{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:09:52Z","timestamp":1765339792162,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":21,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3762109","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T05:56:43Z","timestamp":1761371803000},"page":"14308-14310","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["MUWS 2025: The 4th International Workshop on Multimodal Human Understanding for the Web and Social Media"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7421-6213","authenticated-orcid":false,"given":"Sherzod","family":"Hakimov","sequence":"first","affiliation":[{"name":"University of Potsdam, Potsdam, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2403-0058","authenticated-orcid":false,"given":"David","family":"Semedo","sequence":"additional","affiliation":[{"name":"NOVA LINCS, NOVA University of Lisbon, Lisbon, Portugal"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6802-1241","authenticated-orcid":false,"given":"Eric","family":"M\u00fcller-Budack","sequence":"additional","affiliation":[{"name":"TIB - Leibniz Information Centre for Science and Technology, Hannover, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9193-5973","authenticated-orcid":false,"given":"Marc A.","family":"Kastner","sequence":"additional","affiliation":[{"name":"Hiroshima City University, Hiroshima, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3041-4330","authenticated-orcid":false,"given":"Takahiro","family":"Komamizu","sequence":"additional","affiliation":[{"name":"Nagoya University, Nagoya, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"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","doi-asserted-by":"publisher","DOI":"10.1177\/1464884914568078"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.3389\/frai.2023.1125533"},{"key":"e_1_3_2_1_4_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_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3652583.3657622"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01309"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01279"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-019-08571-4"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1469"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1108\/00220410310506303"},{"key":"e_1_3_2_1_11_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_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-78635-9_20"},{"key":"e_1_3_2_1_13_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_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3323873.3325049"},{"key":"e_1_3_2_1_15_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_16_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.gebnlp-1.10"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449950"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1272"},{"key":"e_1_3_2_1_19_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_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01456"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1323"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Dublin Ireland","acronym":"MM '25"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3762109","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:06:50Z","timestamp":1765339610000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3762109"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":21,"alternative-id":["10.1145\/3746027.3762109","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3762109","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}