{"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":1755825024573,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":35,"publisher":"ACM","funder":[{"name":"National Key Laboratory on Blind Signal Processing","award":["23007522"],"award-info":[{"award-number":["23007522"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1145\/3731715.3733321","type":"proceedings-article","created":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T18:29:43Z","timestamp":1750876183000},"page":"1868-1876","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["EilMoB: Emotion-aware Incongruity Learning and Modality Bridging Network for Multi-modal Sarcasm Detection"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-8593-6079","authenticated-orcid":false,"given":"Haochen","family":"Zhao","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":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2963-0914","authenticated-orcid":false,"given":"Yongxiu","family":"Xu","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":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-6941-7305","authenticated-orcid":false,"given":"Xinkui","family":"Lin","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":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4512-1004","authenticated-orcid":false,"given":"Jiarui","family":"Lu","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":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0258-7840","authenticated-orcid":false,"given":"Hongbo","family":"Xu","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6464-3203","authenticated-orcid":false,"given":"Yubin","family":"Wang","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":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,6,30]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Qwen-vl: A versatile vision-language model for understanding, localization, text reading, and beyond. arXiv preprint arXiv:2308.12966 1, 2","author":"Bai Jinze","year":"2023","unstructured":"Jinze Bai, Shuai Bai, Shusheng Yang, Shijie Wang, Sinan Tan, Peng Wang, Junyang Lin, Chang Zhou, and Jingren Zhou. 2023. Qwen-vl: A versatile vision-language model for understanding, localization, text reading, and beyond. arXiv preprint arXiv:2308.12966 1, 2 (2023), 3."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1239"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.522"},{"key":"e_1_3_2_1_4_1","volume-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. CoRR abs\/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. CoRR abs\/1810.04805 (2018). arXiv:1810.04805 http:\/\/arxiv.org\/abs\/1810.04805"},{"key":"e_1_3_2_1_5_1","volume-title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. CoRR abs\/2010.11929","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, Jakob Uszkoreit, and Neil Houlsby. 2020. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. CoRR abs\/2010.11929 (2020). arXiv:2010.11929 https:\/\/arxiv.org\/abs\/2010.11929"},{"key":"e_1_3_2_1_6_1","volume-title":"Framewise phoneme classification with bidirectional LSTM and other neural network architectures. Neural networks 18, 5--6","author":"Graves Alex","year":"2005","unstructured":"Alex Graves and J\u00fcrgen Schmidhuber. 2005. Framewise phoneme classification with bidirectional LSTM and other neural network architectures. Neural networks 18, 5--6 (2005), 602--610."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1609\/icwsm.v8i1.14550"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29795"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-2124"},{"key":"e_1_3_2_1_11_1","volume-title":"Convolutional Neural Networks for Sentence Classification. CoRR abs\/1408.5882","author":"Kim Yoon","year":"2014","unstructured":"Yoon Kim. 2014. Convolutional Neural Networks for Sentence Classification. CoRR abs\/1408.5882 (2014). arXiv:1408.5882 http:\/\/arxiv.org\/abs\/1408.5882"},{"key":"e_1_3_2_1_12_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_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3643829"},{"key":"e_1_3_2_1_14_1","first-page":"17612","article-title":"Mind the gap: Understanding the modality gap in multi-modal contrastive representation learning","volume":"35","author":"Liang Victor Weixin","year":"2022","unstructured":"Victor Weixin Liang, Yuhui Zhang, Yongchan Kwon, Serena Yeung, and James Y Zou. 2022. Mind the gap: Understanding the modality gap in multi-modal contrastive representation learning. Advances in Neural Information Processing Systems 35 (2022), 17612--17625.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_15_1","volume-title":"Towards multi-modal sarcasm detection via hierarchical congruity modeling with knowledge enhancement. arXiv preprint arXiv:2210.03501","author":"Liu Hui","year":"2022","unstructured":"Hui Liu, Wenya Wang, and Haoliang Li. 2022. Towards multi-modal sarcasm detection via hierarchical congruity modeling with knowledge enhancement. arXiv preprint arXiv:2210.03501 (2022)."},{"key":"e_1_3_2_1_16_1","volume-title":"Decoupled Weight Decay Regularization. In 7th International Conference on Learning Representations, ICLR 2019","author":"Loshchilov Ilya","year":"2019","unstructured":"Ilya Loshchilov and Frank Hutter. 2019. Decoupled Weight Decay Regularization. In 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, May 6-9, 2019. OpenReview.net. https:\/\/openreview.net\/forum? id=Bkg6RiCqY7"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.124"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i8.26138"},{"key":"e_1_3_2_1_19_1","volume-title":"0: towards a reliable multi-modal sarcasm detection system. arXiv preprint arXiv:2307.07135","author":"Qin Libo","year":"2023","unstructured":"Libo Qin, Shijue Huang, Qiguang Chen, Chenran Cai, Yudi Zhang, Bin Liang, Wanxiang Che, and Ruifeng Xu. 2023. MMSD2. 0: towards a reliable multi-modal sarcasm detection system. arXiv preprint arXiv:2307.07135 (2023)."},{"key":"e_1_3_2_1_20_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_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/2684822.2685316"},{"key":"e_1_3_2_1_22_1","volume-title":"Automatic keyword extraction from individual documents. Text mining: applications and theory","author":"Rose Stuart","year":"2010","unstructured":"Stuart Rose, Dave Engel, Nick Cramer, and Wendy Cowley. 2010. Automatic keyword extraction from individual documents. Text mining: applications and theory (2010), 1--20."},{"key":"e_1_3_2_1_23_1","volume-title":"How to bridge the gap between modalities: A comprehensive survey on multimodal large language model. arXiv preprint arXiv:2311.07594","author":"Song Shezheng","year":"2023","unstructured":"Shezheng Song, Xiaopeng Li, Shasha Li, Shan Zhao, Jie Yu, Jun Ma, Xiaoguang Mao, and Weimin Zhang. 2023. How to bridge the gap between modalities: A comprehensive survey on multimodal large language model. arXiv preprint arXiv:2311.07594 (2023)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.97"},{"key":"e_1_3_2_1_25_1","unstructured":"Peng Wang Shuai Bai Sinan Tan Shijie Wang Zhihao Fan Jinze Bai Keqin Chen Xuejing Liu Jialin Wang Wenbin Ge et al. 2024. Qwen2-vl: Enhancing vision-language model's perception of the world at any resolution. arXiv preprint arXiv:2409.12191 (2024)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i4.25594"},{"key":"e_1_3_2_1_27_1","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","volume":"38","author":"Wei Yiwei","year":"2024","unstructured":"Yiwei Wei, Shaozu Yuan, Hengyang Zhou, Longbiao Wang, Zhiling Yan, Ruosong Yang, and Meng Chen. 2024. G\u02c6 2SAM: Graph-Based Global Semantic Awareness Method for Multimodal Sarcasm Detection. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 38. 9151--9159."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00250"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"crossref","unstructured":"Tao Xiong Peiran Zhang Hongbo Zhu and Yihui Yang. 2019. 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_30_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.349"},{"key":"e_1_3_2_1_31_1","first-page":"1","article-title":"Detection of harassment on web 2.0","volume":"2","author":"Yin Dawei","year":"2009","unstructured":"Dawei Yin, Zhenzhen Xue, Liangjie Hong, Brian D Davison, April Kontostathis, Lynne Edwards, et al. 2009. Detection of harassment on web 2.0. Proceedings of the Content Analysis in the WEB 2, 0 (2009), 1--7.","journal-title":"Proceedings of the Content Analysis in the WEB"},{"key":"e_1_3_2_1_32_1","volume-title":"A survey on multimodal large language models. arXiv preprint arXiv:2306.13549","author":"Yin Shukang","year":"2023","unstructured":"Shukang Yin, Chaoyou Fu, Sirui Zhao, Ke Li, Xing Sun, Tong Xu, and Enhong Chen. 2023. A survey on multimodal large language models. arXiv preprint arXiv:2306.13549 (2023)."},{"key":"e_1_3_2_1_33_1","volume-title":"Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: technical papers. 2449--2460","author":"Zhang Meishan","year":"2016","unstructured":"Meishan Zhang, Yue Zhang, and Guohong Fu. 2016. Tweet sarcasm detection using deep neural network. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: technical papers. 2449--2460."},{"key":"e_1_3_2_1_34_1","unstructured":"Wayne Xin Zhao Kun Zhou Junyi Li Tianyi Tang Xiaolei Wang Yupeng Hou Yingqian Min Beichen Zhang Junjie Zhang Zican Dong et al. 2023. A survey of large language models. arXiv preprint arXiv:2303.18223 (2023)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/739"}],"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\/3731715.3733321","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T04:09:38Z","timestamp":1755749378000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3731715.3733321"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":35,"alternative-id":["10.1145\/3731715.3733321","10.1145\/3731715"],"URL":"https:\/\/doi.org\/10.1145\/3731715.3733321","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"}}]}}