{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,25]],"date-time":"2026-07-25T04:16:26Z","timestamp":1784952986848,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":36,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681060","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:33Z","timestamp":1729925973000},"page":"447-455","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["Generating Multimodal Metaphorical Features for Meme Understanding"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4135-0683","authenticated-orcid":false,"given":"Bo","family":"Xu","sequence":"first","affiliation":[{"name":"School of Software, Key Laboratory for Ubiquitous Network and Service Software of Liaoning, Dalian University of Technology, Dalian, Liaoning, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-2853-7642","authenticated-orcid":false,"given":"Junzhe","family":"Zheng","sequence":"additional","affiliation":[{"name":"School of Software, Key Laboratory for Ubiquitous Network and Service Software of Liaoning, Dalian University of Technology, Dalian, Liaoning, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8994-9532","authenticated-orcid":false,"given":"Jiayuan","family":"He","sequence":"additional","affiliation":[{"name":"School of Computing Technologies, Royal Melbourne Institute of Technology, Melbourne, Victoria, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-3743-0103","authenticated-orcid":false,"given":"Yuxuan","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Software, Key Laboratory for Ubiquitous Network and Service Software of Liaoning, Dalian University of Technology, Dalian, Liaoning, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0872-7688","authenticated-orcid":false,"given":"Hongfei","family":"Lin","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Dalian University of Technology, Dalian, Liaoning, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6301-1311","authenticated-orcid":false,"given":"Liang","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Software, Key Laboratory for Ubiquitous Network and Service Software of Liaoning, Dalian University of Technology, Dalian, Liaoning, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8324-1859","authenticated-orcid":false,"given":"Feng","family":"Xia","sequence":"additional","affiliation":[{"name":"School of Computing Technologies, RMIT University, Melbourne, Victoria, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Leonidas John Guibas","author":"Akula Arjun Reddy","year":"2023","unstructured":"Arjun Reddy Akula, Brendan Driscoll, Pradyumna Narayana, Soravit Changpinyo, Zhiwei Jia, Suyash Damle, Garima Pruthi, Sugato Basu, Leonidas John Guibas, William T. Freeman, Yuanzhen Li, and Varun Jampani. 2023. MetaCLUE: Towards Comprehensive Visual Metaphors Research. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023, Vancouver, BC, Canada, June 17--24, 2023. IEEE, 23201--23211."},{"key":"e_1_3_2_1_2_1","volume-title":"DE-FACTIFY@AAAI","author":"Bucur Ana-Maria","year":"2022","unstructured":"Ana-Maria Bucur, Adrian Cosma, and Ioan-Bogdan Iordache. 2022. BLUE at Memotion 2.0 2022: You have my Image, my Text and my Transformer. In DE-FACTIFY@AAAI 2022, Vol. 3199. CEUR-WS.org."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.figlang-1.32"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.141"},{"key":"e_1_3_2_1_5_1","volume-title":"The Language of Internet Memes","author":"Davison Patrick","unstructured":"Patrick Davison. 2012. 9. The Language of Internet Memes. New York University Press, New York, USA, 120--134. ISBN 9780814763025."},{"key":"e_1_3_2_1_6_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_7_1","volume-title":"DE-FACTIFY@AAAI","author":"Duan Baishan","year":"2022","unstructured":"Baishan Duan and Yuesheng Zhu. 2022. BROWALLIA at Memotion 2.0 2022 : Multimodal Memotion Analysis with Modified OGB Strategies. In DE-FACTIFY@AAAI 2022, Vol. 3199. CEUR-WS.org."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.23919\/i-Society.2017.8354676"},{"key":"e_1_3_2_1_9_1","unstructured":"Xiaoyu Guo Jing Ma and Arkaitz Zubiaga. 2023. NUAA-QMUL-AIIT at Memotion 3: Multi-modal Fusion with Squeeze-and-Excitation for Internet Meme Emotion Analysis."},{"key":"e_1_3_2_1_10_1","volume-title":"Artificial Intelligence and Cognitive Science","author":"Hazman Muzhaffar","unstructured":"Muzhaffar Hazman, Susan McKeever, and Josephine Griffith. 2023. Meme Sentiment Analysis Enhanced with\u00a0Multimodal Spatial Encoding and\u00a0Face Embedding. In Artificial Intelligence and Cognitive Science. Springer, Munster, Ireland, 318--331."},{"key":"e_1_3_2_1_11_1","volume-title":"MemeCap: A Dataset for Captioning and Interpreting Memes. CoRR","author":"Hwang EunJeong","year":"2023","unstructured":"EunJeong Hwang and Vered Shwartz. 2023. MemeCap: A Dataset for Captioning and Interpreting Memes. CoRR, Vol. abs\/2305.13703 (2023)."},{"key":"e_1_3_2_1_12_1","volume-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems. 2611--2624","author":"Kiela Douwe","year":"2020","unstructured":"Douwe Kiela, Hamed Firooz, Aravind Mohan, Vedanuj Goswami, Amanpreet Singh, Pratik Ringshia, and Davide Testuggine. 2020. The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes. In Proceedings of the 34th International Conference on Neural Information Processing Systems. 2611--2624."},{"key":"e_1_3_2_1_13_1","volume-title":"Adam: A Method for Stochastic Optimization. In 3rd International Conference on Learning Representations","author":"Diederik","unstructured":"Diederik P. Kingma and Jimmy Ba. 2015. Adam: A Method for Stochastic Optimization. In 3rd International Conference on Learning Representations. San Diego, USA."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3591106.3592254"},{"key":"e_1_3_2_1_15_1","volume-title":"DE-FACTIFY@AAAI","author":"Lee Gwang Gook","year":"2022","unstructured":"Gwang Gook Lee and Mingwei Shen. 2022. Amazon PARS at Memotion 2.0 2022: Multi-modal Multi-task Learning for Memotion 2.0 Challenge. In DE-FACTIFY@AAAI 2022, Vol. 3199. CEUR-WS.org."},{"key":"e_1_3_2_1_16_1","volume-title":"International Conference on Machine Learning, ICML 2023","volume":"19742","author":"Li Junnan","year":"2023","unstructured":"Junnan Li, Dongxu Li, Silvio Savarese, and Steven C. H. Hoi. 2023. BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models. In International Conference on Machine Learning, ICML 2023, 23--29 July 2023, Honolulu, Hawaii, USA (Proceedings of Machine Learning Research, Vol. 202), Andreas Krause, Emma Brunskill, Kyunghyun Cho, Barbara Engelhardt, Sivan Sabato, and Jonathan Scarlett (Eds.). PMLR, 19730--19742. https:\/\/proceedings.mlr.press\/v202\/li23q.html"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_2_1_19_1","volume-title":"Memotion 3: Dataset on Sentiment and Emotion Analysis of Codemixed Hindi-English Memes. CoRR","author":"Mishra Shreyash","year":"2023","unstructured":"Shreyash Mishra, Suryavardan S, Parth Patwa, Megha Chakraborty, Anku Rani, Aishwarya Reganti, Aman Chadha, Amitava Das, Amit P. Sheth, Manoj Chinnakotla, Asif Ekbal, and Srijan Kumar. 2023. Memotion 3: Dataset on Sentiment and Emotion Analysis of Codemixed Hindi-English Memes. CoRR, Vol. abs\/2303.09892 (2023)."},{"key":"e_1_3_2_1_20_1","volume-title":"Ngoc Duy Nguyen, Hai Nguyen, Long H. Nguyen, and Yong-Guk Kim.","author":"Nguyen Thanh Van","year":"2022","unstructured":"Thanh Van Nguyen, Nhat Truong Pham, Ngoc Duy Nguyen, Hai Nguyen, Long H. Nguyen, and Yong-Guk Kim. 2022. HCILab at Memotion 2.0 2022: Analysis of Sentiment, Emotion and Intensity of Emotion Classes from Meme Images using Single and Multi Modalities (short paper). In DE-FACTIFY@AAAI 2022, Vol. 3199. CEUR-WS.org."},{"key":"e_1_3_2_1_22_1","unstructured":"Kim Ngan Phan Gueesang Lee Hyung-Jeong Yang and Soo-Hyung Kim. 2022. Little Flower at Memotion 2.0 2022 : Ensemble of Multi-Modal Model using Attention Mechanism in MEMOTION Analysis (short paper). In DE-FACTIFY@AAAI. https:\/\/api.semanticscholar.org\/CorpusID:252015554"},{"key":"e_1_3_2_1_23_1","volume-title":"Proceedings of the 38th 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, Gretchen Krueger, and Ilya Sutskever. 2021. Learning Transferable Visual Models From Natural Language Supervision. In Proceedings of the 38th International Conference on Machine Learning. PMLR, 8748--8763."},{"key":"e_1_3_2_1_24_1","volume-title":"DE-FACTIFY@AAAI","author":"Ramamoorthy Sathyanarayanan","year":"2022","unstructured":"Sathyanarayanan Ramamoorthy, Nethra Gunti, Shreyash Mishra, Suryavardan S, Aishwarya N. Reganti, Parth Patwa, Amitava Das, Tanmoy Chakraborty, Amit P. Sheth, Asif Ekbal, and Chaitanya Ahuja. 2022. Memotion 2: Dataset on Sentiment and Emotion Analysis of Memes. In DE-FACTIFY@AAAI 2022, Vol. 3199. CEUR-WS.org."},{"key":"e_1_3_2_1_25_1","volume-title":"Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks 1, NeurIPS Datasets and Benchmarks 2021","author":"Ridnik Tal","year":"2021","unstructured":"Tal Ridnik, Emanuel Ben Baruch, Asaf Noy, and Lihi Zelnik. 2021. ImageNet-21K Pretraining for the Masses. In Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks 1, NeurIPS Datasets and Benchmarks 2021, December 2021, virtual, Joaquin Vanschoren and Sai-Kit Yeung (Eds.). https:\/\/datasets-benchmarks-proceedings.neurips.cc\/paper\/2021\/hash\/98f13708210194c475687be6106a3b84-Abstract-round1.html"},{"key":"e_1_3_2_1_26_1","volume-title":"a distilled version of BERT: smaller, faster, cheaper and lighter. CoRR","author":"Sanh Victor","year":"2019","unstructured":"Victor Sanh, Lysandre Debut, Julien Chaumond, and Thomas Wolf. 2019. DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter. CoRR, Vol. abs\/1910.01108 (2019)."},{"key":"e_1_3_2_1_27_1","volume-title":"Proceedings of the 2016 Conference of the North American","author":"Shutova Ekaterina","unstructured":"Ekaterina Shutova, Douwe Kiela, and Jean Maillard. 2016. Black Holes and White Rabbits: Metaphor Identification with Visual Features. In Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. The Association for Computational Linguistics, San Diego California, USA."},{"key":"e_1_3_2_1_28_1","volume-title":"Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing","author":"Stowe Kevin","unstructured":"Kevin Stowe, Tuhin Chakrabarty, Nanyun Peng, Smaranda Muresan, and Iryna Gurevych. 2021. Metaphor Generation with Conceptual Mappings. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing. Association for Computational Linguistics, 6724--6736."},{"key":"e_1_3_2_1_29_1","volume-title":"Good Teacher, then you have Good Meme Analysis. CoRR","author":"Tang Yu-Chien","year":"2023","unstructured":"Yu-Chien Tang, Kuang-Da Wang, Ting-Yun Ou, and Wen-Chih Peng. 2023. NYCU-TWO at Memotion 3: Good Foundation, Good Teacher, then you have Good Meme Analysis. CoRR, Vol. abs\/2302.06078 (2023)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01271"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3532019"},{"key":"e_1_3_2_1_32_1","volume-title":"Recurrent Affine Transformation for Text-to-image Synthesis","author":"Ye Senmao","year":"2023","unstructured":"Senmao Ye, Huan Wang, Mingkui Tan, and Fei Liu. 2023. Recurrent Affine Transformation for Text-to-image Synthesis. IEEE Transactions on Multimedia (2023)."},{"key":"e_1_3_2_1_33_1","volume-title":"Crowd-Sourcing A High-Quality Dataset for Metaphor Identification in Tweets. In 2nd Conference on Language, Data and Knowledge. Schloss Dagstuhl - Leibniz-Zentrum f\u00fcr Informatik","author":"Zayed Omnia","year":"2019","unstructured":"Omnia Zayed, John P. McCrae, and Paul Buitelaar. 2019. Crowd-Sourcing A High-Quality Dataset for Metaphor Identification in Tweets. In 2nd Conference on Language, Data and Knowledge. Schloss Dagstuhl - Leibniz-Zentrum f\u00fcr Informatik, Leipzig, Germany, 1--17."},{"key":"e_1_3_2_1_34_1","volume-title":"Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing","author":"Zhang Dongyu","unstructured":"Dongyu Zhang, Minghao Zhang, Heting Zhang, Liang Yang, and Hongfei Lin. 2021. MultiMET: A Multimodal Dataset for Metaphor Understanding. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing. Association for Computational Linguistics, 3214--3225."},{"key":"e_1_3_2_1_35_1","volume-title":"CAMEL: Capturing Metaphorical Alignment with Context Disentangling for Multimodal Emotion Recognition. In AAAI Conference on Artificial Intelligence.","author":"Zhang Linhao","year":"2024","unstructured":"Linhao Zhang, Li Jin, Guangluan Xu, Xiaoyu Li, Cai Xu, Kaiwen Wei, Nayu Liu, and Haonan Liu. 2024. CAMEL: Capturing Metaphorical Alignment with Context Disentangling for Multimodal Emotion Recognition. In AAAI Conference on Artificial Intelligence."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3501247.3531557"},{"key":"e_1_3_2_1_37_1","volume-title":"DE-FACTIFY@AAAI","author":"Zhuang Yan","year":"2022","unstructured":"Yan Zhuang and Yanru Zhang. 2022. Yet at Memotion 2.0 2022 : Hate Speech Detection Combining BiLSTM and Fully Connected Layers. In DE-FACTIFY@AAAI 2022, Vol. 3199. CEUR-WS.org."}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681060","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681060","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:57:52Z","timestamp":1750294672000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681060"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":36,"alternative-id":["10.1145\/3664647.3681060","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681060","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}