured":"Derong Xu Tong Xu Shiwei Wu Jingbo Zhou and Enhong Chen. 2022. Relation-enhanced negative sampling for multimodal knowledge graph completion. In ACM MM. 3857--3866.","DOI":"10.1145\/3503161.3548388"},{"key":"e_1_3_2_1_42_1","volume-title":"Xiaodong He, Jianfeng Gao, and Li Deng.","author":"Yang Bishan","year":"2015","unstructured":"Bishan Yang, Scott Wen-tau Yih, Xiaodong He, Jianfeng Gao, and Li Deng. 2015. Embedding Entities and Relations for Learning and Inference in Knowledge Bases. In ICLR."},{"key":"e_1_3_2_1_43_1","volume-title":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases.","author":"Zhang Xuan","year":"2022","unstructured":"Xuan Zhang, Xun Liang, Xiangping Zheng, Bo Wu, and Yuhui Guo. 2022. MULTIFORM: few-shot knowledge graph completion via multi-modal contexts. In Joint European Conference on Machine Learning and Knowledge Discovery in Databases."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"crossref","unstructured":"Yichi Zhang Mingyang Chen and Wen Zhang. 2023. Modality-aware negative sampling for multi-modal knowledge graph embedding. In IJCNN. 1--8.","DOI":"10.1109\/IJCNN54540.2023.10191314"},{"key":"e_1_3_2_1_45_1","volume-title":"Unleashing the Power of Imbalanced Modality Information for Multi-modal Knowledge Graph Completion. LREC-COLING","author":"Zhang Yichi","year":"2024","unstructured":"Yichi Zhang, Zhuo Chen, Lei Liang, Huajun Chen, and Wen Zhang. 2024. Unleashing the Power of Imbalanced Modality Information for Multi-modal Knowledge Graph Completion. LREC-COLING (2024)."},{"key":"e_1_3_2_1_46_1","volume-title":"Knowledge graph completion with pre-trained multimodal transformer and twins negative sampling. CoRR","author":"Zhang Yichi","year":"2022","unstructured":"Yichi Zhang and Wen Zhang. 2022. Knowledge graph completion with pre-trained multimodal transformer and twins negative sampling. CoRR (2022)."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.3005952"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.719"},{"key":"e_1_3_2_1_49_1","volume-title":"JointE: Jointly utilizing 1D and 2D convolution for knowledge graph embedding. Knowledge-Based Systems","author":"Zhou Zhehui","year":"2022","unstructured":"Zhehui Zhou, Can Wang, Yan Feng, and Defang Chen. 2022. JointE: Jointly utilizing 1D and 2D convolution for knowledge graph embedding. Knowledge-Based Systems (2022)."}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681696","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681696","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:50Z","timestamp":1750295870000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681696"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":49,"alternative-id":["10.1145\/3664647.3681696","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681696","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}