{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T08:19:05Z","timestamp":1783153145746,"version":"3.54.6"},"publisher-location":"New York, NY, USA","reference-count":52,"publisher":"ACM","funder":[{"name":"National Key Research and Development Program of China","award":["2023YFC3303800"],"award-info":[{"award-number":["2023YFC3303800"]}]},{"name":"National Natural Science Foundation of China","award":["62402491"],"award-info":[{"award-number":["62402491"]}]},{"name":"National Natural Science Foundation of China","award":["62472416"],"award-info":[{"award-number":["62472416"]}]},{"name":"National Natural Science Foundation of China","award":["U25B2029"],"award-info":[{"award-number":["U25B2029"]}]},{"name":"National Natural Science Foundation of China","award":["62322202"],"award-info":[{"award-number":["62322202"]}]},{"name":"China Postdoctoral Science Foundation","award":["2025M771524"],"award-info":[{"award-number":["2025M771524"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,13]]},"DOI":"10.1145\/3774904.3792491","type":"proceedings-article","created":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T12:38:33Z","timestamp":1777293513000},"page":"7318-7329","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["MuVaC: A Variational Causal Framework for Multimodal Sarcasm Understanding in Dialogues"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-8468-3285","authenticated-orcid":false,"given":"Diandian","family":"Guo","sequence":"first","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China and School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6368-8784","authenticated-orcid":false,"given":"Fangfang","family":"Yuan","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China and School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1881-1947","authenticated-orcid":false,"given":"Cong","family":"Cao","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China and School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-6645-0597","authenticated-orcid":false,"given":"Xixun","family":"Lin","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9958-8673","authenticated-orcid":false,"given":"Chuan","family":"Zhou","sequence":"additional","affiliation":[{"name":"Academy of Mathematics and Systems Science, Chinese Academy of Sciences, Beijing, China and School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0458-5977","authenticated-orcid":false,"given":"Hao","family":"Peng","sequence":"additional","affiliation":[{"name":"Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0811-4016","authenticated-orcid":false,"given":"Yanan","family":"Cao","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Science, Beijing, China and School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9653-073X","authenticated-orcid":false,"given":"Yanbing","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China and School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,4,12]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00971"},{"key":"e_1_3_2_1_2_1","volume-title":"Divyank Tiwari, Anjan Dutta, Xiatian Zhu, Pushpak Bhattacharyya, and Diptesh Kanojia.","author":"Bhosale Swapnil","year":"2023","unstructured":"Swapnil Bhosale, Abhra Chaudhuri, Alex Lee Robert Williams, Divyank Tiwari, Anjan Dutta, Xiatian Zhu, Pushpak Bhattacharyya, and Diptesh Kanojia. 2023. Sarcasm in Sight and Sound: Benchmarking and Expansion to Improve Multimodal Sarcasm Detection. arXiv preprint arXiv:2310.01430 (2023)."},{"key":"e_1_3_2_1_3_1","first-page":"2506","article-title":"Multi-modal sarcasm detection in twitter with hierarchical fusion model","author":"Cai Yitao","year":"2019","unstructured":"Yitao Cai, Huiyu Cai, and Xiaojun Wan. 2019. Multi-modal sarcasm detection in twitter with hierarchical fusion model. In Proceedings of the ACL. 2506-2515.","journal-title":"Proceedings of the ACL."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1455"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.401"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.522"},{"key":"e_1_3_2_1_7_1","first-page":"107","article-title":"Semi-supervised recognition of sarcasm in Twitter and Amazon","author":"Davidov Dmitry","year":"2010","unstructured":"Dmitry Davidov, Oren Tsur, and Ari Rappoport. 2010. Semi-supervised recognition of sarcasm in Twitter and Amazon. In Proceedings of the CoNLL. 107-116.","journal-title":"Proceedings of the CoNLL."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3348"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21300"},{"key":"e_1_3_2_1_10_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_11_1","volume-title":"Sentiment Analysis in Social Networks","author":"Hern\u00e1ndez Farias DI","unstructured":"DI Hern\u00e1ndez Farias and Paolo Rosso. 2017. Irony, sarcasm, and sentiment analysis. In Sentiment Analysis in Social Networks. Elsevier, 113-128."},{"key":"e_1_3_2_1_12_1","volume-title":"Proceedings of Meetings on Acoustics","volume":"54","author":"Gao Xiyuan","year":"2024","unstructured":"Xiyuan Gao, Shekhar Nayak, and Matt Coler. 2024. Improving sarcasm detection from speech and text through attention-based fusion exploiting the interplay of emotions and sentiments. In Proceedings of Meetings on Acoustics, Vol. 54. Acoustical Society of America, 060002."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.4324\/9781410616685"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-92307-5_21"},{"key":"e_1_3_2_1_15_1","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence (Sep","author":"Hasan Md Kamrul","year":"2022","unstructured":"Md Kamrul Hasan, Sangwu Lee, Wasifur Rahman, Amir Zadeh, Rada Mihalcea, Louis-Philippe Morency, and Ehsan Hoque. 2022. Humor Knowledge Enriched Transformer for Understanding Multimodal Humor. Proceedings of the AAAI Conference on Artificial Intelligence (Sep 2022), 12972\u201312980."},{"key":"e_1_3_2_1_16_1","volume-title":"Do Androids Laugh at Electric Sheep? Humor ''Understanding'' Benchmarks from The New Yorker Caption Contest. arXiv preprint arXiv:2209.06293","author":"Hessel Jack","year":"2023","unstructured":"Jack Hessel, Ana Marasovi?, Jena D. Hwang, Lillian Lee, Jeff Da, Rowan Zellers, Robert Mankoff, and Yejin Choi. 2023. Do Androids Laugh at Electric Sheep? Humor ''Understanding'' Benchmarks from The New Yorker Caption Contest. arXiv preprint arXiv:2209.06293 (2023)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.635"},{"key":"e_1_3_2_1_18_1","unstructured":"Glenn Jocher Ayush Chaurasia and Jing Qiu. 2023. YOLO by Ultralytics. https:\/\/github.com\/ultralytics\/ultralytics"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1080\/10350330.2018.1504732"},{"key":"e_1_3_2_1_20_1","volume-title":"Md Shad Akhtar, and Tanmoy Chakraborty","author":"Kumar Shivani","year":"2022","unstructured":"Shivani Kumar, Atharva Kulkarni, Md Shad Akhtar, and Tanmoy Chakraborty. 2022. When did you become so smart, oh wise one?! sarcasm explanation in multi-modal multi-party dialogues. arXiv preprint arXiv:2203.06419 (2022)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i11.26526"},{"key":"e_1_3_2_1_22_1","volume-title":"Bart: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. arXiv preprint arXiv:1910.13461","author":"Lewis Mike","year":"2019","unstructured":"Mike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad, Abdelrahman Mohamed, Omer Levy, Ves Stoyanov, and Luke Zettlemoyer. 2019. Bart: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. arXiv preprint arXiv:1910.13461 (2019)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.111457"},{"key":"e_1_3_2_1_24_1","volume-title":"ROUGE: A Package for Automatic Evaluation of Summaries. Meeting of the Association for Computational Linguistics,Meeting of the Association for Computational Linguistics (Jul","author":"Lin Chin-Yew","year":"2004","unstructured":"Chin-Yew Lin. 2004. ROUGE: A Package for Automatic Evaluation of Summaries. Meeting of the Association for Computational Linguistics,Meeting of the Association for Computational Linguistics (Jul 2004)."},{"key":"e_1_3_2_1_25_1","volume-title":"Hallucinations: A Survey of Taxonomy, Methods, and Directions. arXiv preprint arXiv:2509.18970","author":"Lin Xixun","year":"2025","unstructured":"Xixun Lin, Yucheng Ning, Jingwen Zhang, Yan Dong, Yilong Liu, Yongxuan Wu, Xiaohua Qi, Nan Sun, Yanmin Shang, Kun Wang, et al., 2025a. LLM-based Agents Suffer from Hallucinations: A Survey of Taxonomy, Methods, and Directions. arXiv preprint arXiv:2509.18970 (2025)."},{"key":"e_1_3_2_1_26_1","volume-title":"Generative Causality-driven Network for Graph Multi-task Learning","author":"Lin Xixun","year":"2025","unstructured":"Xixun Lin, Qing Yu, Yanan Cao, Lixin Zou, Chuan Zhou, Jia Wu, Chenliang Li, Peng Zhang, and Shirui Pan. 2025b. Generative Causality-driven Network for Graph Multi-task Learning. IEEE transactions on pattern analysis and machine intelligence (2025)."},{"key":"e_1_3_2_1_27_1","volume-title":"Multilingual denoising pre-training for neural machine translation. arXiv preprint arXiv:2001.08210","author":"Liu Y","year":"2020","unstructured":"Y Liu. 2020. Multilingual denoising pre-training for neural machine translation. arXiv preprint arXiv:2001.08210 (2020)."},{"key":"e_1_3_2_1_28_1","volume-title":"Jointly Detecting Multi-Modal Sarcasm and Sentiment Using Quantum Probability. In Findings of the Association for Computational Linguistics: EMNLP","author":"Liu Yaochen","year":"2021","unstructured":"Yaochen Liu, Yazhou Zhang, Qiuchi Li, Benyou Wang, and Dawei Song. 2021. What Does Your Smile Mean? Jointly Detecting Multi-Modal Sarcasm and Sentiment Using Quantum Probability. In Findings of the Association for Computational Linguistics: EMNLP 2021."},{"key":"e_1_3_2_1_29_1","volume-title":"Lrec 2014 proceedings. ELRA.","author":"Maynard Diana G","year":"2014","unstructured":"Diana G Maynard and Mark A Greenwood. 2014. Who cares about sarcastic tweets? investigating the impact of sarcasm on sentiment analysis. In Lrec 2014 proceedings. ELRA."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3565959"},{"key":"e_1_3_2_1_31_1","volume-title":"VyAnG-Net: A Novel Multi-Modal Sarcasm Recognition Model by Uncovering Visual, Acoustic and Glossary Features. arXiv preprint arXiv:2408.10246","author":"Pandey Ananya","year":"2024","unstructured":"Ananya Pandey and Dinesh Kumar Vishwakarma. 2024. VyAnG-Net: A Novel Multi-Modal Sarcasm Recognition Model by Uncovering Visual, Acoustic and Glossary Features. arXiv preprint arXiv:2408.10246 (2024)."},{"key":"e_1_3_2_1_32_1","volume-title":"BLEU. In Proceedings of the 40th Annual Meeting on Association for Computational Linguistics - ACL '02.","author":"Papineni Kishore","year":"2001","unstructured":"Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2001. BLEU. In Proceedings of the 40th Annual Meeting on Association for Computational Linguistics - ACL '02."},{"key":"e_1_3_2_1_33_1","volume-title":"International conference on machine learning. PmLR, 8748-8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al., 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PmLR, 8748-8763."},{"key":"e_1_3_2_1_34_1","first-page":"6992","volume-title":"Proceedings of the Thirteenth Language Resources and Evaluation Conference. European Language Resources Association","author":"Ray Anupama","year":"2022","unstructured":"Anupama Ray, Shubham Mishra, Apoorva Nunna, and Pushpak Bhattacharyya. 2022. A Multimodal Corpus for Emotion Recognition in Sarcasm. In Proceedings of the Thirteenth Language Resources and Evaluation Conference. European Language Resources Association, Marseille, France, 6992-7003."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"e_1_3_2_1_36_1","volume-title":"TimesFormer, and Wav2Vec 2.0 with MUStARD.","author":"Shi Erin","year":"2024","unstructured":"Erin Shi. 2024. Multimodal Sarcasm Detection Using BERT, TimesFormer, and Wav2Vec 2.0 with MUStARD. (2024)."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29864"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548211"},{"key":"e_1_3_2_1_39_1","volume-title":"Siu Cheung Hui, and Jian Su.","author":"Tay Yi","year":"2018","unstructured":"Yi Tay, Anh Tuan Luu, Siu Cheung Hui, and Jian Su. 2018. Reasoning with Sarcasm by Reading In-Between. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Iryna Gurevych and Yusuke Miyao (Eds.). Association for Computational Linguistics, 1010-1020."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612528"},{"key":"e_1_3_2_1_41_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Wang Haobo","year":"2024","unstructured":"Haobo Wang, Yiwen Dong, Ruixuan Xiao, Fei Huang, Gang Chen, and Junbo Zhao. 2024. Debiased and denoised entity recognition from distant supervision. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/MMUL.2021.3069097"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.262"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"crossref","unstructured":"Tao Xiong Peiran Zhang Hongbo Zhu and Yihui Yang. 2019a. Sarcasm detection with self-matching networks and low-rank bilinear pooling. In The world wide web conference. 2115-2124.","DOI":"10.1145\/3308558.3313735"},{"key":"e_1_3_2_1_46_1","volume-title":"Sarcasm Detection with Self-matching Networks and Low-rank Bilinear Pooling (WWW '19)","author":"Xiong Tao","unstructured":"Tao Xiong, Peiran Zhang, Hongbo Zhu, and Yihui Yang. 2019b. Sarcasm Detection with Self-matching Networks and Low-rank Bilinear Pooling (WWW '19). Association for Computing Machinery, New York, NY, USA, 2115\u20132124."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00238"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01822"},{"key":"e_1_3_2_1_49_1","volume-title":"Causal Attention for Vision-Language Tasks. In 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR).","author":"Yang Xu","year":"2021","unstructured":"Xu Yang, Hanwang Zhang, Guojun Qi, and Jianfei Cai. 2021. Causal Attention for Vision-Language Tasks. In 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_3_2_1_50_1","volume-title":"BERTScore: Evaluating Text Generation with BERT. In International Conference on Learning Representations.","author":"Zhang Tianyi","year":"2020","unstructured":"Tianyi Zhang, Varsha Kishore, Felix Wu, Kilian Q. Weinberger, and Yoav Artzi. 2020. BERTScore: Evaluating Text Generation with BERT. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2024.109884"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3627673.3679570"}],"event":{"name":"WWW '26: The ACM Web Conference 2026","location":"Dubai United Arab Emirates","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the ACM Web Conference 2026"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3774904.3792491","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T07:53:58Z","timestamp":1783151638000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3774904.3792491"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,12]]},"references-count":52,"alternative-id":["10.1145\/3774904.3792491","10.1145\/3774904"],"URL":"https:\/\/doi.org\/10.1145\/3774904.3792491","relation":{},"subject":[],"published":{"date-parts":[[2026,4,12]]},"assertion":[{"value":"2026-04-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}