{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:09:18Z","timestamp":1761894558310,"version":"build-2065373602"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11209232","type":"proceedings-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:57:42Z","timestamp":1761847062000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Can MLLMs Tell Jokes Based on Images? A Visual Context-Driven Humor Generation Framework"],"prefix":"10.1109","author":[{"given":"Meixuan","family":"Chen","sequence":"first","affiliation":[{"name":"Huazhong Agricultural University,Wuhan,China"}]},{"given":"Chen","family":"Wang","sequence":"additional","affiliation":[{"name":"Huazhong Agricultural University,Wuhan,China"}]},{"given":"Liu","family":"Hui","sequence":"additional","affiliation":[{"name":"Huazhong Agricultural University,Wuhan,China"}]},{"given":"Yujun","family":"Wu","sequence":"additional","affiliation":[{"name":"Huazhong Agricultural University,Wuhan,China"}]},{"given":"Ying","family":"Sha","sequence":"additional","affiliation":[{"name":"Huazhong Agricultural University,Wuhan,China"}]}],"member":"263","reference":[{"key":"ref1","first-page":"29","article-title":"A survey on approaches to computational humor generation","volume-title":"Proceedings of the 4th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature","author":"Amin"},{"key":"ref2","first-page":"633","article-title":"An implemented model of punning riddles","volume-title":"Proceedings of the 12th National Conference on Artificial Intelligence (AAAI \u201994)","volume":"1","author":"Binsted"},{"key":"ref3","first-page":"243","article-title":"Let everything turn well in your wife: Generation of adult humor using lexical constraints","volume":"2","author":"Toivanen Alessandro Valitutti","year":"2013","journal-title":"Association for Computational Linguistics"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1153"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-naacl.152"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.738"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01258"},{"year":"2020","key":"ref8","article-title":"Colbert: Using bert sentence embedding for humor detection"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33017265"},{"volume-title":"The Psychology of Humor","year":"2018","author":"Ford","key":"ref10"},{"key":"ref11","first-page":"3318","article-title":"Rethinking the agreement in human evaluation tasks","volume-title":"Proceedings of the 27th International Conference on Computational Linguistics","author":"Amidei"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.178"},{"article-title":"Large language models are zero-shot reasoners","volume-title":"Proceedings of the 36th International Conference on Neural Information Processing Systems","author":"Kojima","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29736"},{"issue":"2","key":"ref15","first-page":"3","article-title":"Qwen-vl: A versatile vision-language model for understanding, localization, text reading, and beyond","volume":"1","author":"Bai","year":"2023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.semeval-1.9"},{"article-title":"Direct preference optimization: your language model is secretly a reward model","volume-title":"Proceedings of the 37th International Conference on Neural Information Processing Systems","author":"Rafailov","key":"ref17"},{"key":"ref18","first-page":"34892","article-title":"Visual instruction tuning","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Liu","year":"2023"},{"article-title":"Internlm-xcomposer: A visionlanguage large model for advanced text-image comprehension and composition","year":"2023","author":"Zhang","key":"ref19"},{"article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International Conference on Machine Learning","author":"Li","key":"ref20"},{"article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","year":"2023","author":"Zhu","key":"ref21"},{"article-title":"Llavar: Enhanced visual instruction tuning for text-rich image understanding","year":"2023","author":"Zhang","key":"ref22"},{"article-title":"Visual perception by large language model\u2019s weights","year":"2024","author":"Ma","key":"ref23"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01239"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.210"},{"article-title":"Automated evaluation of personalized text generation using large language models","year":"2023","author":"Wang","key":"ref26"},{"article-title":"Making llama see and draw with seed tokenizer","year":"2023","author":"Ge","key":"ref27"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2025,6,30]]},"location":"Nantes, France","end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11208895\/11208897\/11209232.pdf?arnumber=11209232","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:30:49Z","timestamp":1761888649000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11209232\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11209232","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}