{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:15:05Z","timestamp":1776885305374,"version":"3.51.2"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100008530","name":"European Regional Development Fund (ERDF) as part of project ORAKEL","doi-asserted-by":"publisher","award":["ZS\/2023\/12\/182322"],"award-info":[{"award-number":["ZS\/2023\/12\/182322"]}],"id":[{"id":"10.13039\/501100008530","id-type":"DOI","asserted-by":"publisher"}]},{"name":"European Union and the state of Saxony-Anhalt"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3627778","type":"journal-article","created":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T17:13:01Z","timestamp":1761930781000},"page":"189494-189505","source":"Crossref","is-referenced-by-count":3,"title":["STCM-Mamba: Multimodal Spatio-Temporal Cross-Modal Mamba for Depression Detection"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-0368-6128","authenticated-orcid":false,"given":"Bowen","family":"Zhou","sequence":"first","affiliation":[{"name":"Neuro-Information Technology Group, Institute for Information Technology and Communications, Otto von Guericke University Magdeburg, Magdeburg, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5606-4033","authenticated-orcid":false,"given":"Marc-Andr\u00e9","family":"Fiedler","sequence":"additional","affiliation":[{"name":"Neuro-Information Technology Group, Institute for Information Technology and Communications, Otto von Guericke University Magdeburg, Magdeburg, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3632-2402","authenticated-orcid":false,"given":"Ayoub","family":"Al-Hamadi","sequence":"additional","affiliation":[{"name":"Neuro-Information Technology Group, Institute for Information Technology and Communications, Otto von Guericke University Magdeburg, Magdeburg, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Mental Disorders","year":"2022"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pmed.0030442"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1002\/wps.20771"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2724035"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2025.3530862"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3350071"},{"issue":"3","key":"ref7","doi-asserted-by":"crossref","first-page":"577","DOI":"10.1016\/j.dcan.2023.03.007","article-title":"Depressive semantic awareness from vlog facial and vocal streams via spatio-temporal transformer","volume":"10","author":"Tao","year":"2024","journal-title":"Digit. Commun. Netw."},{"key":"ref8","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2025.131160","article-title":"Disease and personality information enhanced depression detection based on the TransGCL framework","volume":"654","author":"Zhao","year":"2025","journal-title":"Neurocomputing"},{"key":"ref9","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023","journal-title":"arXiv:2312.00752"},{"key":"ref10","article-title":"Vision mamba: Efficient visual representation learning with bidirectional state space model","author":"Zhu","year":"2024","journal-title":"arXiv:2401.09417"},{"key":"ref11","article-title":"Efficiently modeling long sequences with structured state spaces","author":"Gu","year":"2021","journal-title":"arXiv:2111.00396"},{"key":"ref12","article-title":"VMamba: Visual state space model","author":"Liu","year":"2024","journal-title":"arXiv:2401.10166"},{"key":"ref13","article-title":"MambaMixer: Efficient selective state space models with dual token and channel selection","author":"Behrouz","year":"2024","journal-title":"arXiv:2403.19888"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/MIPR62202.2024.00059"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2025.3587918"},{"key":"ref16","article-title":"MambaSOD: Dual mamba-driven cross-modal fusion network for RGB-D salient object detection","author":"Zhan","year":"2024","journal-title":"arXiv:2410.15015"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3709026.3709063"},{"key":"ref18","article-title":"Mamba-enhanced text-audio-video alignment network for emotion recognition in conversations","author":"Li","year":"2024","journal-title":"arXiv:2409.05243"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3390\/life13091828"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s12652-023-04607-8"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI56570.2024.10635568"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2018.00032"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2019.8756584"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2020.3021755"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/2988257.2988267"},{"key":"ref26","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2021.116076","article-title":"Audio based depression detection using convolutional autoencoder","volume":"189","author":"Sardari","year":"2022","journal-title":"Expert Syst. Appl."},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TNSRE.2022.3224135"},{"issue":"11","key":"ref28","first-page":"12226","article-title":"D-vlog: Multimodal vlog dataset for depression detection","volume-title":"Proc. AAAI Conf. Artif. Intell.","volume":"36","author":"Yoon"},{"key":"ref29","article-title":"DepMamba: Progressive fusion mamba for multimodal depression detection","author":"Ye","year":"2024","journal-title":"arXiv:2409.15936"},{"key":"ref30","doi-asserted-by":"crossref","DOI":"10.1016\/j.dsp.2023.103986","article-title":"CAIINET: Neural network based on contextual attention and information interaction mechanism for depression detection","volume":"137","author":"Zhou","year":"2023","journal-title":"Digit. Signal Process."},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2025.103632"},{"key":"ref32","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2023.102161","article-title":"Transformer-based multimodal feature enhancement networks for multimodal depression detection integrating video, audio and remote photoplethysmograph signals","volume":"104","author":"Fan","year":"2024","journal-title":"Inf. Fusion"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2024.3418415"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3347320.3357696"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2025.3552835"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/BIBM62325.2024.10822358"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1002\/SERIES1345"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/5254.708428"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1023\/a:1010933404324"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/EMBC.2017.8037103"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1115"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2023.3282704"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00559"},{"key":"ref44","doi-asserted-by":"crossref","DOI":"10.1016\/j.artmed.2024.102949","article-title":"A systematic review of few-shot learning in medical imaging","volume":"156","author":"Pachetti","year":"2024","journal-title":"Artif. Intell. Med."},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2024.3496813"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11223210.pdf?arnumber=11223210","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T05:55:15Z","timestamp":1762840515000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11223210\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3627778","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}