{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T18:48:30Z","timestamp":1755802110358,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":42,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,5,30]],"date-time":"2024-05-30T00:00:00Z","timestamp":1717027200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,5,30]]},"DOI":"10.1145\/3652583.3658069","type":"proceedings-article","created":{"date-parts":[[2024,6,7]],"date-time":"2024-06-07T06:30:40Z","timestamp":1717741840000},"page":"1347-1355","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["A Knowledge-Driven Approach to Enhance Topic Modeling with Multi-Modal Representation Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0378-4587","authenticated-orcid":false,"given":"Hongzhang","family":"Mu","sequence":"first","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences & School of Cyber Security, University of Chinese Academy of Sciences, Beijing, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-6196-8263","authenticated-orcid":false,"given":"Shuili","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences & School of Cyber Security, University of Chinese Academy of Sciences, Beijing, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-0498-0743","authenticated-orcid":false,"given":"Hongbo","family":"Xu","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2024,6,7]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2021.10.013"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1609\/icwsm.v12i1.14983"},{"key":"e_1_3_2_1_3_1","volume-title":"Manuel Montes-y G\u00f3mez, and Fabio A Gonz\u00e1lez","author":"Arevalo John","year":"2017","unstructured":"John Arevalo, Thamar Solorio, Manuel Montes-y G\u00f3mez, and Fabio A Gonz\u00e1lez. 2017. Gated multimodal units for information fusion. arXiv preprint arXiv:1702.01992 (2017)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-short.96"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143859"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"crossref","unstructured":"David M Blei and John D Lafferty. 2007. A correlated topic model of science. (2007).","DOI":"10.1214\/07-AOAS114"},{"key":"e_1_3_2_1_8_1","first-page":"993","article-title":"Latent dirichlet allocation","author":"Ng Y","year":"2003","unstructured":"DavidMBlei, AndrewY Ng, and Michael I Jordan. 2003. Latent dirichlet allocation. Journal of machine Learning research 3, Jan (2003), 993--1022.","journal-title":"Journal of machine Learning research 3"},{"key":"e_1_3_2_1_9_1","first-page":"31","article-title":"Normalized (pointwise) mutual information in collocation extraction","volume":"30","author":"Bouma Gerlof","year":"2009","unstructured":"Gerlof Bouma. 2009. Normalized (pointwise) mutual information in collocation extraction. Proceedings of GSCL 30 (2009), 31--40.","journal-title":"Proceedings of GSCL"},{"key":"e_1_3_2_1_10_1","first-page":"1","article-title":"Decoupling Sparsity and Smoothness in the Dirichlet Variational Autoencoder Topic Model","volume":"20","author":"Burkhardt Sophie","year":"2019","unstructured":"Sophie Burkhardt and Stefan Kramer. 2019. Decoupling Sparsity and Smoothness in the Dirichlet Variational Autoencoder Topic Model. J. Mach. Learn. Res. 20, 131 (2019), 1--27.","journal-title":"J. Mach. Learn. Res."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9168"},{"key":"e_1_3_2_1_12_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","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:1810.04805 (2018)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00325"},{"key":"e_1_3_2_1_14_1","volume-title":"Hierarchical topic models and the nested Chinese restaurant process. Advances in neural information processing systems 16","author":"Griffiths Thomas","year":"2003","unstructured":"Thomas Griffiths, Michael Jordan, Joshua Tenenbaum, and David Blei. 2003. Hierarchical topic models and the nested Chinese restaurant process. Advances in neural information processing systems 16 (2003)."},{"key":"e_1_3_2_1_15_1","volume-title":"BERTopic: Neural topic modeling with a class-based TF-IDF procedure. arXiv preprint arXiv:2203.05794","author":"Grootendorst Maarten","year":"2022","unstructured":"Maarten Grootendorst. 2022. BERTopic: Neural topic modeling with a class-based TF-IDF procedure. arXiv preprint arXiv:2203.05794 (2022)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098074"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3074803"},{"key":"e_1_3_2_1_18_1","volume-title":"Structure- CLIP: Enhance Multi-modal Language Representations with Structure Knowledge. arXiv preprint arXiv:2305.06152","author":"Huang Yufeng","year":"2023","unstructured":"Yufeng Huang, Jiji Tang, Zhuo Chen, Rongsheng Zhang, Xinfeng Zhang, Weijie Chen, Zeng Zhao, Tangjie Lv, Zhipeng Hu, and Wen Zhang. 2023. Structure- CLIP: Enhance Multi-modal Language Representations with Structure Knowledge. arXiv preprint arXiv:2305.06152 (2023)."},{"key":"e_1_3_2_1_19_1","volume-title":"Proceedings of naacL-HLT","volume":"1","author":"Ming-Wei Chang Jacob Devlin","year":"2019","unstructured":"Jacob Devlin Ming-Wei Chang Kenton and Lee Kristina Toutanova. 2019. Bert: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of naacL-HLT, Vol. 1. 2."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"e_1_3_2_1_21_1","volume-title":"Neural word embedding as implicit matrix factorization. Advances in neural information processing systems 27","author":"Levy Omer","year":"2014","unstructured":"Omer Levy and Yoav Goldberg. 2014. Neural word embedding as implicit matrix factorization. Advances in neural information processing systems 27 (2014)."},{"key":"e_1_3_2_1_22_1","volume-title":"International Conference on Machine Learning. PMLR, 12888--12900","author":"Li Junnan","year":"2022","unstructured":"Junnan Li, Dongxu Li, Caiming Xiong, and Steven Hoi. 2022. Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In International Conference on Machine Learning. PMLR, 12888--12900."},{"key":"e_1_3_2_1_23_1","volume-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. Advances in neural information processing systems 32","author":"Lu Jiasen","year":"2019","unstructured":"Jiasen Lu, Dhruv Batra, Devi Parikh, and Stefan Lee. 2019. Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. Advances in neural information processing systems 32 (2019)."},{"key":"e_1_3_2_1_24_1","volume-title":"UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction. arXiv:1802.03426 [stat.ML]","author":"McInnes Leland","year":"2020","unstructured":"Leland McInnes, John Healy, and James Melville. 2020. UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction. arXiv:1802.03426 [stat.ML]"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CIDM.2014.7008665"},{"key":"e_1_3_2_1_26_1","volume-title":"Towards a multi-modal, multi-task learning based pre-training framework for document representation learning. arXiv preprint arXiv:2009.14457","author":"Pramanik Subhojeet","year":"2020","unstructured":"Subhojeet Pramanik, Shashank Mujumdar, and Hima Patel. 2020. Towards a multi-modal, multi-task learning based pre-training framework for document representation learning. arXiv preprint arXiv:2009.14457 (2020)."},{"key":"e_1_3_2_1_27_1","volume-title":"Multimodal event topic model for social event analysis","author":"Qian Shengsheng","year":"2015","unstructured":"Shengsheng Qian, Tianzhu Zhang, Changsheng Xu, and Jie Shao. 2015. Multimodal event topic model for social event analysis. IEEE transactions on multimedia 18, 2 (2015), 233--246."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.2992485"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.5555\/3455716.3455856"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/2684822.2685324"},{"key":"e_1_3_2_1_31_1","volume-title":"Autoencoding variational inference for topic models. arXiv preprint arXiv:1703.01488","author":"Srivastava Akash","year":"2017","unstructured":"Akash Srivastava and Charles Sutton. 2017. Autoencoding variational inference for topic models. arXiv preprint arXiv:1703.01488 (2017)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00756"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.is.2020.101582"},{"key":"e_1_3_2_1_34_1","volume-title":"International Conference on Artificial Intelligence and Statistics. PMLR, 1147--1156","author":"Wang Xinyi","year":"2020","unstructured":"Xinyi Wang and Yi Yang. 2020. Neural topic model with attention for supervised learning. In International Conference on Artificial Intelligence and Statistics. PMLR, 1147--1156."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/1148170.1148204"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2951194"},{"key":"e_1_3_2_1_37_1","volume-title":"Enhanced Topic Modeling with Multi-modal Representation Learning. In Pacific-Asia Conference on Knowledge Discovery and Data Mining. Springer, 393--404","author":"Zhang Duoyi","year":"2023","unstructured":"Duoyi Zhang, YueWang, Md Abul Bashar, and Richi Nayak. 2023. Enhanced Topic Modeling with Multi-modal Representation Learning. In Pacific-Asia Conference on Knowledge Discovery and Data Mining. Springer, 393--404."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3147064"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.285"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3013398"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2020.105695"},{"key":"e_1_3_2_1_42_1","volume-title":"Multilingual and Multimodal Topic Modelling with Pretrained Embeddings. arXiv preprint arXiv:2211.08057","author":"Zosa Elaine","year":"2022","unstructured":"Elaine Zosa and Lidia Pivovarova. 2022. Multilingual and Multimodal Topic Modelling with Pretrained Embeddings. arXiv preprint arXiv:2211.08057 (2022)."}],"event":{"name":"ICMR '24: International Conference on Multimedia Retrieval","sponsor":["SIGMM ACM Special Interest Group on Multimedia","SIGSOFT ACM Special Interest Group on Software Engineering"],"location":"Phuket Thailand","acronym":"ICMR '24"},"container-title":["Proceedings of the 2024 International Conference on Multimedia Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3652583.3658069","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3652583.3658069","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T08:51:00Z","timestamp":1755766260000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3652583.3658069"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,30]]},"references-count":42,"alternative-id":["10.1145\/3652583.3658069","10.1145\/3652583"],"URL":"https:\/\/doi.org\/10.1145\/3652583.3658069","relation":{},"subject":[],"published":{"date-parts":[[2024,5,30]]},"assertion":[{"value":"2024-06-07","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}