{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T15:57:27Z","timestamp":1781539047120,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":44,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T00:00:00Z","timestamp":1781481600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,6,16]]},"DOI":"10.1145\/3805622.3810756","type":"proceedings-article","created":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T14:42:57Z","timestamp":1781534577000},"page":"672-680","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["TASEN: Topic-Aware Semantic Enhancement Network for Multimodal Named Entity Recognition"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9548-7701","authenticated-orcid":false,"given":"Guohui","family":"Ding","sequence":"first","affiliation":[{"name":"Shenyang Aerospace Universtiy, Shenyang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-9898-0750","authenticated-orcid":false,"given":"Chufei","family":"Wang","sequence":"additional","affiliation":[{"name":"Shenyang Aerospace University, Shenyang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-3577-3066","authenticated-orcid":false,"given":"Hongfeng","family":"Wang","sequence":"additional","affiliation":[{"name":"AVIC Shenyang Aircraft Industry (Group) Co., Ltd., Shenyang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4415-838X","authenticated-orcid":false,"given":"Zakovorotnyi","family":"Oleksandr","sequence":"additional","affiliation":[{"name":"National Technical University Kharkiv Polytechnic Institute, Kharkiv, Ukraine"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,15]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4614-3223-4_4"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"crossref","unstructured":"Majid\u00a0Hameed Ahmed Sabrina Tiun Nazlia Omar and Nor\u00a0Samsiah Sani. 2022. Short text clustering algorithms application and challenges: A survey. Applied Sciences 13 1 (2022) 342.","DOI":"10.3390\/app13010342"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00061"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICEEOT.2016.7754750"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3614975"},{"key":"e_1_3_3_1_7_2","unstructured":"David\u00a0M Blei Andrew\u00a0Y Ng and Michael\u00a0I Jordan. 2003. Latent dirichlet allocation. Journal of machine Learning research 3 Jan (2003) 993\u20131022."},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.wnut-1.11"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"crossref","unstructured":"Xiang Chen Ningyu Zhang Lei Li Yunzhi Yao Shumin Deng Chuanqi Tan Fei Huang Luo Si and Huajun Chen. 2022. Good visual guidance makes a better extractor: Hierarchical visual prefix for multimodal entity and relation extraction. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2205.03521 (2022).","DOI":"10.18653\/v1\/2022.findings-naacl.121"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"crossref","unstructured":"Scott Deerwester Susan\u00a0T Dumais George\u00a0W Furnas Thomas\u00a0K Landauer and Richard Harshman. 1990. Indexing by latent semantic analysis. Journal of the American society for information science 41 6 (1990) 391\u2013407.","DOI":"10.1002\/(SICI)1097-4571(199009)41:6<391::AID-ASI1>3.0.CO;2-9"},{"key":"e_1_3_3_1_11_2","unstructured":"Jacob Devlin Ming-Wei Chang Kenton Lee and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1810.04805 (2018)."},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"crossref","unstructured":"Roman Egger and Joanne Yu. 2022. A topic modeling comparison between lda nmf top2vec and bertopic to demystify twitter posts. Frontiers in sociology 7 (2022) 886498.","DOI":"10.3389\/fsoc.2022.886498"},{"key":"e_1_3_3_1_13_2","first-page":"226","volume-title":"kdd","author":"Ester Martin","year":"1996","unstructured":"Martin Ester, Hans-Peter Kriegel, J\u00f6rg Sander, Xiaowei Xu, et\u00a0al. 1996. A density-based algorithm for discovering clusters in large spatial databases with noise. In kdd , Vol.\u00a096. 226\u2013231."},{"key":"e_1_3_3_1_14_2","first-page":"376","volume-title":"International Symposium on Artificial Intelligence and Robotics","author":"Gan Lin","year":"2023","unstructured":"Lin Gan, Tao Yang, Yifan Huang, Boxiong Yang, Yami\u00a0Yanwen Luo, Lui Wing\u00a0Cheung Richard, and Dabo Guo. 2023. Experimental comparison of three topic modeling methods with LDA, Top2Vec and BERTopic. In International Symposium on Artificial Intelligence and Robotics. Springer, 376\u2013391."},{"key":"e_1_3_3_1_15_2","unstructured":"Octavian Ganea Gary B\u00e9cigneul and Thomas Hofmann. 2018. Hyperbolic neural networks. Advances in neural information processing systems 31 (2018)."},{"key":"e_1_3_3_1_16_2","unstructured":"Maarten Grootendorst. 2022. BERTopic: Neural topic modeling with a class-based TF-IDF procedure. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2203.05794 (2022)."},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.63317\/26e4yx7gpgmd"},{"key":"e_1_3_3_1_18_2","unstructured":"Zhiheng Huang Wei Xu and Kai Yu. 2015. Bidirectional LSTM-CRF models for sequence tagging. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1508.01991 (2015)."},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i7.25971"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"crossref","unstructured":"Guillaume Lample Miguel Ballesteros Sandeep Subramanian Kazuya Kawakami and Chris Dyer. 2016. Neural architectures for named entity recognition. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1603.01360 (2016).","DOI":"10.18653\/v1\/N16-1030"},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1313"},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"crossref","unstructured":"Jing Li Aixin Sun Jianglei Han and Chenliang Li. 2020. A survey on deep learning for named entity recognition. IEEE transactions on knowledge and data engineering 34 1 (2020) 50\u201370.","DOI":"10.1109\/TKDE.2020.2981314"},{"key":"e_1_3_3_1_23_2","unstructured":"Liunian\u00a0Harold Li Mark Yatskar Da Yin Cho-Jui Hsieh and Kai-Wei Chang. 2019. Visualbert: A simple and performant baseline for vision and language. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1908.03557 (2019)."},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1185"},{"key":"e_1_3_3_1_25_2","unstructured":"Xuezhe Ma and Eduard Hovy. 2016. End-to-end sequence labeling via bi-directional lstm-cnns-crf. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1603.01354 (2016)."},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"crossref","unstructured":"M\u00f3nica Marrero Juli\u00e1n Urbano Sonia S\u00e1nchez-Cuadrado Jorge Morato and Juan\u00a0Miguel G\u00f3mez-Berb\u00eds. 2013. Named entity recognition: fallacies challenges and opportunities. Computer Standards & Interfaces 35 5 (2013) 482\u2013489.","DOI":"10.1016\/j.csi.2012.09.004"},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/1281192.1281246"},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403242"},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273576"},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1078"},{"key":"e_1_3_3_1_31_2","doi-asserted-by":"crossref","unstructured":"David Nadeau and Satoshi Sekine. 2007. A survey of named entity recognition and classification. Lingvisticae Investigationes 30 1 (2007) 3\u201326.","DOI":"10.1075\/li.30.1.03nad"},{"key":"e_1_3_3_1_32_2","unstructured":"Maximillian Nickel and Douwe Kiela. 2017. Poincar\u00e9 embeddings for learning hierarchical representations. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_3_1_33_2","first-page":"8748","volume-title":"International conference on machine learning","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong\u00a0Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et\u00a0al. 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PmLR, 8748\u20138763."},{"key":"e_1_3_3_1_34_2","unstructured":"Murat Sensoy Lance Kaplan and Melih Kandemir. 2018. Evidential deep learning to quantify classification uncertainty. Advances in neural information processing systems 31 (2018)."},{"key":"e_1_3_3_1_35_2","unstructured":"Nitish Srivastava and Russ\u00a0R Salakhutdinov. 2012. Multimodal learning with deep boltzmann machines. Advances in neural information processing systems 25 (2012)."},{"key":"e_1_3_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i15.17633"},{"key":"e_1_3_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1145\/3652583.3658097"},{"key":"e_1_3_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612470"},{"key":"e_1_3_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1145\/3488560.3498475"},{"key":"e_1_3_3_1_40_2","unstructured":"Jianfei Yu Jing Jiang Li Yang and Rui Xia. 2020. Improving multimodal named entity recognition via entity span detection with unified multimodal transformer. Association for Computational Linguistics."},{"key":"e_1_3_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i16.17687"},{"key":"e_1_3_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11962"},{"key":"e_1_3_3_1_43_2","doi-asserted-by":"publisher","DOI":"10.1145\/3539597.3570485"},{"key":"e_1_3_3_1_44_2","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548228"},{"key":"e_1_3_3_1_45_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.422"}],"event":{"name":"ICMR '26: International Conference on Multimedia Retrieval","location":"Amsterdam The Netherlands","acronym":"ICMR '26","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 2026 International Conference on Multimedia Retrieval"],"original-title":[],"deposited":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T15:33:57Z","timestamp":1781537637000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805622.3810756"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,15]]},"references-count":44,"alternative-id":["10.1145\/3805622.3810756","10.1145\/3805622"],"URL":"https:\/\/doi.org\/10.1145\/3805622.3810756","relation":{},"subject":[],"published":{"date-parts":[[2026,6,15]]},"assertion":[{"value":"2026-06-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}