{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T21:07:11Z","timestamp":1780088831878,"version":"3.54.0"},"reference-count":78,"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\/501100004775","name":"Gansu Provincial Natural Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004775","id-type":"DOI","asserted-by":"publisher"}]},{"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"}]},{"DOI":"10.13039\/501100012555","name":"Foundation for Innovation Groups of Basic Research in Gansu Province","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012555","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Biomedical Signal Processing and Control"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.bspc.2026.110569","type":"journal-article","created":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T12:18:27Z","timestamp":1778761107000},"page":"110569","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PB","title":["NSANet: Non-Stationary Multi-Scale Attention Network with structured multi-task supervision for video depression detection"],"prefix":"10.1016","volume":"123","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-6806-5563","authenticated-orcid":false,"given":"Wenxu","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qianqian","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiangli","family":"Dong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hui","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-6901-7058","authenticated-orcid":false,"given":"Yipeng","family":"Yin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoe","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lang","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.bspc.2026.110569_b1","series-title":"Depression and other common mental disorders: global health estimates","author":"World Health Organization","year":"2017"},{"key":"10.1016\/j.bspc.2026.110569_b2","doi-asserted-by":"crossref","first-page":"3095","DOI":"10.1001\/jama.289.23.3095","article-title":"The epidemiology of major depressive disorder: results from the national comorbidity survey replication (NCS-R)","volume":"289","author":"Kessler","year":"2003","journal-title":"JAMA"},{"key":"10.1016\/j.bspc.2026.110569_b3","first-page":"860","article-title":"Epidemiology of the association between somatoform disorders and anxiety and depressive disorders: an update","volume":"69","author":"Lieb","year":"2007","journal-title":"Biopsychosoc. Sci. Med."},{"key":"10.1016\/j.bspc.2026.110569_b4","first-page":"591","article-title":"Diagnostic and statistical manual of mental disorders","volume":"21","author":"Edition","year":"2013","journal-title":"Am. Psychiatr. Assoc."},{"key":"10.1016\/j.bspc.2026.110569_b5","first-page":"210","article-title":"Beck depression inventory-II","volume":"1","author":"Inventory-Ii","year":"2010","journal-title":"Corsini Encycl. Psychol."},{"key":"10.1016\/j.bspc.2026.110569_b6","series-title":"Facial Action Coding System: Investigator\u2019s Guide","author":"Ekman","year":"1978"},{"key":"10.1016\/j.bspc.2026.110569_b7","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1016\/S0165-1781(00)00168-2","article-title":"Reduced facial expression and social context in major depression: discrepancies between facial muscle activity and self-reported emotion","volume":"95","author":"Gehricke","year":"2000","journal-title":"Psychiatry Res."},{"key":"10.1016\/j.bspc.2026.110569_b8","doi-asserted-by":"crossref","first-page":"641","DOI":"10.1016\/j.imavis.2013.12.007","article-title":"Nonverbal social withdrawal in depression: Evidence from manual and automatic analyses","volume":"32","author":"Girard","year":"2014","journal-title":"Image Vis. Comput."},{"key":"10.1016\/j.bspc.2026.110569_b9","doi-asserted-by":"crossref","DOI":"10.7554\/eLife.79581","article-title":"Quantifying dynamic facial expressions under naturalistic conditions","volume":"11","author":"Jeganathan","year":"2022","journal-title":"ELife"},{"key":"10.1016\/j.bspc.2026.110569_b10","doi-asserted-by":"crossref","unstructured":"E.A. Stepanov, S. Lathuiliere, S.A. Chowdhury, A. Ghosh, R.-L. Vieriu, N. Sebe, G. Riccardi, Depression severity estimation from multiple modalities, in: Proc. IEEE Healthcom Conf., 2018, pp. 1\u20136.","DOI":"10.1109\/HealthCom.2018.8531119"},{"key":"10.1016\/j.bspc.2026.110569_b11","doi-asserted-by":"crossref","unstructured":"M. Nasir, A. Jati, P.G. Shivakumar, S. Nallan Chakravarthula, P. Georgiou, Multimodal and multiresolution depression detection from speech and facial landmark features, in: Proc. 6th Int. Workshop Audio\/Visual Emotion Challenge, 2016, pp. 43\u201350.","DOI":"10.1145\/2988257.2988261"},{"key":"10.1016\/j.bspc.2026.110569_b12","doi-asserted-by":"crossref","unstructured":"T.R. Almaev, M.F. Valstar, Local gabor binary patterns from three orthogonal planes for automatic facial expression recognition, in: Proc. Humaine Assoc. Conf. Affect. Comput. Intell. Interact., 2013, pp. 356\u2013361.","DOI":"10.1109\/ACII.2013.65"},{"key":"10.1016\/j.bspc.2026.110569_b13","doi-asserted-by":"crossref","first-page":"64","DOI":"10.1186\/s13640-017-0212-3","article-title":"Quantitative comparison of motion history image variants for video-based depression assessment","volume":"2017","author":"Pampouchidou","year":"2017","journal-title":"EURASIP J. Image Video Process."},{"key":"10.1016\/j.bspc.2026.110569_b14","doi-asserted-by":"crossref","first-page":"1432","DOI":"10.1109\/TIFS.2015.2414392","article-title":"Automated depression diagnosis based on facial dynamic analysis and sparse coding","volume":"10","author":"Wen","year":"2015","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"10.1016\/j.bspc.2026.110569_b15","doi-asserted-by":"crossref","unstructured":"M. Gahalawat, R. Fernandez Rojas, T. Guha, R. Subramanian, R. Goecke, Explainable depression detection via head motion patterns, in: Proc. 25th Int. Conf. Multimodal Interact., 2023, pp. 261\u2013270.","DOI":"10.1145\/3577190.3614130"},{"key":"10.1016\/j.bspc.2026.110569_b16","doi-asserted-by":"crossref","unstructured":"L. He, D. Jiang, H. Sahli, Multimodal depression recognition with dynamic visual and audio cues, in: Proc. Int. Conf. Affect. Comput. Intell. Interact., ACII, 2015, pp. 260\u2013266.","DOI":"10.1109\/ACII.2015.7344581"},{"key":"10.1016\/j.bspc.2026.110569_b17","doi-asserted-by":"crossref","first-page":"624","DOI":"10.1109\/TAFFC.2024.3453443","article-title":"From static to dynamic: Adapting landmark-aware image models for facial expression recognition in videos","volume":"16","author":"Chen","year":"2025","journal-title":"IEEE Trans. Affect. Comput."},{"key":"10.1016\/j.bspc.2026.110569_b18","doi-asserted-by":"crossref","first-page":"9230","DOI":"10.3390\/app13169230","article-title":"A depression recognition method based on the alteration of video temporal angle features","volume":"13","author":"Ding","year":"2023","journal-title":"Appl. Sci."},{"key":"10.1016\/j.bspc.2026.110569_b19","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1016\/j.inffus.2021.10.012","article-title":"Deep learning for depression recognition with audiovisual cues: A review","volume":"80","author":"He","year":"2022","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.bspc.2026.110569_b20","doi-asserted-by":"crossref","unstructured":"Q. Cao, J. Gao, Z. Lv, M. Li, Assessment of depression level based on multi-scale 3D convolution and expression videos, in: Proc. Third Int. Conf. Comput. Vis. Pattern Anal., 2023, pp. 181\u2013185.","DOI":"10.1117\/12.2684233"},{"key":"10.1016\/j.bspc.2026.110569_b21","doi-asserted-by":"crossref","DOI":"10.1016\/j.compbiomed.2023.106782","article-title":"A gated temporal-separable attention network for EEG-based depression recognition","volume":"157","author":"Yang","year":"2023","journal-title":"Comput. Biol. Med."},{"key":"10.1016\/j.bspc.2026.110569_b22","article-title":"Sentence-level multi-modal feature learning for depression recognition","volume":"16","author":"Zhang","year":"2025","journal-title":"Front. Psychiatry"},{"key":"10.1016\/j.bspc.2026.110569_b23","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."},{"key":"10.1016\/j.bspc.2026.110569_b24","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.129106","article-title":"Facial action units guided graph representation learning for multimodal depression detection","volume":"619","author":"Fu","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.bspc.2026.110569_b25","doi-asserted-by":"crossref","first-page":"e936409","DOI":"10.12659\/MSM.936409","article-title":"Automatic identification of depression using facial images with deep convolutional neural network","volume":"28","author":"Kong","year":"2022","journal-title":"Med. Sci. Monit."},{"key":"10.1016\/j.bspc.2026.110569_b26","doi-asserted-by":"crossref","unstructured":"D. Gimeno-G\u00f3mez, A.-M. Bucur, A. Cosma, C.-D. Mart\u00ednez-Hinarejos, P. Rosso, Reading between the frames: Multi-modal depression detection in videos from non-verbal cues, in: Proc. Eur. Conf. Inf. Retr., 2024, pp. 191\u2013209.","DOI":"10.1007\/978-3-031-56027-9_12"},{"key":"10.1016\/j.bspc.2026.110569_b27","doi-asserted-by":"crossref","first-page":"2063","DOI":"10.1007\/s13042-023-02016-z","article-title":"Transformer embedded spectral-based graph network for facial expression recognition","volume":"15","author":"Jin","year":"2024","journal-title":"Int. J. Mach. Learn. Cybern."},{"key":"10.1016\/j.bspc.2026.110569_b28","doi-asserted-by":"crossref","first-page":"3815","DOI":"10.1002\/int.22704","article-title":"DepNet: An automated industrial intelligent system using deep learning for video-based depression analysis","volume":"37","author":"He","year":"2022","journal-title":"Int. J. Intell. Syst."},{"key":"10.1016\/j.bspc.2026.110569_b29","doi-asserted-by":"crossref","first-page":"10140","DOI":"10.1002\/int.22426","article-title":"Intelligent system for depression scale estimation with facial expressions and case study in industrial intelligence","volume":"37","author":"He","year":"2022","journal-title":"Int. J. Intell. Syst."},{"key":"10.1016\/j.bspc.2026.110569_b30","article-title":"A facial depression recognition method based on hybrid multi-head cross attention network","volume":"17","author":"Li","year":"2023","journal-title":"Front. Neurosci."},{"key":"10.1016\/j.bspc.2026.110569_b31","doi-asserted-by":"crossref","first-page":"1313","DOI":"10.3390\/life14101313","article-title":"Tcedn: a lightweight time-context enhanced depression detection network","volume":"14","author":"Yan","year":"2024","journal-title":"Life"},{"key":"10.1016\/j.bspc.2026.110569_b32","doi-asserted-by":"crossref","DOI":"10.1016\/j.bspc.2025.108806","article-title":"Attention-driven contextual feature fusion network for facial videos-based depression recognition","volume":"113","author":"Xiao","year":"2026","journal-title":"Biomed. Signal Process. Control."},{"key":"10.1016\/j.bspc.2026.110569_b33","doi-asserted-by":"crossref","unstructured":"S. Li, Y. Xiao, S. Hu, A depression detection method based on multi-modal feature fusion using cross-attention, in: Proc. 8th Int. Conf. Adv. Algorithms Control Eng., ICAACE, 2025, pp. 1825\u20131831.","DOI":"10.1109\/ICAACE65325.2025.11019096"},{"key":"10.1016\/j.bspc.2026.110569_b34","article-title":"Audio-visual feature disentanglement and fusion network for automatic depression severity prediction","author":"Li","year":"2025","journal-title":"IEEE Trans. Affect. Comput."},{"key":"10.1016\/j.bspc.2026.110569_b35","doi-asserted-by":"crossref","DOI":"10.1016\/j.bspc.2024.106767","article-title":"LSCAformer: Long and short-term cross-attention-aware transformer for depression recognition from video sequences","volume":"98","author":"He","year":"2024","journal-title":"Biomed. Signal Process. Control."},{"key":"10.1016\/j.bspc.2026.110569_b36","doi-asserted-by":"crossref","DOI":"10.1016\/j.bspc.2024.106490","article-title":"Depressformer: Leveraging video swin transformer and fine-grained local features for depression scale estimation","volume":"96","author":"He","year":"2024","journal-title":"Biomed. Signal Process. Control."},{"key":"10.1016\/j.bspc.2026.110569_b37","doi-asserted-by":"crossref","first-page":"195","DOI":"10.1007\/s10489-024-05908-x","article-title":"LMTformer: facial depression recognition with lightweight multi-scale transformer from videos: L. He et al.","volume":"55","author":"He","year":"2025","journal-title":"Appl. Intell."},{"key":"10.1016\/j.bspc.2026.110569_b38","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":"10.1016\/j.bspc.2026.110569_b39","doi-asserted-by":"crossref","first-page":"652","DOI":"10.3934\/mbe.2025024","article-title":"Multimodal depression detection based on an attention graph convolution and transformer","volume":"22","author":"Jia","year":"2025","journal-title":"Math. Biosci. Eng."},{"key":"10.1016\/j.bspc.2026.110569_b40","doi-asserted-by":"crossref","first-page":"120","DOI":"10.1016\/j.neunet.2022.05.025","article-title":"Reducing noisy annotations for depression estimation from facial images","volume":"153","author":"He","year":"2022","journal-title":"Neural Netw."},{"key":"10.1016\/j.bspc.2026.110569_b41","doi-asserted-by":"crossref","DOI":"10.1155\/2024\/1564574","article-title":"FPT-former: A flexible parallel transformer of recognizing depression by using audiovisual expert-knowledge-based multimodal measures","volume":"2024","author":"Li","year":"2024","journal-title":"Int. J. Intell. Syst."},{"key":"10.1016\/j.bspc.2026.110569_b42","doi-asserted-by":"crossref","unstructured":"M.R. Haque, M.M. Islam, S.T.U. Raju, H. Altaheri, L. Nassar, F. Karray, Mmfformer: Multimodal fusion transformer network for depression detection, in: Proc. IEEE Int. Conf. Syst. Man Cybern., SMC, 2025, pp. 5912\u20135919.","DOI":"10.1109\/SMC58881.2025.11342694"},{"key":"10.1016\/j.bspc.2026.110569_b43","article-title":"FedDAAM: Federated domain adversarial learning with attention mechanism for privacy preserving multimodal depression assessment","author":"He","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.bspc.2026.110569_b44","article-title":"LMVD: A large-scale multimodal vlog dataset for depression detection in the wild","author":"He","year":"2025","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.bspc.2026.110569_b45","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2026.104213","article-title":"FDA-CAPMA: Federated domain adaptation with co-activation pattern and multimodal mamba for fMRI depression detection","author":"He","year":"2026","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.bspc.2026.110569_b46","doi-asserted-by":"crossref","first-page":"4819","DOI":"10.3390\/s25154819","article-title":"MB-MSTFNet: A multi-band spatio-temporal attention network for EEG sensor-based emotion recognition","volume":"25","author":"Fang","year":"2025","journal-title":"Sensors"},{"key":"10.1016\/j.bspc.2026.110569_b47","doi-asserted-by":"crossref","first-page":"1067","DOI":"10.1109\/TAFFC.2023.3318321","article-title":"AMDET: Attention based multiple dimensions EEG transformer for emotion recognition","volume":"15","author":"Xu","year":"2023","journal-title":"IEEE Trans. Affect. Comput."},{"key":"10.1016\/j.bspc.2026.110569_b48","doi-asserted-by":"crossref","first-page":"550","DOI":"10.3390\/info13110550","article-title":"Multimodal EEG emotion recognition based on the attention recurrent graph convolutional network","volume":"13","author":"Chen","year":"2022","journal-title":"Information"},{"key":"10.1016\/j.bspc.2026.110569_b49","doi-asserted-by":"crossref","DOI":"10.3389\/fpsyt.2025.1584474","article-title":"Attention-based multi-scale convolution and conformer for EEG-based depression detection","volume":"16","author":"Yan","year":"2025","journal-title":"Front. Psychiatry"},{"key":"10.1016\/j.bspc.2026.110569_b50","doi-asserted-by":"crossref","first-page":"31319","DOI":"10.1038\/s41598-024-82705-z","article-title":"EEG-based emotion recognition using multi-scale dynamic CNN and gated transformer","volume":"14","author":"Cheng","year":"2024","journal-title":"Sci. Rep."},{"key":"10.1016\/j.bspc.2026.110569_b51","series-title":"MF-GCN: A multi-frequency graph convolutional network for tri-modal depression detection using eye-tracking, facial, and acoustic features","author":"Rahman","year":"2025"},{"key":"10.1016\/j.bspc.2026.110569_b52","doi-asserted-by":"crossref","first-page":"2029","DOI":"10.3390\/s25072029","article-title":"MSDSANet: Multimodal emotion recognition based on multi-stream network and dual-scale attention network feature representation","volume":"25","author":"Sun","year":"2025","journal-title":"Sensors"},{"key":"10.1016\/j.bspc.2026.110569_b53","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.107060","article-title":"Emotion recognition using multi-scale EEG features through graph convolutional attention network","volume":"184","author":"Cao","year":"2025","journal-title":"Neural Netw."},{"key":"10.1016\/j.bspc.2026.110569_b54","article-title":"CMTNet: A collaborative mamba-transformer network with spatial-temporal cross-fusion for speech emotion recognition","author":"Dong","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.bspc.2026.110569_b55","article-title":"TTFNet: Temporal-frequency features fusion network for speech based automatic depression recognition and assessment","author":"Chen","year":"2025","journal-title":"IEEE J. Biomed. Health Inf."},{"key":"10.1016\/j.bspc.2026.110569_b56","doi-asserted-by":"crossref","unstructured":"M. Valstar, B. Schuller, K. Smith, F. Eyben, B. Jiang, S. Bilakhia, S. Schnieder, R. Cowie, M. Pantic, Avec 2013: the continuous audio\/visual emotion and depression recognition challenge, in: Proc. 3rd ACM Int. Workshop Audio\/Visual Emotion Challenge, 2013, pp. 3\u201310.","DOI":"10.1145\/2512530.2512533"},{"key":"10.1016\/j.bspc.2026.110569_b57","doi-asserted-by":"crossref","unstructured":"M. Valstar, B. Schuller, K. Smith, T. Almaev, F. Eyben, J. Krajewski, R. Cowie, M. Pantic, Avec 2014: 3d dimensional affect and depression recognition challenge, in: Proc. 4th Int. Workshop Audio\/Visual Emotion Challenge, 2014, pp. 3\u201310.","DOI":"10.1145\/2661806.2661807"},{"key":"10.1016\/j.bspc.2026.110569_b58","doi-asserted-by":"crossref","unstructured":"F. Ringeval, B. Schuller, M. Valstar, N. Cummins, R. Cowie, L. Tavabi, M. Schmitt, S. Alisamir, S. Amiriparian, E.-M. Messner, et al., AVEC 2019 workshop and challenge: state-of-mind, detecting depression with AI, and cross-cultural affect recognition, in: Proc. 9th Int. Audio\/Visual Emotion Challenge Workshop, 2019, pp. 3\u201312.","DOI":"10.1145\/3347320.3357688"},{"key":"10.1016\/j.bspc.2026.110569_b59","doi-asserted-by":"crossref","unstructured":"Z. Chen, J. Deng, J. Zhou, J. Wu, T. Qian, M. Huang, Depression detection in clinical interviews with LLM-empowered structural element graph, in: Proc. NAACL-HLT, 2024, pp. 8181\u20138194.","DOI":"10.18653\/v1\/2024.naacl-long.452"},{"key":"10.1016\/j.bspc.2026.110569_b60","article-title":"FC-AEN: Fully convolutional adaptive ensemble network for automatic depression detection","author":"Wang","year":"2025","journal-title":"IEEE Trans. Comput. Soc. Syst."},{"key":"10.1016\/j.bspc.2026.110569_b61","doi-asserted-by":"crossref","unstructured":"H. Sun, H. Wang, J. Liu, Y.-W. Chen, L. Lin, CubeMLP: An MLP-based model for multimodal sentiment analysis and depression estimation, in: Proc. ACM Int. Conf. Multimedia, 2022, pp. 3722\u20133729.","DOI":"10.1145\/3503161.3548025"},{"key":"10.1016\/j.bspc.2026.110569_b62","doi-asserted-by":"crossref","first-page":"4520","DOI":"10.3390\/s25144520","article-title":"DepressionMIGNN: A multiple-instance learning-based depression detection model with graph neural networks","volume":"25","author":"Zhao","year":"2025","journal-title":"Sensors"},{"key":"10.1016\/j.bspc.2026.110569_b63","doi-asserted-by":"crossref","first-page":"161","DOI":"10.1109\/TAFFC.2024.3415770","article-title":"Two-stage temporal modelling framework for video-based depression recognition using graph representation","volume":"16","author":"Xu","year":"2024","journal-title":"IEEE Trans. Affect. Comput."},{"key":"10.1016\/j.bspc.2026.110569_b64","doi-asserted-by":"crossref","unstructured":"Z. Lin, Y. Wang, Y. Zhou, F. Du, Y. Yang, Ste-mamba: Automated multimodal depression detection through emotional analysis and spatio-temporal information ensemble, in: Proc. IEEE Int. Conf. Acoust. Speech Signal Process., ICASSP, 2025, pp. 1\u20135.","DOI":"10.1109\/ICASSP49660.2025.10889512"},{"key":"10.1016\/j.bspc.2026.110569_b65","article-title":"Simma: multimodal automatic depression detection via spatiotemporal ensemble and cross-modal alignment","author":"Wang","year":"2025","journal-title":"IEEE Trans. Comput. Soc. Syst."},{"key":"10.1016\/j.bspc.2026.110569_b66","doi-asserted-by":"crossref","DOI":"10.1109\/TAFFC.2025.3585599","article-title":"MLM-EOE: Automatic depression detection via sentimental annotation and multi-expert ensemble","author":"Lin","year":"2025","journal-title":"IEEE Trans. Affect. Comput."},{"key":"10.1016\/j.bspc.2026.110569_b67","doi-asserted-by":"crossref","DOI":"10.3389\/fpsyt.2025.1508772","article-title":"Diagnosis of depression based on facial multimodal data","volume":"16","author":"Jin","year":"2025","journal-title":"Front. Psychiatry"},{"key":"10.1016\/j.bspc.2026.110569_b68","doi-asserted-by":"crossref","DOI":"10.3389\/fpsyt.2024.1466507","article-title":"DepITCM: an audio-visual method for detecting depression","volume":"15","author":"Zhang","year":"2025","journal-title":"Front. Psychiatry"},{"key":"10.1016\/j.bspc.2026.110569_b69","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."},{"key":"10.1016\/j.bspc.2026.110569_b70","doi-asserted-by":"crossref","first-page":"165","DOI":"10.1016\/j.neucom.2020.10.015","article-title":"Automatic depression recognition using CNN with attention mechanism from videos","volume":"422","author":"He","year":"2021","journal-title":"Neurocomputing"},{"key":"10.1016\/j.bspc.2026.110569_b71","doi-asserted-by":"crossref","first-page":"1476","DOI":"10.1109\/TMM.2018.2877129","article-title":"Automatic depression analysis using dynamic facial appearance descriptor and dirichlet process fisher encoding","volume":"21","author":"He","year":"2018","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.bspc.2026.110569_b72","doi-asserted-by":"crossref","DOI":"10.1016\/j.compbiomed.2023.106589","article-title":"PRA-net: Part-and-relation attention network for depression recognition from facial expression","volume":"157","author":"Liu","year":"2023","journal-title":"Comput. Biol. Med."},{"key":"10.1016\/j.bspc.2026.110569_b73","doi-asserted-by":"crossref","unstructured":"W.C. De Melo, E. Granger, M.B. Lopez, Encoding temporal information for automatic depression recognition from facial analysis, in: Proc. IEEE Int. Conf. Acoust. Speech Signal Process., ICASSP, 2020, pp. 1080\u20131084.","DOI":"10.1109\/ICASSP40776.2020.9054375"},{"key":"10.1016\/j.bspc.2026.110569_b74","doi-asserted-by":"crossref","unstructured":"J. Gao, Y. Wei, Depression level assessment based on 3D CNN and facial expression videos, in: Proc. Int. Conf. Comput. Vis. Robot. Autom. Eng., 2024, pp. 9\u201314.","DOI":"10.56028\/aetr.10.1.382.2024"},{"key":"10.1016\/j.bspc.2026.110569_b75","doi-asserted-by":"crossref","first-page":"2557","DOI":"10.1109\/TAFFC.2021.3139651","article-title":"LQGDNet: A local quaternion and global deep network for facial depression recognition","volume":"14","author":"Shang","year":"2021","journal-title":"IEEE Trans. Affect. Comput."},{"key":"10.1016\/j.bspc.2026.110569_b76","doi-asserted-by":"crossref","first-page":"578","DOI":"10.1109\/TAFFC.2017.2650899","article-title":"Automated depression diagnosis based on deep networks to encode facial appearance and dynamics","volume":"9","author":"Zhu","year":"2017","journal-title":"IEEE Trans. Affect. Comput."},{"key":"10.1016\/j.bspc.2026.110569_b77","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.bspc.2026.110569_b78","doi-asserted-by":"crossref","unstructured":"Y. Pan, J. Jiang, K. Jiang, Z. Wu, K. Yu, X. Liu, Opticaldr: A deep optical imaging model for privacy-protective depression recognition, in: Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit., 2024, pp. 1303\u20131312.","DOI":"10.1109\/CVPR52733.2024.00130"}],"container-title":["Biomedical Signal Processing and Control"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1746809426011237?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1746809426011237?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T20:10:28Z","timestamp":1780085428000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1746809426011237"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":78,"alternative-id":["S1746809426011237"],"URL":"https:\/\/doi.org\/10.1016\/j.bspc.2026.110569","relation":{},"ISSN":["1746-8094"],"issn-type":[{"value":"1746-8094","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"NSANet: Non-Stationary Multi-Scale Attention Network with structured multi-task supervision for video depression detection","name":"articletitle","label":"Article Title"},{"value":"Biomedical Signal Processing and Control","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.bspc.2026.110569","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":"110569"}}