{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T01:10:24Z","timestamp":1755825024445,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":43,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100006374","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276073"],"award-info":[{"award-number":["62276073"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1145\/3731715.3733312","type":"proceedings-article","created":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T18:31:39Z","timestamp":1750876299000},"page":"1903-1911","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["DMR-XNet: Dynamic Multi-Relation Cross-Fusion Network for Aspect-Based Multimodal Sentiment Analysis"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-6913-8223","authenticated-orcid":false,"given":"Fengling","family":"Zhou","sequence":"first","affiliation":[{"name":"Key Lab of Education Blockchain and Intelligent Technology, Ministry of Education, Guangxi Normal University, Guilin, Guangxi, China and Guangxi Key Lab of Multi-source Information Mining and Security, Guangxi Normal University, Guilin, Guangxi, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5313-6134","authenticated-orcid":false,"given":"Zhixin","family":"Li","sequence":"additional","affiliation":[{"name":"Key Lab of Education Blockchain and Intelligent Technology, Ministry of Education, Guangxi Normal University, Guilin, Guangxi, China and Guangxi Key Lab of Multi-source Information Mining and Security, Guangxi Normal University, Guilin, Guangxi, China"}]}],"member":"320","published-online":{"date-parts":[[2025,6,30]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.24"},{"key":"e_1_3_2_1_2_1","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 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 Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 4171--4186."},{"key":"e_1_3_2_1_3_1","volume-title":"An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929","author":"Dosovitskiy Alexey","year":"2020","unstructured":"Alexey Dosovitskiy. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1051"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3652583.3658115"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.360"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475692"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475692"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.494"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1310"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-023-10685-z"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.107643"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.13"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.152"},{"key":"e_1_3_2_1_15_1","volume-title":"RoBERTa: A robustly optimized BERT pretraining approach. arXiv preprint arXiv:1907.11692","author":"Liu Y","year":"1907","unstructured":"Y Liu, M Ott, N Goyal, J Du, M Joshi, D Chen, O Levy, M Lewis, L Zettlemoyer, and V Stoyanov. 1907. RoBERTa: A robustly optimized BERT pretraining approach. arXiv preprint arXiv:1907.11692 (1907)."},{"key":"e_1_3_2_1_16_1","volume-title":"Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101","author":"Loshchilov I","year":"2017","unstructured":"I Loshchilov. 2017. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.128874"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29852"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2024.111553"},{"key":"e_1_3_2_1_20_1","volume-title":"Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation. 16187--16197","author":"Wang Di","year":"2024","unstructured":"Di Wang, Yuzheng He, Xiao Liang, Yumin Tian, Shaofeng Li, and Lin Zhao. 2024. TMFN: A Target-oriented Multi-grained Fusion Network for End-to-end Aspect-based Multimodal Sentiment Analysis. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation. 16187--16197."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60450-9_12"},{"key":"e_1_3_2_1_22_1","volume-title":"Google's neural machine translation system: Bridging the gap between human and machine translation. arXiv preprint arXiv:1609.08144","author":"Yonghui Wu.","year":"2016","unstructured":"Yonghui Wu. 2016. Google's neural machine translation system: Bridging the gap between human and machine translation. arXiv preprint arXiv:1609.08144 (2016)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413650"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102304"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2023.103508"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.188"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.219"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.111724"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2022.103038"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"crossref","unstructured":"Xiaocui Yang Shi Feng Daling Wang Sun Qi Wenfang Wu Yifei Zhang Pengfei Hong and Soujanya Poria. 2023. Few-shot joint multimodal aspect-sentiment analysis based on generative multimodal prompt. In Findings of the Association for Computational Linguistics. 11575--11589.","DOI":"10.18653\/v1\/2023.findings-acl.735"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/751"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2957872"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.306"},{"volume-title":"Proceedings of the 2nd Conference of the Asia-Pacific","author":"Yu Zhewen","key":"e_1_3_2_1_34_1","unstructured":"Zhewen Yu, Jin Wang, Liang-Chih Yu, and Xuejie Zhang. 2022. Dual-encoder transformers with cross-modal alignment for multimodal aspect-based sentiment analysis. In Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 414--423."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.107335"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.362"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.561"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-025-06465-7"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"crossref","unstructured":"Ru Zhou Wenya Guo Xumeng Liu Shenglong Yu Ying Zhang and Xiaojie Yuan. 2023. AoM: Detecting aspect-oriented information for multimodal aspect-based sentiment analysis. In Findings of the Association for Computational Linguistics. 8184--8196.","DOI":"10.18653\/v1\/2023.findings-acl.519"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/738"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2024.109884"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3627673.3679570"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.125818"}],"event":{"name":"ICMR '25: International Conference on Multimedia Retrieval","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Chicago IL USA","acronym":"ICMR '25"},"container-title":["Proceedings of the 2025 International Conference on Multimedia Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3731715.3733312","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T04:14:08Z","timestamp":1755749648000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3731715.3733312"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":43,"alternative-id":["10.1145\/3731715.3733312","10.1145\/3731715"],"URL":"https:\/\/doi.org\/10.1145\/3731715.3733312","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]},"assertion":[{"value":"2025-06-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}