{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T22:41:27Z","timestamp":1775947287646,"version":"3.50.1"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Youth Science Fund of the Natural Science Foundation of the Autonomous Region","award":["XQZX20240123"],"award-info":[{"award-number":["XQZX20240123"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U23B2053"],"award-info":[{"award-number":["U23B2053"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62176182"],"award-info":[{"award-number":["62176182"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1109\/tcsvt.2025.3530436","type":"journal-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T13:46:31Z","timestamp":1737035191000},"page":"6413-6423","source":"Crossref","is-referenced-by-count":3,"title":["DeepMSD: Advancing Multimodal Sarcasm Detection Through Knowledge-Augmented Graph Reasoning"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7627-5487","authenticated-orcid":false,"given":"Yiwei","family":"Wei","sequence":"first","affiliation":[{"name":"Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-9442-3399","authenticated-orcid":false,"given":"Hengyang","family":"Zhou","sequence":"additional","affiliation":[{"name":"College of Petroleum Engineering, China University of Petroleum (Beijing) at Karamay, Karamay, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5084-7064","authenticated-orcid":false,"given":"Shaozu","family":"Yuan","sequence":"additional","affiliation":[{"name":"JD AI Research, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9908-4524","authenticated-orcid":false,"given":"Meng","family":"Chen","sequence":"additional","affiliation":[{"name":"JD AI Research, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-0028-1281","authenticated-orcid":false,"given":"Haitao","family":"Shi","sequence":"additional","affiliation":[{"name":"College of Petroleum Engineering, China University of Petroleum (Beijing) at Karamay, Karamay, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8423-8785","authenticated-orcid":false,"given":"Zhiyang","family":"Jia","sequence":"additional","affiliation":[{"name":"College of Petroleum Engineering, China University of Petroleum (Beijing) at Karamay, Karamay, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8094-6861","authenticated-orcid":false,"given":"Longbiao","family":"Wang","sequence":"additional","affiliation":[{"name":"Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China"}]},{"given":"Xiaodong","family":"He","sequence":"additional","affiliation":[{"name":"JD AI Research, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1093"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1050"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313735"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3312858"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3273577"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3341728"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.349"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475190"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.124"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.333"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i8.26138"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00250"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.124"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.nlpbt-1.3"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3098712"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i8.28766"},{"key":"ref17","article-title":"A survey of large language models","author":"Zhao","year":"2023","journal-title":"arXiv:2303.18223"},{"key":"ref18","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","volume":"35","author":"Ouyang"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref20","article-title":"Graph attention networks","author":"Veli\u02c7ckovi\u00b4c","year":"2017","journal-title":"arXiv:1710.10903"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p19-1239"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2964321"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref24","article-title":"MME: A comprehensive evaluation benchmark for multimodal large language models","author":"Fu","year":"2023","journal-title":"arXiv:2306.13394"},{"key":"ref25","article-title":"mPLUG-Owl2: Revolutionizing multi-modal large language model with modality collaboration","author":"Ye","year":"2023","journal-title":"arXiv:2311.04257"},{"key":"ref26","first-page":"34892","article-title":"Visual instruction tuning","volume-title":"Proc. 37th Int. Conf. Neural Inf. Process. Syst. (NIPS)","author":"Liu"},{"key":"ref27","article-title":"MMICL: Empowering vision-language model with multi-modal in-context learning","author":"Zhao","year":"2023","journal-title":"arXiv:2309.07915"},{"key":"ref28","article-title":"Shikra: Unleashing multimodal LLM\u2019s referential dialogue magic","author":"Chen","year":"2023","journal-title":"arXiv:2306.15195"},{"key":"ref29","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref30","volume-title":"Vicuna: An Open-source Chatbot Impressing GPT-4 With 90%* ChatGPT Quality","author":"Chiang","year":"2023"},{"key":"ref31","first-page":"48573","article-title":"Knowledge-augmented reasoning distillation for small language models in knowledge-intensive tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Kang"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3327113"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3662732"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681403"},{"key":"ref35","first-page":"2206","article-title":"Improving language models by retrieving from trillions of tokens","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","author":"Borgeaud"},{"key":"ref36","article-title":"RA-DIT: Retrieval-augmented dual instruction tuning","author":"Lin","year":"2023","journal-title":"arXiv:2310.01352"},{"key":"ref37","article-title":"Self-RAG: Learning to retrieve, generate, and critique through self-reflection","author":"Asai","year":"2023","journal-title":"arXiv:2310.11511"},{"key":"ref38","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1181"},{"key":"ref41","first-page":"10834","article-title":"MMSD2.0: Towards a reliable multi-modal sarcasm detection system","volume-title":"Proc. Findings Assoc. Comput. Linguistics, ACL","author":"Qin"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2005.06.042"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3347722"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3342811"},{"key":"ref45","first-page":"3859","article-title":"Dynamic routing between capsules","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Sabour"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11071401\/10843779.pdf?arnumber=10843779","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T18:40:39Z","timestamp":1767638439000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10843779\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7]]},"references-count":45,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3530436","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7]]}}}