{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T20:06:24Z","timestamp":1780949184473,"version":"3.54.1"},"reference-count":75,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100018542","name":"Natural Science Foundation of Sichuan","doi-asserted-by":"crossref","award":["2025YFHZ0124"],"award-info":[{"award-number":["2025YFHZ0124"]}],"id":[{"id":"10.13039\/501100018542","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2682026ZT007"],"award-info":[{"award-number":["2682026ZT007"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Frontier Cross Innovation Team Project of Southwest Jiaotong University","award":["YH1500112432297"],"award-info":[{"award-number":["YH1500112432297"]}]},{"name":"Engineering Research Center of Sustainable Urban Intelligent Transportation, Ministry of Education"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Knowl. Data Eng."],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1109\/tkde.2026.3690133","type":"journal-article","created":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T19:37:33Z","timestamp":1777923453000},"page":"4569-4583","source":"Crossref","is-referenced-by-count":0,"title":["Modeling Deep Fusion of Intra- and Inter-Modal Incongruity for Multimodal Sarcasm Detection"],"prefix":"10.1109","volume":"38","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1640-0992","authenticated-orcid":false,"given":"Fengmao","family":"Lv","sequence":"first","affiliation":[{"name":"School of Computing and Artificial Intelligence, Southwest Jiaotong University, Chengdu, Sichuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-8162-3201","authenticated-orcid":false,"given":"Junlin","family":"Fang","sequence":"additional","affiliation":[{"name":"School of Computing and Artificial Intelligence, Southwest Jiaotong University, Chengdu, Sichuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0329-7458","authenticated-orcid":false,"given":"Guosheng","family":"Lin","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanyang Technological University, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5612-7818","authenticated-orcid":false,"given":"Wenya","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanyang Technological University, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2015.2508816"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2016.2541148"},{"key":"ref3","first-page":"173","article-title":"On the psycholinguistics of sarcasm","volume-title":"Irony in Language and Thougt: A Cognitive Science Reader","author":"Gibbs","year":"2007"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-2124"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1093"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313735"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.349"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.124"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475190"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.124"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.562"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29795"},{"key":"ref13","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"162","author":"Li","year":"2022"},{"key":"ref14","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li","year":"2021"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01505"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.333"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3412003"},{"key":"ref19","first-page":"4835","article-title":"Deep multimodal fusion by channel exchanging","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang","year":"2020"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s10115-020-01449-0"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3075238"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2018.2857492"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D13-1066"},{"key":"ref24","first-page":"581","article-title":"Identifying sarcasm in twitter: A closer look","volume-title":"Proc. 49th Ann. Meeting Assoc. Comput. Linguist.","author":"Gonz\u00e1lez-Ib\u00e1\u00f1ez","year":"2011"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1169"},{"key":"ref26","first-page":"2449","article-title":"Tweet sarcasm detection using deep neural network","volume-title":"Proc. Int. Conf. Comput. Linguist.","author":"Zhang","year":"2016"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.20"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/tkde.2022.3155290"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2019.2932406"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.2968894"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2016.2555310"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2019.2913641"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i8.28766"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i4.25594"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.97"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2964321"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p19-1239"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3177356"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3247939"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00536"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i8.28787"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00062"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i4.25614"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i8.26138"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00250"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i8.26138"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.139"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.689"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.101921"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref51","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy","year":"2021"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1656"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02513"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00236"},{"key":"ref56","article-title":"SGDR: Stochastic gradient descent with warm restarts","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov","year":"2017"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2005.06.042"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/d14-1181"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3776561"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/7503.003.0069"},{"key":"ref62","article-title":"RoBERTa: A robustly optimized BERT pretraining approach","author":"Liu","year":"2019"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-27674-8_2"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3755092"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681404"},{"key":"ref66","article-title":"GPT-4 Technical Report","year":"2023"},{"key":"ref67","article-title":"Introducing claude opus 4.5","year":"2025"},{"key":"ref68","article-title":"Gemini 2.5: Pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities","author":"Comanici","year":"2025"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3860"},{"key":"ref71","article-title":"AIDC-AI\/OVIS2-8B (model card)","year":"2024"},{"key":"ref72","article-title":"Qwen2.5-VL Technical report","author":"Bai","year":"2025"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0441"},{"key":"ref74","article-title":"MOKA: Multimodal low-rank adaptation for MLLMs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wei","year":"2025"},{"key":"ref75","article-title":"InternVL3: Exploring advanced training and test-time recipes for open-source multimodal models","author":"Zhu","year":"2025"}],"container-title":["IEEE Transactions on Knowledge and Data Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/69\/11538062\/11505743.pdf?arnumber=11505743","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T19:53:49Z","timestamp":1780948429000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11505743\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":75,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tkde.2026.3690133","relation":{},"ISSN":["1041-4347","1558-2191","2326-3865"],"issn-type":[{"value":"1041-4347","type":"print"},{"value":"1558-2191","type":"electronic"},{"value":"2326-3865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7]]}}}