{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T21:58:00Z","timestamp":1782856680877,"version":"3.54.5"},"reference-count":50,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100003995","name":"Anhui Provincial Natural Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003995","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Knowledge-Based Systems"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.knosys.2026.116541","type":"journal-article","created":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T23:03:01Z","timestamp":1782601381000},"page":"116541","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Complementary encoder refinement and multilevel crossmodal interaction for multimodal sarcasm detection"],"prefix":"10.1016","volume":"349","author":[{"given":"Hao","family":"Guo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Subin","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhifa","family":"Geng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-5288-048X","authenticated-orcid":false,"given":"Junjie","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sanmin","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chao","family":"Kong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.knosys.2026.116541_b1","series-title":"Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing","first-page":"2900","article-title":"DGLF: A dual graph-based learning framework for multi-modal sarcasm detection","author":"Zhu","year":"2024"},{"key":"10.1016\/j.knosys.2026.116541_b2","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.113614","article-title":"RCLMuFN: Relational context learning and multiplex fusion network for multimodal sarcasm detection","volume":"319","author":"Wang","year":"2025","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2026.116541_b3","series-title":"Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence, IJCAI-24","first-page":"2279","article-title":"Multi-modal sarcasm detection based on dual generative processes","author":"Ma","year":"2024"},{"key":"10.1016\/j.knosys.2026.116541_b4","series-title":"Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)","first-page":"1732","article-title":"Leveraging generative large language models with visual instruction and demonstration retrieval for multimodal sarcasm detection","author":"Tang","year":"2024"},{"key":"10.1016\/j.knosys.2026.116541_b5","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TMM.2023.3336236","article-title":"Enhancing semantic awareness by sentimental constraint with automatic outlier masking for multimodal sarcasm detection","author":"Yuan","year":"2025","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.knosys.2026.116541_b6","series-title":"AMuSeD: An attentive deep neural network for multimodal sarcasm detection incorporating bi-modal data augmentation","author":"Gao","year":"2024"},{"key":"10.1016\/j.knosys.2026.116541_b7","series-title":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","first-page":"2506","article-title":"Multi-modal sarcasm detection in Twitter with hierarchical fusion model","author":"Cai","year":"2019"},{"key":"10.1016\/j.knosys.2026.116541_b8","series-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics","first-page":"3777","article-title":"Reasoning with multimodal sarcastic tweets via modeling cross-modality contrast and semantic association","author":"Xu","year":"2020"},{"key":"10.1016\/j.knosys.2026.116541_b9","series-title":"Findings of the Association for Computational Linguistics: EMNLP 2020","first-page":"1383","article-title":"Modeling intra and inter-modality incongruity for multi-modal sarcasm detection","author":"Pan","year":"2020"},{"key":"10.1016\/j.knosys.2026.116541_b10","series-title":"Proceedings of the 29th ACM International Conference on Multimedia","first-page":"4707","article-title":"Multi-modal sarcasm detection with interactive in-modal and cross-modal graphs","author":"Liang","year":"2021"},{"key":"10.1016\/j.knosys.2026.116541_b11","series-title":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","first-page":"1767","article-title":"Multi-modal sarcasm detection via cross-modal graph convolutional network","author":"Liang","year":"2022"},{"key":"10.1016\/j.knosys.2026.116541_b12","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"9151","article-title":"G2SAM: Graph-based global semantic awareness method for multimodal sarcasm detection","author":"Wei","year":"2024"},{"key":"10.1016\/j.knosys.2026.116541_b13","doi-asserted-by":"crossref","DOI":"10.1109\/TCSVT.2025.3530436","article-title":"DeepMSD: Advancing multimodal sarcasm detection through knowledge-augmented graph reasoning","author":"Wei","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.knosys.2026.116541_b14","series-title":"Proceedings of the 31st International Conference on Computational Linguistics","first-page":"380","article-title":"Ambiguity-aware multi-level incongruity fusion network for multi-modal sarcasm detection","author":"Li","year":"2025"},{"key":"10.1016\/j.knosys.2026.116541_b15","series-title":"Findings of the Association for Computational Linguistics: ACL 2023","first-page":"10834","article-title":"MMSD2.0: Towards a reliable multi-modal sarcasm detection system","author":"Qin","year":"2023"},{"key":"10.1016\/j.knosys.2026.116541_b16","series-title":"2015 IEEE Global Communications Conference","first-page":"1","article-title":"Sarcasm detection in twitter:\u201c all your products are incredibly amazing!!!\u201d-are they really?","author":"Bouazizi","year":"2015"},{"key":"10.1016\/j.knosys.2026.116541_b17","series-title":"Proceedings of the Eighth ACM International Conference on Web Search and Data Mining","first-page":"97","article-title":"Sarcasm detection on twitter: A behavioral modeling approach","author":"Rajadesingan","year":"2015"},{"key":"10.1016\/j.knosys.2026.116541_b18","series-title":"Proceedings of the 24th ACM International Conference on Multimedia","first-page":"1136","article-title":"Detecting sarcasm in multimodal social platforms","author":"Schifanella","year":"2016"},{"issue":"4","key":"10.1016\/j.knosys.2026.116541_b19","doi-asserted-by":"crossref","first-page":"1874","DOI":"10.1109\/TAFFC.2024.3380375","article-title":"Fusion and discrimination: A multimodal graph contrastive learning framework for multimodal sarcasm detection","volume":"15","author":"Liang","year":"2024","journal-title":"IEEE Trans. Affect. Comput."},{"key":"10.1016\/j.knosys.2026.116541_b20","series-title":"Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation","first-page":"2493","article-title":"Breakthrough from nuance and inconsistency: Enhancing multimodal sarcasm detection with context-aware self-attention fusion and word weight calculation","author":"Xue","year":"2024"},{"key":"10.1016\/j.knosys.2026.116541_b21","series-title":"International Conference on Machine Learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.knosys.2026.116541_b22","article-title":"InterCLIP-MEP: Interactive CLIP and memory-enhanced predictor for multi-modal sarcasm detection","author":"Chen","year":"2025","journal-title":"ACM Trans. Multimed. Comput. Commun. Appl."},{"key":"10.1016\/j.knosys.2026.116541_b23","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"18354","article-title":"Debiasing multimodal sarcasm detection with contrastive learning","author":"Jia","year":"2024"},{"key":"10.1016\/j.knosys.2026.116541_b24","series-title":"Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence, IJCAI-24","first-page":"6687","article-title":"TFCD: Towards multi-modal sarcasm detection via training-free counterfactual debiasing","author":"Zhu","year":"2024"},{"key":"10.1016\/j.knosys.2026.116541_b25","series-title":"Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","first-page":"9663","article-title":"CofiPara: A coarse-to-fine paradigm for multimodal sarcasm target identification with large multimodal models","author":"Chen","year":"2024"},{"key":"10.1016\/j.knosys.2026.116541_b26","series-title":"ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"1","article-title":"LDGNet: LLMs debate-guided network for multimodal sarcasm detection","author":"Zhou","year":"2025"},{"key":"10.1016\/j.knosys.2026.116541_b27","series-title":"Seeing sarcasm through different eyes: Analyzing multimodal sarcasm perception in large vision-language models","author":"Chen","year":"2025"},{"key":"10.1016\/j.knosys.2026.116541_b28","series-title":"Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing","first-page":"16051","article-title":"Joyful: Joint modality fusion and graph contrastive learning for multimoda emotion recognition","author":"Li","year":"2023"},{"key":"10.1016\/j.knosys.2026.116541_b29","series-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019"},{"key":"10.1016\/j.knosys.2026.116541_b30","series-title":"2016 IEEE Conference on Computer Vision and Pattern Recognition","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"10.1016\/j.knosys.2026.116541_b31","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"17933","article-title":"DocMSU: A comprehensive benchmark for document-level multimodal sarcasm understanding","volume":"Vol. 38","author":"Du","year":"2024"},{"key":"10.1016\/j.knosys.2026.116541_b32","series-title":"Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing","first-page":"1746","article-title":"Convolutional neural networks for sentence classification","author":"Kim","year":"2014"},{"key":"10.1016\/j.knosys.2026.116541_b33","series-title":"Bidirectional LSTM-CRF models for sequence tagging","author":"Huang","year":"2015"},{"key":"10.1016\/j.knosys.2026.116541_b34","series-title":"Proceedings of the 2019 World Wide Web Conference","first-page":"2115","article-title":"Sarcasm detection with self-matching networks and low-rank bilinear pooling","author":"Xiong","year":"2019"},{"key":"10.1016\/j.knosys.2026.116541_b35","series-title":"Roberta: A robustly optimized bert pretraining approach","author":"Liu","year":"2019"},{"key":"10.1016\/j.knosys.2026.116541_b36","series-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"10.1016\/j.knosys.2026.116541_b37","series-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"10.1016\/j.knosys.2026.116541_b38","series-title":"The llama 3 herd of models","author":"Dubey","year":"2024"},{"key":"10.1016\/j.knosys.2026.116541_b39","series-title":"Qwen2.5 technical report","author":"Yang","year":"2024"},{"key":"10.1016\/j.knosys.2026.116541_b40","series-title":"Advances in Neural Information Processing Systems","first-page":"34892","article-title":"Visual instruction tuning","author":"Liu","year":"2023"},{"key":"10.1016\/j.knosys.2026.116541_b41","series-title":"International Conference on Machine Learning","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023"},{"key":"10.1016\/j.knosys.2026.116541_b42","series-title":"Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing","first-page":"4995","article-title":"Towards multi-modal sarcasm detection via hierarchical congruity modeling with knowledge enhancement","author":"Liu","year":"2022"},{"key":"10.1016\/j.knosys.2026.116541_b43","series-title":"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","first-page":"2468","article-title":"Dynamic routing transformer network for multimodal sarcasm detection","author":"Tian","year":"2023"},{"key":"10.1016\/j.knosys.2026.116541_b44","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"2540","article-title":"Dip: Dual incongruity perceiving network for sarcasm detection","author":"Wen","year":"2023"},{"key":"10.1016\/j.knosys.2026.116541_b45","series-title":"Proceedings of the 37th AAAI Conference on Artificial Intelligence","first-page":"9507","article-title":"Mutual-enhanced incongruity learning network for multi-modal sarcasm detection","author":"Qiao","year":"2023"},{"key":"10.1016\/j.knosys.2026.116541_b46","series-title":"Proceedings of the 32nd ACM International Conference on Multimedia","first-page":"4264","article-title":"MoBA: Mixture of bi-directional adapter for multi-modal sarcasm detection","author":"Xie","year":"2024"},{"issue":"5","key":"10.1016\/j.knosys.2026.116541_b47","doi-asserted-by":"crossref","first-page":"3755","DOI":"10.1109\/TCSVT.2023.3319330","article-title":"MC-blur: A comprehensive benchmark for image deblurring","volume":"34","author":"Zhang","year":"2024","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.knosys.2026.116541_b48","doi-asserted-by":"crossref","unstructured":"T. Wang, K. Zhang, T. Shen, W. Luo, B. Stenger, T. Lu, Ultra-high-definition low-light image enhancement: A benchmark and transformer-based method, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 37, 2023, pp. 2654\u20132662.","DOI":"10.1609\/aaai.v37i3.25364"},{"key":"10.1016\/j.knosys.2026.116541_b49","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111628","article-title":"LLDiffusion: Learning degradation representations in diffusion models for low-light image enhancement","volume":"166","author":"Wang","year":"2025","journal-title":"Pattern Recognit."},{"issue":"10","key":"10.1016\/j.knosys.2026.116541_b50","doi-asserted-by":"crossref","first-page":"4541","DOI":"10.1007\/s11263-024-02056-0","article-title":"GridFormer: Residual dense transformer with grid structure for image restoration in adverse weather conditions","volume":"132","author":"Wang","year":"2024","journal-title":"Int. J. Comput. Vis."}],"container-title":["Knowledge-Based Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126012670?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126012670?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T20:49:51Z","timestamp":1782852591000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0950705126012670"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":50,"alternative-id":["S0950705126012670"],"URL":"https:\/\/doi.org\/10.1016\/j.knosys.2026.116541","relation":{},"ISSN":["0950-7051"],"issn-type":[{"value":"0950-7051","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Complementary encoder refinement and multilevel crossmodal interaction for multimodal sarcasm detection","name":"articletitle","label":"Article Title"},{"value":"Knowledge-Based Systems","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.knosys.2026.116541","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"116541"}}