{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,11]],"date-time":"2026-01-11T08:50:03Z","timestamp":1768121403045,"version":"3.49.0"},"publisher-location":"Singapore","reference-count":38,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819557608","type":"print"},{"value":"9789819557615","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-981-95-5761-5_40","type":"book-chapter","created":{"date-parts":[[2026,1,11]],"date-time":"2026-01-11T05:52:35Z","timestamp":1768110755000},"page":"576-589","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-modal Metaphor Explanation: A Dataset and\u00a0Benchmark"],"prefix":"10.1007","author":[{"given":"Zikai","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenye","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cheng","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pijian","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qingbao","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,1,12]]},"reference":[{"key":"40_CR1","unstructured":"Birke, J., Sarkar, A.: A clustering approach for nearly unsupervised recognition of nonliteral language. In: EACL 2006, 11st Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference. The Association for Computer Linguistics (2006). https:\/\/aclanthology.org\/E06-1042\/"},{"key":"40_CR2","doi-asserted-by":"publisher","unstructured":"Bizzoni, Y., Dobnik, S.: Sky + fire = sunset. exploring parallels between visually grounded metaphors and image classifiers. In: Proceedings of the Second Workshop on Figurative Language Processing, Fig-Lang@ACL 2020, pp. 126\u2013135. Association for Computational Linguistics (2020). https:\/\/doi.org\/10.18653\/v1\/2020.figlang-1.19","DOI":"10.18653\/v1\/2020.figlang-1.19"},{"key":"40_CR3","unstructured":"Boisson, J., Siddique, Z., Borkakoty, H., Antypas, D., Espinosa\u00a0Anke, L., Camacho-Collados, J.: Automatic extraction of metaphoric analogies from literary texts: task formulation, dataset construction, and evaluation. In: Rambow, O., Wanner, L., Apidianaki, M., Al-Khalifa, H., Eugenio, B.D., Schockaert, S. (eds.) Proceedings of the 31st International Conference on Computational Linguistics, pp. 6692\u20136704. Association for Computational Linguistics, Abu Dhabi, UAE (2025), https:\/\/aclanthology.org\/2025.coling-main.448\/"},{"key":"40_CR4","doi-asserted-by":"publisher","unstructured":"Chen, X., Leong, C.W., Flor, M., Klebanov, B.B.: Go figure! multi-task transformer-based architecture for metaphor detection using idioms: ETS team in 2020 metaphor shared task. In: Proceedings of the Second Workshop on Figurative Language Processing, Fig-Lang@ACL 2020, pp. 235\u2013243. Association for Computational Linguistics (2020). https:\/\/doi.org\/10.18653\/v1\/2020.figlang-1.32","DOI":"10.18653\/v1\/2020.figlang-1.32"},{"issue":"2","key":"40_CR5","doi-asserted-by":"publisher","first-page":"199","DOI":"10.1075\/ssol.1.2.03chr","volume":"1","author":"U Christmann","year":"2011","unstructured":"Christmann, U., Wimmer, L., Groeben, N.: The aesthetic paradox in processing conventional and non-conventional metaphors: a reaction time study. Scientific study of Literature 1(2), 199\u2013240 (2011)","journal-title":"Scientific study of Literature"},{"key":"40_CR6","doi-asserted-by":"publisher","unstructured":"Dai, W., Hou, L., Shang, L., Jiang, X., Liu, Q., Fung, P.: Enabling multimodal generation on CLIP via vision-language knowledge distillation. In: Findings of the Association for Computational Linguistics: ACL 2022, Dublin, Ireland, pp. 2383\u20132395. Association for Computational Linguistics (2022). https:\/\/doi.org\/10.18653\/v1\/2022.findings-acl.187","DOI":"10.18653\/v1\/2022.findings-acl.187"},{"key":"40_CR7","doi-asserted-by":"publisher","unstructured":"Denkowski, M.J., Lavie, A.: Meteor universal: language specific translation evaluation for any target language. In: Proceedings of the Ninth Workshop on Statistical Machine Translation, WMT@ACL 2014, pp. 376\u2013380. The Association for Computer Linguistics (2014). https:\/\/doi.org\/10.3115\/v1\/w14-3348, https:\/\/doi.org\/10.3115\/v1\/w14-3348","DOI":"10.3115\/v1\/w14-3348"},{"key":"40_CR8","doi-asserted-by":"crossref","unstructured":"Desai, P., Chakraborty, T., Akhtar, M.S.: Nice perfume. How long did you marinate in it? Multimodal sarcasm explanation. In: Thirty-Sixth AAAI Conference on Artificial Intelligence, AAAI 2022, pp. 10563\u201310571. AAAI Press (2022). https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/21300","DOI":"10.1609\/aaai.v36i10.21300"},{"key":"40_CR9","doi-asserted-by":"publisher","unstructured":"Devlin, J., Chang, M., Lee, K., Toutanova, K.: 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, NAACL-HLT 2019, Minneapolis, MN, USA, June 2-7, 2019, Volume 1 (Long and Short Papers), pp. 4171\u20134186. Association for Computational Linguistics (2019). https:\/\/doi.org\/10.18653\/v1\/n19-1423","DOI":"10.18653\/v1\/n19-1423"},{"key":"40_CR10","doi-asserted-by":"publisher","unstructured":"Dey, A.U., Ghosh, S.K., Valveny, E., Harit, G.: Beyond visual semantics: exploring the role of scene text in image understanding. Pattern Recognit. Lett. 149, 164\u2013171 (2021). https:\/\/doi.org\/10.1016\/j.patrec.2021.06.011","DOI":"10.1016\/j.patrec.2021.06.011"},{"key":"40_CR11","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021, OpenReview.net (2021). https:\/\/openreview.net\/forum?id=YicbFdNTTy"},{"issue":"5","key":"40_CR12","doi-asserted-by":"publisher","first-page":"378","DOI":"10.1037\/h0031619","volume":"76","author":"JL Fleiss","year":"1971","unstructured":"Fleiss, J.L.: Measuring nominal scale agreement among many raters. Psychol. Bull. 76(5), 378 (1971)","journal-title":"Psychol. Bull."},{"key":"40_CR13","doi-asserted-by":"crossref","unstructured":"Forceville, C., Urios-Aparisi, E., et\u00a0al.: Multimodal Metaphor, vol.\u00a011. Mouton de Gruyter Berlin (2009)","DOI":"10.1515\/9783110215366"},{"key":"40_CR14","doi-asserted-by":"publisher","unstructured":"Guo, M., Hwa, R., Kovashka, A.: Detecting persuasive atypicality by modeling contextual compatibility. In: 2021 IEEE\/CVF International Conference on Computer Vision, ICCV 2021, Montreal, QC, Canada, pp. 952\u2013962. IEEE (2021). https:\/\/doi.org\/10.1109\/ICCV48922.2021.00101","DOI":"10.1109\/ICCV48922.2021.00101"},{"key":"40_CR15","doi-asserted-by":"crossref","unstructured":"He, Q., Wang, X., Liang, J., Xiao, Y.: MAPS-KB: a million-scale probabilistic simile knowledge base. arXiv preprint arXiv:2212.05254 (2022)","DOI":"10.1609\/aaai.v37i5.25787"},{"key":"40_CR16","doi-asserted-by":"publisher","unstructured":"Hussain, Z., et al.: Automatic understanding of image and video advertisements. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, pp. 1100\u20131110. IEEE Computer Society (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.123, https:\/\/doi.org\/10.1109\/CVPR.2017.123","DOI":"10.1109\/CVPR.2017.123"},{"key":"40_CR17","doi-asserted-by":"publisher","unstructured":"Kalra, K., Kurma, B., Sreelatha, S.V., Patwardhan, M.S., Karande, S.S.: Understanding advertisements with BERT. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, ACL 2020, pp. 7542\u20137547. Association for Computational Linguistics (2020). https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.674","DOI":"10.18653\/v1\/2020.acl-main.674"},{"issue":"2","key":"40_CR18","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1075\/msw.1.2.02kap","volume":"1","author":"H Kappelhoff","year":"2011","unstructured":"Kappelhoff, H., M\u00fcller, C.: Embodied meaning construction: multimodal metaphor and expressive movement in speech, gesture, and feature film. Metaphor and the social world 1(2), 121\u2013153 (2011)","journal-title":"Metaphor and the social world"},{"key":"40_CR19","unstructured":"Lakoff, G., Johnson, M.: Metaphors we Live by. University of Chicago press (2008)"},{"key":"40_CR20","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.C.H.: BLIP: bootstrapping language-image pre-training for unified vision-language understanding and generation. In: International Conference on Machine Learning, ICML 2022, Proceedings of Machine Learning Research, vol.\u00a0162, pp. 12888\u201312900. PMLR (2022). https:\/\/proceedings.mlr.press\/v162\/li22n.html"},{"key":"40_CR21","unstructured":"Lin, C.Y.: Rouge: a package for automatic evaluation of summaries. In: Text summarization of ACL 2004, pp. 74\u201381 (2004)"},{"issue":"1","key":"40_CR22","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1162\/089120104773633376","volume":"30","author":"ZJ Mason","year":"2004","unstructured":"Mason, Z.J.: Cormet: a computational, corpus-based conventional metaphor extraction system. Comput. Linguist. 30(1), 23\u201344 (2004)","journal-title":"Comput. Linguist."},{"key":"40_CR23","doi-asserted-by":"publisher","unstructured":"Mohammad, S.M., Shutova, E., Turney, P.D.: Metaphor as a medium for emotion: an empirical study. In: Proceedings of the Fifth Joint Conference on Lexical and Computational Semantics, *SEM@ACL 2016, Berlin, Germany. The *SEM 2016 Organizing Committee (2016). https:\/\/doi.org\/10.18653\/v1\/s16-2003","DOI":"10.18653\/v1\/s16-2003"},{"key":"40_CR24","unstructured":"Ovchinnikova, E., Zaytsev, V., Wertheim, S., Israel, R.: Generating conceptual metaphors from proposition stores. arXiv preprint arxiv:abs\/1409.7619 (2014)"},{"key":"40_CR25","doi-asserted-by":"publisher","unstructured":"Pan, Y.: On visual knowledge. Front. Inf. Technol. Electron. Eng. 20(8), 1021\u20131025 (2019). https:\/\/doi.org\/10.1631\/FITEE.1910001","DOI":"10.1631\/FITEE.1910001"},{"key":"40_CR26","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: Bleu: a method for automatic evaluation of machine translation. In: Proceedings of the 40th annual meeting of the Association for Computational Linguistics, ACL 2002, pp. 311\u2013318 (2002)","DOI":"10.3115\/1073083.1073135"},{"issue":"1","key":"40_CR27","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1177\/1470357203002001755","volume":"2","author":"EE Refaie","year":"2003","unstructured":"Refaie, E.E.: Understanding visual metaphor: the example of newspaper cartoons. Vis. Commun. 2(1), 75\u201395 (2003)","journal-title":"Vis. Commun."},{"key":"40_CR28","doi-asserted-by":"publisher","unstructured":"Shutova, E., Kiela, D., Maillard, J.: Black holes and white rabbits: metaphor identification with visual features. In: NAACL HLT 2016, The 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 160\u2013170. The Association for Computational Linguistics (2016). https:\/\/doi.org\/10.18653\/v1\/n16-1020","DOI":"10.18653\/v1\/n16-1020"},{"key":"40_CR29","doi-asserted-by":"publisher","DOI":"10.1075\/celcr.14","volume-title":"A Method for Linguistic Metaphor Identification","author":"G Steen","year":"2010","unstructured":"Steen, G., Dorst, A.G., Herrmann, J.B., Kaal, A., Krennmayr, T., Pasma, T.: A Method for Linguistic Metaphor Identification. Benjamins, Amsterdam (2010)"},{"key":"40_CR30","doi-asserted-by":"crossref","unstructured":"Steen, G.J.: Visual metaphor: structure and process, vol.\u00a018. John Benjamins Publishing Company (2018)","DOI":"10.1075\/celcr.18"},{"key":"40_CR31","doi-asserted-by":"publisher","unstructured":"Tong, X., Choenni, R., Lewis, M., Shutova, E.: Metaphor understanding challenge dataset for LLMs. In: Ku, L.W., Martins, A., Srikumar, V. (eds.) Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 3517\u20133536. Association for Computational Linguistics, Bangkok, Thailand (2024). https:\/\/doi.org\/10.18653\/v1\/2024.acl-long.193","DOI":"10.18653\/v1\/2024.acl-long.193"},{"key":"40_CR32","doi-asserted-by":"publisher","unstructured":"Tsvetkov, Y., Boytsov, L., Gershman, A., Nyberg, E., Dyer, C.: Metaphor detection with cross-lingual model transfer. In: Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics, ACL 2014, pp. 248\u2013258. The Association for Computer Linguistics (2014). https:\/\/doi.org\/10.3115\/v1\/p14-1024","DOI":"10.3115\/v1\/p14-1024"},{"key":"40_CR33","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1515\/9783110215366.2.95","volume":"11","author":"E Urios-Aparisi","year":"2009","unstructured":"Urios-Aparisi, E.: Interaction of multimodal metaphor and metonymy in tv commercials: four case studies. Multimodal Metaphor 11, 95\u2013116 (2009)","journal-title":"Multimodal Metaphor"},{"key":"40_CR34","doi-asserted-by":"publisher","unstructured":"Vedantam, R., Zitnick, C.L., Parikh, D.: Cider: consensus-based image description evaluation. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015, pp. 4566\u20134575. IEEE Computer Society (2015). https:\/\/doi.org\/10.1109\/CVPR.2015.7299087","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"40_CR35","doi-asserted-by":"publisher","unstructured":"Xu, B., et al.: Met-meme: a multimodal meme dataset rich in metaphors. In: SIGIR \u201922: The 45th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 2887\u20132899. ACM (2022). https:\/\/doi.org\/10.1145\/3477495.3532019","DOI":"10.1145\/3477495.3532019"},{"key":"40_CR36","doi-asserted-by":"publisher","unstructured":"Ye, K., Nazari, N.H., Hahn, J., Hussain, Z., Zhang, M., Kovashka, A.: Interpreting the rhetoric of visual advertisements. IEEE Trans. Pattern Anal. Mach. Intell. 43(4), 1308\u20131323 (2021). https:\/\/doi.org\/10.1109\/TPAMI.2019.2947440","DOI":"10.1109\/TPAMI.2019.2947440"},{"key":"40_CR37","doi-asserted-by":"publisher","unstructured":"Zayed, O., McCrae, J.P., Buitelaar, P.: Crowd-sourcing a high-quality dataset for metaphor identification in tweets. In: 2nd Conference on Language, Data and Knowledge, LDK 2019, OASIcs, vol.\u00a070, pp. 10:1\u201310:17. Schloss Dagstuhl - Leibniz-Zentrum f\u00fcr Informatik (2019). https:\/\/doi.org\/10.4230\/OASIcs.LDK.2019.10","DOI":"10.4230\/OASIcs.LDK.2019.10"},{"key":"40_CR38","doi-asserted-by":"publisher","unstructured":"Zhang, D., Zhang, M., Zhang, H., Yang, L., Lin, H.: 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, ACL\/IJCNLP 2021, pp. 3214\u20133225. Association for Computational Linguistics (2021). https:\/\/doi.org\/10.18653\/v1\/2021.acl-long.249","DOI":"10.18653\/v1\/2021.acl-long.249"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-5761-5_40","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,11]],"date-time":"2026-01-11T05:52:38Z","timestamp":1768110758000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-5761-5_40"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819557608","9789819557615"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-5761-5_40","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"12 January 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shanghai","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2025.prcv.cn\/index.asp","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}