{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T12:08:14Z","timestamp":1779192494397,"version":"3.51.4"},"reference-count":34,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"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":["62206114"],"award-info":[{"award-number":["62206114"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100017962","name":"Jiangsu Commission of Health","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100017962","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013280","name":"Major Basic Research Project of the Natural Science Foundation of the Jiangsu Higher Education Institutions","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100013280","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Information Fusion"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.inffus.2026.104374","type":"journal-article","created":{"date-parts":[[2026,4,12]],"date-time":"2026-04-12T16:34:29Z","timestamp":1776011669000},"page":"104374","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Decoding depression: A hybrid GRU\u2013Mamba architecture with multi-dimensional interpretability framework for facial dynamics analysis"],"prefix":"10.1016","volume":"134","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9427-4023","authenticated-orcid":false,"given":"Ge","family":"Jin","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5023-8038","authenticated-orcid":false,"given":"Xinyi","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1749-8653","authenticated-orcid":false,"given":"Qian","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8495-6648","authenticated-orcid":false,"given":"Yong","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-8922-3305","authenticated-orcid":false,"given":"Yingwen","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1224-4366","authenticated-orcid":false,"given":"Na","family":"Lyu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6135-3809","authenticated-orcid":false,"given":"Huiling","family":"Ye","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4284-3308","authenticated-orcid":false,"given":"Xin","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4957-0747","authenticated-orcid":false,"given":"Xiaohua","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0800-4842","authenticated-orcid":false,"given":"Qing","family":"Fan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"issue":"1","key":"10.1016\/j.inffus.2026.104374_bib0001","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1186\/s40708-023-00188-6","article-title":"Deep learning and machine learning in psychiatry: a survey of current progress in depression detection, diagnosis and treatment","volume":"10","author":"Squires","year":"2023","journal-title":"Brain Inf."},{"key":"10.1016\/j.inffus.2026.104374_bib0002","series-title":"2019 IEEE International Conference on Image Processing (ICIP)","first-page":"4544","article-title":"Depression detection based on deep distribution learning","author":"De Melo","year":"2019"},{"issue":"3","key":"10.1016\/j.inffus.2026.104374_bib0003","doi-asserted-by":"crossref","first-page":"1581","DOI":"10.1109\/TAFFC.2020.3021755","article-title":"A deep multiscale spatiotemporal network for assessing depression from facial dynamics","volume":"13","author":"De Melo","year":"2020","journal-title":"IEEE Trans. Affect. Comput."},{"issue":"5","key":"10.1016\/j.inffus.2026.104374_bib0004","doi-asserted-by":"crossref","first-page":"5728","DOI":"10.1109\/TCSS.2024.3393247","article-title":"Automatic diagnosis of depression based on facial expression information and deep convolutional neural network","volume":"11","author":"Li","year":"2024","journal-title":"IEEE Trans. Comput. Social Syst."},{"issue":"1","key":"10.1016\/j.inffus.2026.104374_bib0005","doi-asserted-by":"crossref","first-page":"87","DOI":"10.9758\/cpn.23.1059","article-title":"A deep learning driven simulation analysis of the emotional profiles of depression based on facial expression dynamics","volume":"22","author":"Lee","year":"2023","journal-title":"Clin. Psychopharmacol. Neurosci."},{"issue":"3","key":"10.1016\/j.inffus.2026.104374_bib0006","doi-asserted-by":"crossref","first-page":"1857","DOI":"10.1109\/TAFFC.2022.3143100","article-title":"An overview of facial micro-expression analysis: data, methodology and challenge","volume":"14","author":"Xie","year":"2022","journal-title":"IEEE Trans. Affect. Comput."},{"issue":"1","key":"10.1016\/j.inffus.2026.104374_bib0007","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1109\/TAFFC.2020.3035535","article-title":"Interpretation of depression detection models via feature selection methods","volume":"14","author":"Alghowinem","year":"2020","journal-title":"IEEE Trans. Affect. Comput."},{"key":"10.1016\/j.inffus.2026.104374_bib0008","unstructured":"F. Kares, T. Speith, H. Zhang, M. Langer, What makes for a good saliency map? Comparing strategies for evaluating saliency maps in explainable AI (XAI), arXiv: 2504.17023(2025)."},{"issue":"4","key":"10.1016\/j.inffus.2026.104374_bib0009","doi-asserted-by":"crossref","DOI":"10.1016\/j.apjo.2024.100087","article-title":"The role of saliency maps in enhancing ophthalmologists\u2019 trust in artificial intelligence models","volume":"13","author":"Wong","year":"2024","journal-title":"Asia-Pac. J. Ophthalmol."},{"issue":"1","key":"10.1016\/j.inffus.2026.104374_bib0010","doi-asserted-by":"crossref","first-page":"578","DOI":"10.1109\/TAFFC.2021.3072579","article-title":"MDN: a deep maximization-differentiation network for spatio-temporal depression detection","volume":"14","author":"de Melo","year":"2021","journal-title":"IEEE Trans. Affect. Comput."},{"key":"10.1016\/j.inffus.2026.104374_bib0011","doi-asserted-by":"crossref","unstructured":"Z. Hu, N.A. Daryakenari, Q. Shen, K. Kawaguchi, G.E. Karniadakis, State-space models are accurate and efficient neural operators for dynamical systems, arXiv: 2409.03231(2024).","DOI":"10.2139\/ssrn.4990229"},{"key":"10.1016\/j.inffus.2026.104374_bib0012","series-title":"First Conference on Language Modeling","article-title":"Mamba: linear-time sequence modeling with selective state spaces","author":"Gu","year":"2024"},{"issue":"3","key":"10.1016\/j.inffus.2026.104374_bib0013","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1159\/000506879","article-title":"The Hamilton rating scales for depression: a critical review of clinimetric properties of different versions","volume":"89","author":"Carrozzino","year":"2020","journal-title":"Psychother. Psychosom."},{"issue":"8","key":"10.1016\/j.inffus.2026.104374_bib0014","doi-asserted-by":"crossref","first-page":"1368","DOI":"10.1017\/S0033291719001314","article-title":"Equivalency of the diagnostic accuracy of the PHQ-8 and PHQ-9: a systematic review and individual participant data meta-analysis","volume":"50","author":"Wu","year":"2020","journal-title":"Psychol. Med."},{"issue":"3","key":"10.1016\/j.inffus.2026.104374_bib0015","doi-asserted-by":"crossref","first-page":"542","DOI":"10.1109\/TAFFC.2018.2828819","article-title":"Visually interpretable representation learning for depression recognition from facial images","volume":"11","author":"Zhou","year":"2018","journal-title":"IEEE Trans. Affect. Comput."},{"issue":"1","key":"10.1016\/j.inffus.2026.104374_bib0016","doi-asserted-by":"crossref","first-page":"64","DOI":"10.1109\/TCSS.2024.3405949","article-title":"Multimodal depression detection based on self-attention network with facial expression and pupil","volume":"12","author":"Liu","year":"2024","journal-title":"IEEE Trans. Comput. Social Syst."},{"issue":"3","key":"10.1016\/j.inffus.2026.104374_bib0017","doi-asserted-by":"crossref","first-page":"1855","DOI":"10.1109\/TAFFC.2025.3543226","article-title":"Automatic depression recognition with an ensemble of multimodal spatio-temporal routing features","volume":"16","author":"Wang","year":"2025","journal-title":"IEEE Trans. Affect. Comput."},{"key":"10.1016\/j.inffus.2026.104374_bib0018","doi-asserted-by":"crossref","unstructured":"K. Cho, B. Van Merri\u00ebnboer, C. Gulcehre, D. Bahdanau, F. Bougares, H. Schwenk, Y. Bengio, Learning phrase representations using RNN encoder-decoder for statistical machine translation, arXiv: 1406.1078(2014).","DOI":"10.3115\/v1\/D14-1179"},{"key":"10.1016\/j.inffus.2026.104374_bib0019","doi-asserted-by":"crossref","first-page":"2412","DOI":"10.1109\/TMM.2024.3521788","article-title":"Fer-former: multimodal transformer for facial expression recognition","volume":"27","author":"Li","year":"2025","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.inffus.2026.104374_bib0020","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2023.121410","article-title":"Spatial\u2013temporal attention network for depression recognition from facial videos","volume":"237","author":"Pan","year":"2024","journal-title":"Expert Syst. Appl."},{"issue":"3","key":"10.1016\/j.inffus.2026.104374_bib0021","doi-asserted-by":"crossref","first-page":"1078","DOI":"10.1109\/TAFFC.2023.3312263","article-title":"MTDAN: a lightweight multi-scale temporal difference attention networks for automated video depression detection","volume":"15","author":"Zhang","year":"2023","journal-title":"IEEE Trans. Affect. Comput."},{"key":"10.1016\/j.inffus.2026.104374_bib0022","series-title":"Chinese Conference on Pattern Recognition and Computer Vision (PRCV)","first-page":"172","article-title":"Long short-term perception network for dynamic facial expression recognition","author":"Lu","year":"2023"},{"issue":"8","key":"10.1016\/j.inffus.2026.104374_bib0023","first-page":"1","article-title":"Multi fine-grained fusion network for depression detection","volume":"20","author":"Zhou","year":"2024","journal-title":"ACM Trans. Multimed. Comput. Commun. Appl."},{"key":"10.1016\/j.inffus.2026.104374_bib0024","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2023.102017","article-title":"IIFDD: intra and inter-modal fusion for depression detection with multi-modal information from internet of medical things","volume":"102","author":"Chen","year":"2024","journal-title":"Inf. Fusion"},{"issue":"23","key":"10.1016\/j.inffus.2026.104374_bib0025","doi-asserted-by":"crossref","first-page":"9402","DOI":"10.3390\/s23239402","article-title":"Explainable depression detection based on facial expression using LSTM on attentional intermediate feature fusion with label smoothing","volume":"23","author":"Mahayossanunt","year":"2023","journal-title":"Sensors"},{"key":"10.1016\/j.inffus.2026.104374_bib0026","series-title":"Asian Conference on Pattern Recognition","first-page":"403","article-title":"Comparing facial expression recognition in humans and machines: using CAM, GradCAM, and extremal perturbation","author":"Park","year":"2021"},{"issue":"3","key":"10.1016\/j.inffus.2026.104374_bib0027","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1023\/A:1022627411411","article-title":"Support-vector networks","volume":"20","author":"Cortes","year":"1995","journal-title":"Mach. Learn."},{"issue":"1","key":"10.1016\/j.inffus.2026.104374_bib0028","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn."},{"key":"10.1016\/j.inffus.2026.104374_bib0029","series-title":"Advances in neural information processing systems","first-page":"3149","article-title":"LightGBM: a highly efficient gradient boosting decision tree","volume":"30","author":"Ke","year":"2017"},{"key":"10.1016\/j.inffus.2026.104374_bib0030","series-title":"Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","first-page":"785","article-title":"XGBoost: a scalable tree boosting system","author":"Chen","year":"2016"},{"key":"10.1016\/j.inffus.2026.104374_bib0031","unstructured":"A.V. Dorogush, V. Ershov, A. Gulin, CatBoost: gradient boosting with categorical features support, arXiv: 1810.11363(2018)."},{"key":"10.1016\/j.inffus.2026.104374_bib0032","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"156","article-title":"Temporal convolutional networks for action segmentation and detection","author":"Lea","year":"2017"},{"key":"10.1016\/j.inffus.2026.104374_bib0033","unstructured":"H. Wu, T. Hu, Y. Liu, H. Zhou, J. Wang, M. Long, TimesNet: temporal 2D-variation modeling for general time series analysis, arXiv: 2210.02186(2022)."},{"key":"10.1016\/j.inffus.2026.104374_bib0034","series-title":"Proceedings of the 32nd ACM International Conference on Multimedia","first-page":"311","article-title":"FacialPulse: an efficient RNN-based depression detection via temporal facial landmarks","author":"Wang","year":"2024"}],"container-title":["Information Fusion"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1566253526002538?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1566253526002538?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T11:40:30Z","timestamp":1779190830000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1566253526002538"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":34,"alternative-id":["S1566253526002538"],"URL":"https:\/\/doi.org\/10.1016\/j.inffus.2026.104374","relation":{},"ISSN":["1566-2535"],"issn-type":[{"value":"1566-2535","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Decoding depression: A hybrid GRU\u2013Mamba architecture with multi-dimensional interpretability framework for facial dynamics analysis","name":"articletitle","label":"Article Title"},{"value":"Information Fusion","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.inffus.2026.104374","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":"104374"}}