{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T21:56:53Z","timestamp":1781301413547,"version":"3.54.1"},"reference-count":48,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"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","award":["62376027"],"award-info":[{"award-number":["62376027"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.patcog.2026.113712","type":"journal-article","created":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T17:17:32Z","timestamp":1776100652000},"page":"113712","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PB","title":["MADSC: Aspect-aware description and calibrated alignment for unified Multimodal Aspect-Based Sentiment Analysis"],"prefix":"10.1016","volume":"179","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3307-4017","authenticated-orcid":false,"given":"Tianyu","family":"Zhao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-0106-0478","authenticated-orcid":false,"given":"Ling-Ang","family":"Meng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8660-3608","authenticated-orcid":false,"given":"Dawei","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2026.113712_b1","doi-asserted-by":"crossref","unstructured":"J. Yu, J. Jiang, Adapting BERT for Target-Oriented Multimodal Sentiment Classification, in: IJCAI, 2019, pp. 5408\u20135414.","DOI":"10.24963\/ijcai.2019\/751"},{"key":"10.1016\/j.patcog.2026.113712_b2","doi-asserted-by":"crossref","unstructured":"X. Ju, D. Zhang, R. Xiao, J. Li, S. Li, M. Zhang, G. Zhou, Joint multi-modal aspect-sentiment analysis with auxiliary cross-modal relation detection, in: EMNLP, 2021, pp. 4395\u20134405.","DOI":"10.18653\/v1\/2021.emnlp-main.360"},{"issue":"11","key":"10.1016\/j.patcog.2026.113712_b3","doi-asserted-by":"crossref","first-page":"2253","DOI":"10.1109\/JAS.2024.124521","article-title":"Image enhancement via associated perturbation removal and texture reconstruction learning","volume":"11","author":"Jiang","year":"2024","journal-title":"IEEE\/CAA J. Autom. Sin."},{"key":"10.1016\/j.patcog.2026.113712_b4","doi-asserted-by":"crossref","first-page":"1766","DOI":"10.1109\/TIP.2025.3547298","article-title":"Multi-axis feature diversity enhancement for remote sensing video super-resolution","author":"Xiao","year":"2025","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.patcog.2026.113712_b5","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111870","article-title":"Towards robust sentiment analysis with multimodal interaction graph and hybrid contrastive learning","volume":"169","author":"Gong","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113712_b6","series-title":"Is ChatGPT a good sentiment analyzer? A preliminary study","author":"Wang","year":"2023"},{"key":"10.1016\/j.patcog.2026.113712_b7","doi-asserted-by":"crossref","unstructured":"X. Liu, P. Lin, X. Tu, W. Jia, C. Jiang, R. Li, SDG-MLLM: Injecting Structured Dialogue Graphs into MLLM for Multimodal Conversational Aspect-Based Sentiment Analysis, in: ACM MM, 2025, pp. 14114\u201314121.","DOI":"10.1145\/3746027.3762071"},{"key":"10.1016\/j.patcog.2026.113712_b8","series-title":"Hallucination of multimodal large language models: A survey","author":"Bai","year":"2024"},{"key":"10.1016\/j.patcog.2026.113712_b9","doi-asserted-by":"crossref","unstructured":"H. Liu, C. Li, Q. Wu, Y.J. Lee, Visual instruction tuning, in: NeurIPS, Vol. 36, 2023, pp. 34892\u201334916.","DOI":"10.52202\/075280-1516"},{"key":"10.1016\/j.patcog.2026.113712_b10","series-title":"Findings of EMNLP","first-page":"7535","article-title":"Difficult task yes but simple task no: Unveiling the laziness in multimodal LLMs","author":"Zhao","year":"2024"},{"key":"10.1016\/j.patcog.2026.113712_b11","doi-asserted-by":"crossref","unstructured":"Z. Chen, Z. Zhu, W. Xu, Y. Zhang, X. Wu, Y. Zheng, Aspects are Anchors: Towards Multimodal Aspect-based Sentiment Analysis via Aspect-driven Alignment and Refinement, in: ACM MM, 2024, pp. 2292\u20132300.","DOI":"10.1145\/3664647.3681189"},{"key":"10.1016\/j.patcog.2026.113712_b12","series-title":"Findings of ACL","first-page":"14369","article-title":"DaNet: Dual-aware enhanced alignment network for multimodal aspect-based sentiment analysis","author":"Zhu","year":"2025"},{"key":"10.1016\/j.patcog.2026.113712_b13","doi-asserted-by":"crossref","unstructured":"S. Moon, L. Neves, V. Carvalho, Multimodal Named Entity Recognition for Short Social Media Posts, in: NAACL-HLT, 2018, pp. 852\u2013860.","DOI":"10.18653\/v1\/N18-1078"},{"key":"10.1016\/j.patcog.2026.113712_b14","doi-asserted-by":"crossref","unstructured":"Q. Zhang, J. Fu, X. Liu, X. Huang, Adaptive co-attention network for named entity recognition in tweets, in: AAAI, 32, 2018, pp. 5674\u20135681.","DOI":"10.1609\/aaai.v32i1.11962"},{"key":"10.1016\/j.patcog.2026.113712_b15","doi-asserted-by":"crossref","unstructured":"M. Jia, L. Shen, X. Shen, L. Liao, M. Chen, X. He, Z. Chen, J. Li, Mner-qg: An end-to-end MRC framework for multimodal named entity recognition with query grounding, in: AAAI, 37, 2023, pp. 8032\u20138040.","DOI":"10.1609\/aaai.v37i7.25971"},{"key":"10.1016\/j.patcog.2026.113712_b16","doi-asserted-by":"crossref","first-page":"1274","DOI":"10.1109\/TASLP.2023.3345146","article-title":"Enhancing multimodal entity and relation extraction with variational information bottleneck","volume":"32","author":"Cui","year":"2024","journal-title":"IEEE\/ACM Trans. Audio, Speech, Lang. Process."},{"key":"10.1016\/j.patcog.2026.113712_b17","doi-asserted-by":"crossref","unstructured":"X. Hu, J. Chen, A. Liu, S. Meng, L. Wen, P.S. Yu, Prompt me up: Unleashing the power of alignments for multimodal entity and relation extraction, in: ACM MM, 2023, pp. 5185\u20135194.","DOI":"10.1145\/3581783.3611899"},{"key":"10.1016\/j.patcog.2026.113712_b18","doi-asserted-by":"crossref","unstructured":"J. Li, H. Li, Z. Pan, D. Sun, J. Wang, W. Zhang, G. Pan, Prompting chatgpt in MNER: enhanced multimodal named entity recognition with auxiliary refined knowledge, in: EMNLP, 2023, pp. 2787\u20132802.","DOI":"10.18653\/v1\/2023.findings-emnlp.184"},{"issue":"6","key":"10.1016\/j.patcog.2026.113712_b19","doi-asserted-by":"crossref","first-page":"1957","DOI":"10.1007\/s11280-021-00955-7","article-title":"ModalNet: an aspect-level sentiment classification model by exploring multimodal data with fusion discriminant attentional network","volume":"24","author":"Zhang","year":"2021","journal-title":"World Wide Web"},{"issue":"3","key":"10.1016\/j.patcog.2026.113712_b20","doi-asserted-by":"crossref","first-page":"688","DOI":"10.1109\/TETC.2022.3231746","article-title":"Affective region recognition and fusion network for target-level multimodal sentiment classification","volume":"12","author":"Jia","year":"2024","journal-title":"IEEE Trans. Emerg. Top. Comput."},{"key":"10.1016\/j.patcog.2026.113712_b21","doi-asserted-by":"crossref","unstructured":"Z. Khan, Y. Fu, Exploiting BERT for multimodal target sentiment classification through input space translation, in: ACM MM, 2021, pp. 3034\u20133042.","DOI":"10.1145\/3474085.3475692"},{"key":"10.1016\/j.patcog.2026.113712_b22","doi-asserted-by":"crossref","unstructured":"H. Yang, Y. Zhao, B. Qin, Face-Sensitive Image-to-Emotional-Text Cross-modal Translation for Multimodal Aspect-based Sentiment Analysis, in: EMNLP, 2022, pp. 3324\u20133335.","DOI":"10.18653\/v1\/2022.emnlp-main.219"},{"key":"10.1016\/j.patcog.2026.113712_b23","doi-asserted-by":"crossref","unstructured":"Y. Ling, J. Yu, R. Xia, Vision-Language Pre-Training for Multimodal Aspect-Based Sentiment Analysis, in: ACL, 2022, pp. 2149\u20132159.","DOI":"10.18653\/v1\/2022.acl-long.152"},{"key":"10.1016\/j.patcog.2026.113712_b24","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2024.102304","article-title":"Atlantis: Aesthetic-oriented multiple granularities fusion network for joint multimodal aspect-based sentiment analysis","author":"Xiao","year":"2024","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.patcog.2026.113712_b25","series-title":"Findings of ACL","first-page":"8184","article-title":"AoM: Detecting aspect-oriented information for multimodal aspect-based sentiment analysis","author":"Zhou","year":"2023"},{"key":"10.1016\/j.patcog.2026.113712_b26","doi-asserted-by":"crossref","unstructured":"D. Wang, Y. He, X. Liang, Y. Tian, S. Li, L. Zhao, TMFN: A Target-oriented Multi-grained Fusion Network for End-to-end Aspect-based Multimodal Sentiment Analysis, in: LREC-COLING, 2024, pp. 16187\u201316197.","DOI":"10.63317\/58q6gxohm4v4"},{"key":"10.1016\/j.patcog.2026.113712_b27","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111369","article-title":"A vision and language hierarchical alignment for multimodal aspect-based sentiment analysis","volume":"162","author":"Zou","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113712_b28","doi-asserted-by":"crossref","unstructured":"T. Peng, Z. Li, P. Wang, L. Zhang, H. Zhao, A novel energy based model mechanism for multi-modal aspect-based sentiment analysis, in: AAAI, 38, 2024, pp. 18869\u201318878.","DOI":"10.1609\/aaai.v38i17.29852"},{"key":"10.1016\/j.patcog.2026.113712_b29","doi-asserted-by":"crossref","unstructured":"J. Zhao, R. Li, Q. Jin, Missing modality imagination network for emotion recognition with uncertain missing modalities, in: ACL-IJCNLP, 2021, pp. 2608\u20132618.","DOI":"10.18653\/v1\/2021.acl-long.203"},{"key":"10.1016\/j.patcog.2026.113712_b30","article-title":"Resolving sentiment discrepancy for multimodal sentiment detection via semantics completion and decomposition","author":"Wu","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113712_b31","doi-asserted-by":"crossref","unstructured":"X. Zhang, J. Yoon, M. Bansal, H. Yao, Multimodal representation learning by alternating unimodal adaptation, in: CVPR, 2024, pp. 27456\u201327466.","DOI":"10.1109\/CVPR52733.2024.02592"},{"key":"10.1016\/j.patcog.2026.113712_b32","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2026.131591","article-title":"DAGG-net: Dual Adaptive Graph and Gating network for multimodal aspect-based sentiment analysis","author":"Han","year":"2026","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.patcog.2026.113712_b33","unstructured":"X. Liu, R. Li, S. Ye, G. Zhang, X. Wang, Multimodal Aspect-Based Sentiment Analysis under Conditional Relation, in: COLING 2025, 2025, pp. 313\u2013323."},{"key":"10.1016\/j.patcog.2026.113712_b34","doi-asserted-by":"crossref","unstructured":"J. Cheng, D. Liang, S. Tan, Transfer clip for generalizable image denoising, in: CVPR, 2024, pp. 25974\u201325984.","DOI":"10.1109\/CVPR52733.2024.02454"},{"key":"10.1016\/j.patcog.2026.113712_b35","doi-asserted-by":"crossref","unstructured":"Z. Yu, K. Jiang, J. Jiang, X. Liu, G. Sun, Y. Xiao, Semantics and Content Matter: Towards Multi-Prior Hierarchical Mamba for Image Deraining, in: AAAI, Vol. 40, No. 14, 2026, pp. 12222\u201312230.","DOI":"10.1609\/aaai.v40i14.38213"},{"key":"10.1016\/j.patcog.2026.113712_b36","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.131010","article-title":"Unpaired iterative prompt learning for real-world image deraining","author":"Wen","year":"2026","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.patcog.2026.113712_b37","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: NAACL-HLT, 2019, pp. 4171\u20134186.","DOI":"10.18653\/v1\/N19-1423"},{"key":"10.1016\/j.patcog.2026.113712_b38","doi-asserted-by":"crossref","unstructured":"P. Zhang, X. Li, X. Hu, J. Yang, L. Zhang, L. Wang, Y. Choi, J. Gao, Vinvl: Revisiting visual representations in vision-language models, in: CVPR, 2021, pp. 5579\u20135588.","DOI":"10.1109\/CVPR46437.2021.00553"},{"key":"10.1016\/j.patcog.2026.113712_b39","unstructured":"A. Dosovitskiy, L. Beyer, A. Kolesnikov, D. Weissenborn, X. Zhai, T. Unterthiner, M. Dehghani, M. Minderer, G. Heigold, S. Gelly, J. Uszkoreit, N. Houlsby, An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale, in: ICLR, 2021."},{"key":"10.1016\/j.patcog.2026.113712_b40","series-title":"Hello gpt-4o.","author":"OpenAI","year":"2024"},{"key":"10.1016\/j.patcog.2026.113712_b41","unstructured":"J. Li, D. Li, S. Savarese, S. Hoi, Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models, in: ICML, 2023, pp. 19730\u201319742."},{"key":"10.1016\/j.patcog.2026.113712_b42","doi-asserted-by":"crossref","unstructured":"B. Xu, S. Huang, C. Sha, H. Wang, MAF: a general matching and alignment framework for multimodal named entity recognition, in: ACM WSDM, 2022, pp. 1215\u20131223.","DOI":"10.1145\/3488560.3498475"},{"issue":"3","key":"10.1016\/j.patcog.2026.113712_b43","doi-asserted-by":"crossref","first-page":"1264","DOI":"10.1109\/TAFFC.2023.3333200","article-title":"Image-to-text conversion and aspect-oriented filtration for multimodal aspect-based sentiment analysis","volume":"15","author":"Wang","year":"2024","journal-title":"IEEE Trans. Affect. Comput."},{"key":"10.1016\/j.patcog.2026.113712_b44","unstructured":"L. Zhu, H. Sun, Q. Gao, T. Yi, L. He, Joint multimodal aspect sentiment analysis with aspect enhancement and syntactic adaptive learning, in: IJCAI, 2024, pp. 6678\u20136686."},{"key":"10.1016\/j.patcog.2026.113712_b45","doi-asserted-by":"crossref","unstructured":"Z. Han, M. Hu, Y. Bai, X. Wang, B. Luo, DEQA: Descriptions Enhanced Question-Answering Framework for Multimodal Aspect-Based Sentiment Analysis, in: AAAI, Vol. 39, 2025, pp. 23987\u201323995.","DOI":"10.1609\/aaai.v39i22.34572"},{"key":"10.1016\/j.patcog.2026.113712_b46","doi-asserted-by":"crossref","unstructured":"R. Liu, J. Cao, J. Ren, X. Bai, Y. Cao, Dual-Path Counterfactual Integration for Multimodal Aspect-Based Sentiment Classification, in: EMNLP, 2025, pp. 22759\u201322769.","DOI":"10.18653\/v1\/2025.emnlp-main.1158"},{"key":"10.1016\/j.patcog.2026.113712_b47","series-title":"Findings of ACL","first-page":"11575","article-title":"Few-shot joint multimodal aspect-sentiment analysis based on generative multimodal prompt","author":"Yang","year":"2023"},{"key":"10.1016\/j.patcog.2026.113712_b48","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2025.103878","article-title":"Semantic-guided multi-grained cross-modal alignment and fusion network for multimodal aspect-based sentiment analysis","volume":"127","author":"Lin","year":"2026","journal-title":"Inf. Fusion"}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326006771?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326006771?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T21:15:34Z","timestamp":1781298934000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326006771"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":48,"alternative-id":["S0031320326006771"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113712","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"MADSC: Aspect-aware description and calibrated alignment for unified Multimodal Aspect-Based Sentiment Analysis","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113712","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"113712"}}