{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T01:40:46Z","timestamp":1755826846442,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":18,"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:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,5,30]]},"DOI":"10.1145\/3652583.3658893","type":"proceedings-article","created":{"date-parts":[[2024,6,7]],"date-time":"2024-06-07T06:30:40Z","timestamp":1717741840000},"page":"1342-1344","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["MUWS 2024: The 3rd International Workshop on Multimodal Human Understanding for the Web and Social Media"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9193-5973","authenticated-orcid":false,"given":"Marc A.","family":"Kastner","sequence":"first","affiliation":[{"name":"Kyoto University, Kyoto, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4354-9629","authenticated-orcid":false,"given":"Gullal S.","family":"Cheema","sequence":"additional","affiliation":[{"name":"Leibniz University Hannover, Hannover, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7421-6213","authenticated-orcid":false,"given":"Sherzod","family":"Hakimov","sequence":"additional","affiliation":[{"name":"University of Potsdam, Potsdam, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9200-6359","authenticated-orcid":false,"given":"Noa","family":"Garcia","sequence":"additional","affiliation":[{"name":"Osaka University, Osaka, Japan"}]}],"member":"320","published-online":{"date-parts":[[2024,6,7]]},"reference":[{"volume-title":"Text and image: A critical introduction to the visual\/verbal divide","author":"Bateman John A","key":"e_1_3_2_1_1_1","unstructured":"John A Bateman. 2014. Text and image: A critical introduction to the visual\/verbal divide. Routledge."},{"key":"e_1_3_2_1_2_1","volume-title":"Dall-eval: Probing the reasoning skills and social biases of text-to-image generative transformers. arXiv preprint arXiv:2202.04053","author":"Cho Jaemin","year":"2022","unstructured":"Jaemin Cho, Abhay Zala, and Mohit Bansal. 2022. Dall-eval: Probing the reasoning skills and social biases of text-to-image generative transformers. arXiv preprint arXiv:2202.04053 (2022)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01309"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01279"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-019-08571-4"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1469"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1108\/00220410310506303"},{"key":"e_1_3_2_1_8_1","volume-title":"A system for image--text relations in new (and old) media. Visual communication","author":"Martinec Radan","year":"2005","unstructured":"Radan Martinec and Andrew Salway. 2005. A system for image--text relations in new (and old) media. Visual communication, Vol. 4, 3 (2005), 337--371."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-78635-9_20"},{"key":"e_1_3_2_1_10_1","volume-title":"IPA-CLIP: Integrating Phonetic Priors into Vision and Language Pretraining. arXiv preprint arXiv:2303.03144","author":"Matsuhira Chihaya","year":"2023","unstructured":"Chihaya Matsuhira, Marc A. Kastner, Takahiro Komamizu, Takatsugu Hirayama, Keisuke Doman, Yasutomo Kawanishi, and Ichiro Ide. 2023. IPA-CLIP: Integrating Phonetic Priors into Vision and Language Pretraining. arXiv preprint arXiv:2303.03144 (2023)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3323873.3325049"},{"key":"e_1_3_2_1_12_1","first-page":"2751","article-title":"Be different to be better! A benchmark to leverage the complementarity of language and vision. In Findings of the association for computational linguistics","volume":"2020","author":"Pezzelle Sandro","year":"2020","unstructured":"Sandro Pezzelle, Claudio Greco, Greta Gandolfi, Eleonora Gualdoni, and Raffaella Bernardi. 2020. Be different to be better! A benchmark to leverage the complementarity of language and vision. In Findings of the association for computational linguistics: EMNLP 2020. 2751--2767.","journal-title":"EMNLP"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.gebnlp-1.10"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449950"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1272"},{"key":"e_1_3_2_1_16_1","volume-title":"Equal But Not The Same: Understanding the Implicit Relationship Between Persuasive Images and Text. In British Machine Vision Conference (BMVC).","author":"Zhang Mingda","year":"2018","unstructured":"Mingda Zhang, Rebecca Hwa, and Adriana Kovashka. 2018. Equal But Not The Same: Understanding the Implicit Relationship Between Persuasive Images and Text. In British Machine Vision Conference (BMVC)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01456"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1323"}],"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\/3652583.3658893","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3652583.3658893","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T08:47:26Z","timestamp":1755766046000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3652583.3658893"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,30]]},"references-count":18,"alternative-id":["10.1145\/3652583.3658893","10.1145\/3652583"],"URL":"https:\/\/doi.org\/10.1145\/3652583.3658893","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"}}]}}