{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T12:00:20Z","timestamp":1781006420825,"version":"3.54.1"},"reference-count":75,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"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":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Knowledge-Based Systems"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1016\/j.knosys.2026.116137","type":"journal-article","created":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T16:25:05Z","timestamp":1778084705000},"page":"116137","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["BIG-TM: Bridging Individual Guidance with Trifusion MoPoE for Chinese memes understanding"],"prefix":"10.1016","volume":"345","author":[{"given":"Tongguan","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junkai","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feiyue","family":"Xue","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongyu","family":"Su","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guixin","family":"Su","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaopeng","family":"Wen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6638-5009","authenticated-orcid":false,"given":"Ying","family":"Sha","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.knosys.2026.116137_b1","series-title":"Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, Virtual","article-title":"The hateful memes challenge: Detecting hate speech in multimodal memes","author":"Kiela","year":"2020"},{"key":"10.1016\/j.knosys.2026.116137_b2","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.111778","article-title":"What do they \u201cmeme\u201d? A metaphor-aware multi-modal multi-task framework for fine-grained meme understanding","volume":"294","author":"Wang","year":"2024","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2026.116137_b3","article-title":"RCLMuFN: Relational context learning and multiplex fusion network for multimodal sarcasm detection","author":"Wang","year":"2025","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2026.116137_b4","series-title":"Advances in Neural Information Processing Systems","first-page":"49659","article-title":"JourneyDB: A benchmark for generative image understanding","volume":"Vol. 36","author":"Sun","year":"2023"},{"key":"10.1016\/j.knosys.2026.116137_b5","doi-asserted-by":"crossref","unstructured":"D. Zhang, M. Zhang, H. Zhang, L. Yang, H. Lin, MultiMET: A multimodal dataset for metaphor understanding, in: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), 2021, pp. 3214\u20133225.","DOI":"10.18653\/v1\/2021.acl-long.249"},{"key":"10.1016\/j.knosys.2026.116137_b6","series-title":"Findings of the Association for Computational Linguistics: EMNLP 2023","first-page":"6141","article-title":"Multicmet: A novel chinese benchmark for understanding multimodal metaphor","author":"Zhang","year":"2023"},{"key":"10.1016\/j.knosys.2026.116137_b7","series-title":"Hummus: A dataset of humorous multimodal metaphor use","author":"Tong","year":"2025"},{"key":"10.1016\/j.knosys.2026.116137_b8","series-title":"Proceedings of the ACM Web Conference 2024","isbn-type":"print","doi-asserted-by":"crossref","first-page":"4642","DOI":"10.1145\/3589334.3648151","article-title":"MemeCraft: Contextual and stance-driven multimodal meme generation","author":"Wang","year":"2024","ISBN":"https:\/\/id.crossref.org\/isbn\/9798400701719"},{"key":"10.1016\/j.knosys.2026.116137_b9","doi-asserted-by":"crossref","unstructured":"B. Xu, J. Zheng, J. He, Y. Sun, H. Lin, L. Zhao, F. Xia, Generating Multimodal Metaphorical Features for Meme Understanding, in: Proceedings of the 32nd ACM International Conference on Multimedia, 2024, pp. 447\u2013455.","DOI":"10.1145\/3664647.3681060"},{"key":"10.1016\/j.knosys.2026.116137_b10","doi-asserted-by":"crossref","unstructured":"Y. Chen, S. Yan, Z. Zhu, Z. Li, Y. Xiao, Xmecap: Meme caption generation with sub-image adaptability, in: Proceedings of the 32nd ACM International Conference on Multimedia, 2024, pp. 3352\u20133361.","DOI":"10.1145\/3664647.3681332"},{"key":"10.1016\/j.knosys.2026.116137_b11","series-title":"Toxic memes: A survey of computational perspectives on the detection and explanation of meme toxicities","author":"Pandiani","year":"2024"},{"key":"10.1016\/j.knosys.2026.116137_b12","series-title":"Proceedings of the Second Workshop on Trolling, Aggression and Cyberbullying, TRAC@LREC 2020, Marseille, France, May 2020","first-page":"32","article-title":"Multimodal meme dataset (multioff) for identifying offensive content in image and text","author":"Suryawanshi","year":"2020"},{"key":"10.1016\/j.knosys.2026.116137_b13","series-title":"Findings of the Association for Computational Linguistics: ACL\/IJCNLP 2021, Online Event, August 1-6, 2021","first-page":"2783","article-title":"Detecting harmful memes and their targets","author":"Pramanick","year":"2021"},{"key":"10.1016\/j.knosys.2026.116137_b14","series-title":"Findings of the Association for Computational Linguistics: EMNLP 2021, Virtual Event \/ Punta Cana, Dominican Republic, 16-20 November, 2021","first-page":"4439","article-title":"MOMENTA: A multimodal framework for detecting harmful memes and their targets","author":"Pramanick","year":"2021"},{"key":"10.1016\/j.knosys.2026.116137_b15","series-title":"Enhance multimodal transformer with external label and in-domain pretrain: Hateful meme challenge winning solution","author":"Zhu","year":"2020"},{"key":"10.1016\/j.knosys.2026.116137_b16","series-title":"MM \u201922: The 30th ACM International Conference on Multimedia, Lisboa, Portugal, October 10 - 14, 2022","first-page":"4505","article-title":"Multimodal hate speech detection via cross-domain knowledge transfer","author":"Yang","year":"2022"},{"key":"10.1016\/j.knosys.2026.116137_b17","series-title":"Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022, Abu Dhabi, United Arab Emirates, December 7-11, 2022","first-page":"321","article-title":"Prompting for multimodal hateful meme classification","author":"Cao","year":"2022"},{"key":"10.1016\/j.knosys.2026.116137_b18","series-title":"Proceedings of the 31st ACM International Conference on Multimedia, MM 2023, Ottawa, on, Canada, 29 October 2023- 3 November 2023","first-page":"5244","article-title":"Pro-cap: Leveraging a frozen vision-language model for hateful meme detection","author":"Cao","year":"2023"},{"key":"10.1016\/j.knosys.2026.116137_b19","series-title":"Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2024, Bangkok, Thailand, August 11-16, 2024","first-page":"4361","article-title":"Uncertainty-guided modal rebalance for hateful memes detection","author":"Yang","year":"2024"},{"key":"10.1016\/j.knosys.2026.116137_b20","series-title":"Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2024, Bangkok, Thailand, August 11-16, 2024","first-page":"5333","article-title":"Improving hateful meme detection through retrieval-guided contrastive learning","author":"Mei","year":"2024"},{"key":"10.1016\/j.knosys.2026.116137_b21","series-title":"Proceedings of the ACM on Web Conference 2024, WWW 2024, Singapore, May 13-17, 2024","first-page":"2359","article-title":"Towards explainable harmful meme detection through multimodal debate between large language models","author":"Lin","year":"2024"},{"key":"10.1016\/j.knosys.2026.116137_b22","doi-asserted-by":"crossref","unstructured":"C. Zhu, H. Gao, Y. Duan, G. Hao, M. Luo, X. Zhao, OSPC: OCR-Assisted VLM for Zero-Shot Harmful Meme Detection, in: Companion Proceedings of the ACM Web Conference 2024, 2024, pp. 1904\u20131907.","DOI":"10.1145\/3589335.3665994"},{"key":"10.1016\/j.knosys.2026.116137_b23","first-page":"13302","article-title":"Towards comprehensive detection of chinese harmful memes","volume":"37","author":"Lu","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.116137_b24","unstructured":"W. Huang, J. Liang, G. Wan, D. Zhu, H. Li, J. Shao, M. Ye, B. Du, D. Tao, Be confident: Uncovering overfitting in mllm multi-task tuning, in: Forty-Second International Conference on Machine Learning, 2025."},{"key":"10.1016\/j.knosys.2026.116137_b25","series-title":"Zero shot VLMs for hate meme detection: Are we there yet?","author":"Rizwan","year":"2024"},{"key":"10.1016\/j.knosys.2026.116137_b26","doi-asserted-by":"crossref","unstructured":"B.R. Chakravarthi, R. Ponnusamy, S. Rajiakodi, S.P.M. Chinnan, P. Buitelaar, B. Sivagnanam, A. KA, Findings of the Shared Task on Misogyny Meme Detection: DravidianLangTech@ NAACL 2025, in: Proceedings of the Fifth Workshop on Speech, Vision, and Language Technologies for Dravidian Languages, 2025, pp. 721\u2013731.","DOI":"10.18653\/v1\/2025.dravidianlangtech-1.123"},{"key":"10.1016\/j.knosys.2026.116137_b27","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2024.102269","article-title":"KERMIT: knowledge-empowered model in harmful meme detection","volume":"106","author":"Grasso","year":"2024","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.knosys.2026.116137_b28","doi-asserted-by":"crossref","unstructured":"E. Hossain, O. Sharif, M.M. Hoque, S.M. Preum, Deciphering Hate: Identifying Hateful Memes and Their Targets, in: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2024, pp. 8347\u20138359.","DOI":"10.18653\/v1\/2024.acl-long.454"},{"key":"10.1016\/j.knosys.2026.116137_b29","series-title":"International Conference on Advanced Communications and Machine Intelligence","first-page":"107","article-title":"Identification of misogynistic memes using transformer models","author":"Chinivar","year":"2024"},{"key":"10.1016\/j.knosys.2026.116137_b30","series-title":"Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence, IJCAI 2024, Jeju, South Korea, August 3-9, 2024","first-page":"6397","article-title":"Prompt-enhanced network for hateful meme classification","author":"Liu","year":"2024"},{"key":"10.1016\/j.knosys.2026.116137_b31","series-title":"CCF International Conference on Natural Language Processing and Chinese Computing","first-page":"95","article-title":"CETA: Context-enhanced and target-aware hateful meme inference method","author":"Wang","year":"2024"},{"key":"10.1016\/j.knosys.2026.116137_b32","doi-asserted-by":"crossref","unstructured":"J. Ji, X. Lin, U. Naseem, CapAlign: Improving Cross Modal Alignment via Informative Captioning for Harmful Meme Detection, in: Proceedings of the ACM on Web Conference 2024, 2024, pp. 4585\u20134594.","DOI":"10.1145\/3589334.3648146"},{"key":"10.1016\/j.knosys.2026.116137_b33","first-page":"1","article-title":"SCARE: A novel framework to enhance Chinese harmful memes detection","author":"Gu","year":"2024","journal-title":"IEEE Trans. Affect. Comput."},{"key":"10.1016\/j.knosys.2026.116137_b34","doi-asserted-by":"crossref","unstructured":"D. Hazarika, R. Zimmermann, S. Poria, Misa: Modality-invariant and-specific representations for multimodal sentiment analysis, in: Proceedings of the 28th ACM International Conference on Multimedia, 2020, pp. 1122\u20131131.","DOI":"10.1145\/3394171.3413678"},{"key":"10.1016\/j.knosys.2026.116137_b35","doi-asserted-by":"crossref","first-page":"2740","DOI":"10.1109\/TMM.2023.3303711","article-title":"Dynamically shifting multimodal representations via hybrid-modal attention for multimodal sentiment analysis","volume":"26","author":"Lin","year":"2023","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.knosys.2026.116137_b36","unstructured":"R. Lin, Q. He, S. Mai, Y. Zeng, A. Xiong, L. Huang, Y.-P. Tan, H. Hu, CyIN: Cyclic Informative Latent Space for Bridging Complete and Incomplete Multimodal Learning, in: The Thirty-Ninth Annual Conference on Neural Information Processing Systems, 2025."},{"issue":"1","key":"10.1016\/j.knosys.2026.116137_b37","doi-asserted-by":"crossref","DOI":"10.1215\/S0012-7094-40-00725-6","article-title":"The method of orthogonal projection in potential theory","volume":"7","author":"Weyl","year":"1940","journal-title":"Duke Math. J."},{"key":"10.1016\/j.knosys.2026.116137_b38","series-title":"Asian Conference on Machine Learning","first-page":"1","article-title":"Learning convolutional neural networks using hybrid orthogonal projection and estimation","author":"Pan","year":"2017"},{"key":"10.1016\/j.knosys.2026.116137_b39","doi-asserted-by":"crossref","first-page":"376","DOI":"10.1007\/s10851-019-00902-2","article-title":"On orthogonal projections for dimension reduction and applications in augmented target loss functions for learning problems","volume":"62","author":"Breger","year":"2020","journal-title":"J. Math. Imaging Vision"},{"key":"10.1016\/j.knosys.2026.116137_b40","series-title":"KOPPA: Improving prompt-based continual learning with key-query orthogonal projection and prototype-based one-versus-all","author":"Tran","year":"2023"},{"issue":"9","key":"10.1016\/j.knosys.2026.116137_b41","doi-asserted-by":"crossref","first-page":"5518","DOI":"10.1002\/mp.16377","article-title":"Deep learning-based fast volumetric imaging using kV and MV projection images for lung cancer radiotherapy: a feasibility study","volume":"50","author":"Lei","year":"2023","journal-title":"Med. Phys."},{"key":"10.1016\/j.knosys.2026.116137_b42","article-title":"Revisiting flatness-aware optimization in continual learning with orthogonal gradient projection","author":"Yang","year":"2025","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"1","key":"10.1016\/j.knosys.2026.116137_b43","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1162\/neco.1991.3.1.79","article-title":"Adaptive mixtures of local experts","volume":"3","author":"Jacobs","year":"1991","journal-title":"Neural Comput."},{"issue":"4","key":"10.1016\/j.knosys.2026.116137_b44","doi-asserted-by":"crossref","first-page":"948","DOI":"10.1109\/72.857774","article-title":"Mixture of experts for classification of gender, ethnic origin, and pose of human faces","volume":"11","author":"Gutta","year":"2000","journal-title":"IEEE Trans. Neural Netw."},{"key":"10.1016\/j.knosys.2026.116137_b45","doi-asserted-by":"crossref","unstructured":"P. Le, M. Dymetman, J.-M. Renders, LSTM-Based Mixture-of-Experts for Knowledge-Aware Dialogues, in: Proceedings of the 1st Workshop on Representation Learning for NLP, 2016, pp. 94\u201399.","DOI":"10.18653\/v1\/W16-1611"},{"key":"10.1016\/j.knosys.2026.116137_b46","series-title":"Findings of the Association for Computational Linguistics: EMNLP 2023","first-page":"11329","article-title":"Scaling vision-language models with sparse mixture of experts","author":"Shen","year":"2023"},{"key":"10.1016\/j.knosys.2026.116137_b47","doi-asserted-by":"crossref","unstructured":"Z. Xie, Y. Zhang, C. Zhuang, Q. Shi, Z. Liu, J. Gu, G. Zhang, Mode: A mixture-of-experts model with mutual distillation among the experts, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 38, 2024, pp. 16067\u201316075.","DOI":"10.1609\/aaai.v38i14.29539"},{"key":"10.1016\/j.knosys.2026.116137_b48","doi-asserted-by":"crossref","unstructured":"D. Dai, C. Deng, C. Zhao, R. Xu, H. Gao, D. Chen, J. Li, W. Zeng, X. Yu, Y. Wu, et al., DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models, in: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2024, pp. 1280\u20131297.","DOI":"10.18653\/v1\/2024.acl-long.70"},{"key":"10.1016\/j.knosys.2026.116137_b49","series-title":"Findings of the Association for Computational Linguistics: EMNLP 2024","first-page":"10456","article-title":"MoE-I2: Compressing mixture of experts models through inter-expert pruning and intra-expert low-rank decomposition","author":"Yang","year":"2024"},{"key":"10.1016\/j.knosys.2026.116137_b50","doi-asserted-by":"crossref","unstructured":"X. Lu, Q. Liu, Y. Xu, A. Zhou, S. Huang, B. Zhang, J. Yan, H. Li, Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models, in: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2024, pp. 6159\u20136172.","DOI":"10.18653\/v1\/2024.acl-long.334"},{"key":"10.1016\/j.knosys.2026.116137_b51","unstructured":"M.N.R. Chowdhury, M. Wang, K. El Maghraoui, N. Wang, P.-Y. Chen, C. Carothers, A provably effective method for pruning experts in fine-tuned sparse mixture-of-experts, in: Proceedings of the 41st International Conference on Machine Learning, 2024, pp. 8815\u20138847."},{"key":"10.1016\/j.knosys.2026.116137_b52","series-title":"MoE-Pruner: Pruning mixture-of-experts large language model using the hints from its router","author":"Xie","year":"2024"},{"key":"10.1016\/j.knosys.2026.116137_b53","doi-asserted-by":"crossref","first-page":"67850","DOI":"10.52202\/079017-2167","article-title":"Fusemoe: Mixture-of-experts transformers for fleximodal fusion","volume":"37","author":"Han","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"8","key":"10.1016\/j.knosys.2026.116137_b54","doi-asserted-by":"crossref","first-page":"1771","DOI":"10.1162\/089976602760128018","article-title":"Training products of experts by minimizing contrastive divergence","volume":"14","author":"Hinton","year":"2002","journal-title":"Neural Comput."},{"issue":"10","key":"10.1016\/j.knosys.2026.116137_b55","doi-asserted-by":"crossref","first-page":"3879","DOI":"10.4249\/scholarpedia.3879","article-title":"Product of experts","volume":"2","author":"Welling","year":"2007","journal-title":"Scholarpedia"},{"key":"10.1016\/j.knosys.2026.116137_b56","article-title":"Variational mixture-of-experts autoencoders for multi-modal deep generative models","volume":"32","author":"Shi","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.116137_b57","article-title":"Multimodal generative models for scalable weakly-supervised learning","volume":"31","author":"Wu","year":"2018","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.116137_b58","doi-asserted-by":"crossref","unstructured":"A. Joshi, N. Gupta, J. Shah, B. Bhattarai, A. Modi, D. Stoyanov, Generalized product-of-experts for learning multimodal representations in noisy environments, in: Proceedings of the 2022 International Conference on Multimodal Interaction, 2022, pp. 83\u201393.","DOI":"10.1145\/3536221.3556596"},{"key":"10.1016\/j.knosys.2026.116137_b59","doi-asserted-by":"crossref","unstructured":"P. Qiu, W. Zhu, S. Kumar, X. Chen, J. Yang, X. Sun, A. Razi, Y. Wang, A. Sotiras, Multimodal variational autoencoder: A barycentric view, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 39, 2025, pp. 20060\u201320068.","DOI":"10.1609\/aaai.v39i19.34209"},{"key":"10.1016\/j.knosys.2026.116137_b60","series-title":"Product of experts for visual generation","author":"Zhang","year":"2025"},{"key":"10.1016\/j.knosys.2026.116137_b61","doi-asserted-by":"crossref","unstructured":"T. Yue, X. Shi, R. Mao, Z. Hu, E. Cambria, SarcNet: a multilingual multimodal sarcasm detection dataset, in: Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation, LREC-COLING 2024, 2024, pp. 14325\u201314335.","DOI":"10.63317\/2kcxx9snfhyk"},{"key":"10.1016\/j.knosys.2026.116137_b62","series-title":"RoBERTa: A robustly optimized BERT pretraining approach","author":"Liu","year":"2019"},{"key":"10.1016\/j.knosys.2026.116137_b63","series-title":"2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016, Las Vegas, NV, USA, June 27-30, 2016","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"10.1016\/j.knosys.2026.116137_b64","series-title":"9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021"},{"key":"10.1016\/j.knosys.2026.116137_b65","series-title":"Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18-24 July 2021, Virtual Event","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.knosys.2026.116137_b66","doi-asserted-by":"crossref","unstructured":"S.B. Shah, S. Shiwakoti, M. Chaudhary, H. Wang, Memeclip: Leveraging clip representations for multimodal meme classification, in: Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024, pp. 17320\u201317332.","DOI":"10.18653\/v1\/2024.emnlp-main.959"},{"issue":"2","key":"10.1016\/j.knosys.2026.116137_b67","doi-asserted-by":"crossref","first-page":"933","DOI":"10.1109\/TAFFC.2024.3481419","article-title":"SCARE: A novel framework to enhance Chinese harmful memes detection","volume":"16","author":"Gu","year":"2024","journal-title":"IEEE Trans. Affect. Comput."},{"issue":"4","key":"10.1016\/j.knosys.2026.116137_b68","doi-asserted-by":"crossref","DOI":"10.1016\/j.ipm.2025.104602","article-title":"Multi-view dynamic perception framework for Chinese harmful meme detection","volume":"63","author":"Hu","year":"2026","journal-title":"Inf. Process. Manage."},{"key":"10.1016\/j.knosys.2026.116137_b69","doi-asserted-by":"crossref","unstructured":"J. Devlin, M.-W. Chang, K. Lee, K. Toutanova, Bert: Pre-training of deep bidirectional transformers for language understanding, in: 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), 2019, pp. 4171\u20134186.","DOI":"10.18653\/v1\/N19-1423"},{"key":"10.1016\/j.knosys.2026.116137_b70","doi-asserted-by":"crossref","unstructured":"A. Conneau, K. Khandelwal, N. Goyal, V. Chaudhary, G. Wenzek, F. Guzm\u00e1n, E. Grave, M. Ott, L. Zettlemoyer, V. Stoyanov, Unsupervised cross-lingual representation learning at scale, in: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, 2020, pp. 8440\u20138451.","DOI":"10.18653\/v1\/2020.acl-main.747"},{"issue":"6","key":"10.1016\/j.knosys.2026.116137_b71","doi-asserted-by":"crossref","first-page":"7399","DOI":"10.1007\/s12652-022-04447-y","article-title":"Transformer-based models for multimodal irony detection","volume":"14","author":"Tom\u00e1s","year":"2023","journal-title":"J. Ambient Intell. Humaniz. Comput."},{"issue":"5","key":"10.1016\/j.knosys.2026.116137_b72","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":"2023","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.knosys.2026.116137_b73","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.2026.116137_b74","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.2026.116137_b75","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:S0950705126008634?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126008634?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T11:25:27Z","timestamp":1781004327000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0950705126008634"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":75,"alternative-id":["S0950705126008634"],"URL":"https:\/\/doi.org\/10.1016\/j.knosys.2026.116137","relation":{},"ISSN":["0950-7051"],"issn-type":[{"value":"0950-7051","type":"print"}],"subject":[],"published":{"date-parts":[[2026,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"BIG-TM: Bridging Individual Guidance with Trifusion MoPoE for Chinese memes understanding","name":"articletitle","label":"Article Title"},{"value":"Knowledge-Based Systems","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.knosys.2026.116137","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":"116137"}}