{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T21:26:07Z","timestamp":1765229167344,"version":"3.46.0"},"reference-count":58,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100004862","name":"Zhejiang University of Science and Technology","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004862","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":[[2025,11]]},"DOI":"10.1016\/j.knosys.2025.114793","type":"journal-article","created":{"date-parts":[[2025,10,29]],"date-time":"2025-10-29T07:53:39Z","timestamp":1761724419000},"page":"114793","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PC","title":["FractalMM architecture: Fractal feature fusion for privacy-preserved multimodal depression recognition"],"prefix":"10.1016","volume":"330","author":[{"given":"Junyi","family":"Gu","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2919-5222","authenticated-orcid":false,"given":"Xiang","family":"Guo","sequence":"additional","affiliation":[]},{"given":"Yang","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Linyu","family":"Dong","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"issue":"4","key":"10.1016\/j.knosys.2025.114793_bib0001","doi-asserted-by":"crossref","first-page":"328","DOI":"10.1037\/ccp0000936","article-title":"Future directions in depression prevention","volume":"93","author":"Batterham","year":"2025","journal-title":"J. Consult. Clin. Psychol."},{"key":"10.1016\/j.knosys.2025.114793_bib0002","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2025.129605","article-title":"Deep learning-based depression recognition through facial expression: a systematic review","author":"Cao","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.knosys.2025.114793_bib0003","series-title":"Proceedings of the 7th Annual Workshop on Audio\/Visual Emotion Challenge","first-page":"3","article-title":"AVEC 2017-real-life depression, and affect recognition workshop and challenge","author":"Ringeval","year":"2017"},{"key":"10.1016\/j.knosys.2025.114793_bib0004","first-page":"89","article-title":"Multi-feature deep supervised voiceprint adversarial network for depression recognition from speech","author":"Pan","year":"2024","journal-title":"Biomed. Signal. Process. Control"},{"key":"10.1016\/j.knosys.2025.114793_bib0005","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.knosys.2025.114793_bib0006","first-page":"117","article-title":"Text-guided multimodal depression detection via cross-modal feature reconstruction and decomposition","author":"Chen","year":"2025","journal-title":"Inf. Fusion."},{"key":"10.1016\/j.knosys.2025.114793_bib0007","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1016\/j.inffus.2020.01.008","article-title":"Feature-level fusion approaches based on multimodal EEG data for depression recognition","volume":"59","author":"Cai","year":"2020","journal-title":"Inf. Fusion."},{"issue":"2","key":"10.1016\/j.knosys.2025.114793_bib0008","doi-asserted-by":"crossref","DOI":"10.1111\/psyp.14481","article-title":"Heart rate variability: evaluating a potential biomarker of anxiety disorders","volume":"61","author":"Tomasi","year":"2024","journal-title":"Psychophysiology"},{"key":"10.1016\/j.knosys.2025.114793_bib0009","first-page":"121","article-title":"Poisoning attacks resilient privacy-preserving federated learning scheme based on lightweight homomorphic encryption","author":"Zhang","year":"2025","journal-title":"Inf. Fusion."},{"key":"10.1016\/j.knosys.2025.114793_bib0010","first-page":"120","article-title":"Privacy-preserving heterogeneous multi-modal sensor data fusion via federated learning for smart healthcare","author":"Wang","year":"2025","journal-title":"Inf. Fusion."},{"issue":"1","key":"10.1016\/j.knosys.2025.114793_bib0011","first-page":"49","article-title":"A comprehensive survey on federated learning applications in computational mental healthcare","volume":"142","author":"Vajrobol","year":"2025","journal-title":"Comput. Model. Eng. Sci."},{"key":"10.1016\/j.knosys.2025.114793_bib0012","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"1303","article-title":"OpticalDR: a deep optical imaging model for privacy-protective depression recognition","author":"Pan","year":"2024"},{"key":"10.1016\/j.knosys.2025.114793_bib0013","first-page":"121","article-title":"GenRAN: GenFusion-guided reversible anonymization network for face privacy preserving","author":"Wang","year":"2025","journal-title":"Inf. Fusion."},{"issue":"4","key":"10.1016\/j.knosys.2025.114793_bib0014","doi-asserted-by":"crossref","first-page":"2126","DOI":"10.1109\/TPAMI.2020.3026709","article-title":"Privacy-preserving deep action recognition: an adversarial learning framework and a new dataset","volume":"44","author":"Wu","year":"2022","journal-title":"IEEe Trans. Pattern. Anal. Mach. Intell."},{"key":"10.1016\/j.knosys.2025.114793_bib0015","series-title":"2023 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","first-page":"1","article-title":"Representation learning for audio privacy preservation using source separation and robust adversarial learning","author":"Luong","year":"2023"},{"key":"10.1016\/j.knosys.2025.114793_bib0016","first-page":"105","article-title":"Fairness and privacy preserving in federated learning: a survey","author":"Rafi","year":"2024","journal-title":"Inf. Fusion."},{"key":"10.1016\/j.knosys.2025.114793_bib0017","doi-asserted-by":"crossref","first-page":"2864","DOI":"10.1109\/TASLP.2021.3108063","article-title":"Privacy-preserving audio classification using variational information feature extraction","volume":"29","author":"Nelus","year":"2021","journal-title":"IEEE\/ACM. Trans. Audio Speech. Lang. Process."},{"issue":"3","key":"10.1016\/j.knosys.2025.114793_bib0018","doi-asserted-by":"crossref","first-page":"1749","DOI":"10.1109\/JIOT.2021.3089080","article-title":"Audio-visual autoencoding for privacy-preserving video streaming","volume":"9","author":"Xu","year":"2022","journal-title":"IEEe Internet. Things. J."},{"key":"10.1016\/j.knosys.2025.114793_bib0019","doi-asserted-by":"crossref","first-page":"282","DOI":"10.1016\/j.jad.2024.07.140","article-title":"Mutual eye gaze and vocal pitch in relation to social anxiety and depression: a virtual interaction task","volume":"363","author":"Howell","year":"2024","journal-title":"J. Affect. Disord."},{"key":"10.1016\/j.knosys.2025.114793_bib0020","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1016\/j.genhosppsych.2023.04.010","article-title":"Abnormal eye movement features in patients with depression: preliminary findings based on eye tracking technology","volume":"84","author":"Gao","year":"2023","journal-title":"Gen. Hosp. Psychiatry"},{"issue":"7","key":"10.1016\/j.knosys.2025.114793_bib0021","doi-asserted-by":"crossref","first-page":"580","DOI":"10.1016\/j.biopsych.2012.03.015","article-title":"Vocal acoustic biomarkers of depression severity and treatment response","volume":"72","author":"Mundt","year":"2012","journal-title":"Biol. Psychiatry"},{"issue":"4","key":"10.1016\/j.knosys.2025.114793_bib0022","doi-asserted-by":"crossref","first-page":"478","DOI":"10.1109\/TAFFC.2016.2634527","article-title":"Multimodal depression detection: fusion analysis of paralinguistic, head pose and eye gaze behaviors","volume":"9","author":"Alghowinem","year":"2018","journal-title":"IEEe Trans. Affect. Comput."},{"key":"10.1016\/j.knosys.2025.114793_bib0023","first-page":"1","article-title":"Facial depression estimation via multi-cue contrastive learning","author":"Wang","year":"2025","journal-title":"IEEe Trans. Circuits. Syst. Video Technol."},{"issue":"3","key":"10.1016\/j.knosys.2025.114793_bib0024","doi-asserted-by":"crossref","first-page":"559","DOI":"10.1007\/s00406-023-01608-8","article-title":"Free-viewing gaze patterns reveal a mood-congruency bias in MDD during an affective fMRI\/eye-tracking task","volume":"274","author":"Sun","year":"2024","journal-title":"Eur. Arch. Psychiatry Clin. Neurosci."},{"key":"10.1016\/j.knosys.2025.114793_bib0025","first-page":"86","article-title":"Enhancing accuracy and privacy in speech-based depression detection through speaker disentanglement","author":"Ravi","year":"2024","journal-title":"Comput. Speech. Lang."},{"key":"10.1016\/j.knosys.2025.114793_bib0026","first-page":"1","article-title":"Speech-based depression assessment: a comprehensive survey","author":"Leal","year":"2024","journal-title":"IEEe Trans. Affect. Comput."},{"key":"10.1016\/j.knosys.2025.114793_bib0027","first-page":"90","article-title":"A deep learning model for depression detection based on MFCC and CNN generated spectrogram features","author":"Das","year":"2024","journal-title":"Biomed. Signal. Process. Control"},{"key":"10.1016\/j.knosys.2025.114793_bib0028","first-page":"1","article-title":"Depression scale dictionary decomposition framework for multimodal automatic depression level prediction","author":"Niu","year":"2025","journal-title":"IEEe Trans. Circuits. Syst. Video Technol."},{"key":"10.1016\/j.knosys.2025.114793_bib0029","doi-asserted-by":"crossref","first-page":"748","DOI":"10.1109\/TASLPRO.2025.3533370","article-title":"Weakly-supervised depression detection in speech through self-learning based label correction","volume":"33","author":"Sun","year":"2025","journal-title":"IEEe Trans. Audio Speech. Lang. Process."},{"key":"10.1016\/j.knosys.2025.114793_bib0030","doi-asserted-by":"crossref","first-page":"775","DOI":"10.1109\/TASLP.2023.3235194","article-title":"SpeechFormer++: a hierarchical efficient framework for paralinguistic speech processing","volume":"31","author":"Chen","year":"2023","journal-title":"IEEE\/ACM. Trans. Audio Speech. Lang. Process."},{"key":"10.1016\/j.knosys.2025.114793_bib0031","first-page":"88","article-title":"A novel study for depression detecting using audio signals based on graph neural network","author":"Sun","year":"2024","journal-title":"Biomed. Signal. Process. Control"},{"issue":"1","key":"10.1016\/j.knosys.2025.114793_bib0032","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":"2025","journal-title":"IEEe Trans. Affect. Comput."},{"key":"10.1016\/j.knosys.2025.114793_bib0033","series-title":"IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"131","article-title":"CNN architectures for large-scale audio classification","author":"Hershey","year":"2017"},{"key":"10.1016\/j.knosys.2025.114793_bib0034","first-page":"104","article-title":"Transformer-based multimodal feature enhancement networks for multimodal depression detection integrating video, audio and remote photoplethysmograph signals","author":"Fan","year":"2024","journal-title":"Inf. Fusion."},{"key":"10.1016\/j.knosys.2025.114793_bib0035","series-title":"CEUR Workshop Proceedings","first-page":"57","article-title":"Privacy-preserving unsupervised speaker disentanglement method for depression detection from speech","author":"Ravi","year":"2024"},{"key":"10.1016\/j.knosys.2025.114793_bib0036","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1016\/j.jad.2024.08.002","article-title":"Multilevel hybrid handcrafted feature extraction based depression recognition method using speech","volume":"364","author":"Tasci","year":"2024","journal-title":"J. Affect. Disord."},{"key":"10.1016\/j.knosys.2025.114793_bib0037","first-page":"619","article-title":"Facial action units guided graph representation learning for multimodal depression detection","author":"Fu","year":"2025","journal-title":"Neurocomputing"},{"issue":"3","key":"10.1016\/j.knosys.2025.114793_bib0038","doi-asserted-by":"crossref","first-page":"234","DOI":"10.1007\/s43657-023-00152-8","article-title":"A multimodal approach for detection and assessment of depression using text, audio and video","volume":"4","author":"Zhang","year":"2024","journal-title":"Phenomics"},{"issue":"3","key":"10.1016\/j.knosys.2025.114793_bib0039","doi-asserted-by":"crossref","first-page":"828","DOI":"10.1109\/TAFFC.2023.3296318","article-title":"Integrating deep facial priors into landmarks for privacy preserving multimodal depression recognition","volume":"15","author":"Pan","year":"2024","journal-title":"IEEe Trans. Affect. Comput."},{"key":"10.1016\/j.knosys.2025.114793_bib0040","first-page":"120","article-title":"SSLMM: semi-supervised learning with missing modalities for multimodal sentiment analysis","author":"Wang","year":"2025","journal-title":"Inf. Fusion."},{"key":"10.1016\/j.knosys.2025.114793_bib0041","series-title":"Workshops at the Twenty-Ninth AAAI Conference on Artificial Intelligence","article-title":"Encoding time series as images for visual inspection and classification using tiled convolutional neural networks","author":"Wang","year":"2015"},{"issue":"1","key":"10.1016\/j.knosys.2025.114793_bib0042","doi-asserted-by":"crossref","first-page":"460","DOI":"10.1109\/JSEN.2022.3221779","article-title":"Application of convolutional dendrite net for detection of myocardial infarction using ecg signals","volume":"23","author":"Ma","year":"2022","journal-title":"IEEe Sens. J."},{"key":"10.1016\/j.knosys.2025.114793_bib0043","series-title":"CEUR Workshop Proceedings","article-title":"Neural network analysis of electroencephalograms graphical representation","author":"Bragin","year":"2020"},{"issue":"8","key":"10.1016\/j.knosys.2025.114793_bib0044","doi-asserted-by":"crossref","first-page":"5617","DOI":"10.1109\/JIOT.2020.3030492","article-title":"Is image encoding beneficial for deep learning in finance?","volume":"9","author":"Wang","year":"2020","journal-title":"IEEe Internet. Things. J."},{"key":"10.1016\/j.knosys.2025.114793_bib0045","doi-asserted-by":"crossref","first-page":"179","DOI":"10.1023\/A:1025196714293","article-title":"Analysis of multi-dimensional space-filling curves","volume":"7","author":"Mokbel","year":"2003","journal-title":"Geoinformatica"},{"key":"10.1016\/j.knosys.2025.114793_bib0046","series-title":"Proceedings of the 9th International on Audio\/visual Emotion Challenge and Workshop","article-title":"AVEC 2019 workshop and challenge: state-of-mind, detecting depression with AI, and cross-cultural affect recognition","author":"Ringeval","year":"2019"},{"key":"10.1016\/j.knosys.2025.114793_bib0047","series-title":"Proceedings of the 9th International on Audio\/Visual Emotion Challenge and Workshop","first-page":"55","article-title":"Multimodal fusion of BERT-CNN and gated CNN representations for depression detection","author":"Rodrigues Makiuchi","year":"2019"},{"key":"10.1016\/j.knosys.2025.114793_bib0048","series-title":"Proceedings of the 9th International on Audio\/Visual Emotion Challenge and Workshop","first-page":"65","article-title":"A multi-modal hierarchical recurrent neural network for depression detection","author":"Yin","year":"2019"},{"key":"10.1016\/j.knosys.2025.114793_bib0049","series-title":"Proceedings of the 9th International on Audio\/Visual Emotion Challenge and Workshop","first-page":"73","article-title":"Multi-modality depression detection via multi-scale temporal dilated CNNs","author":"Fan","year":"2019"},{"key":"10.1016\/j.knosys.2025.114793_bib0050","series-title":"Proceedings of the 30th ACM International Conference on Multimedia","first-page":"3722","article-title":"CubeMLP: An MLP-based model for multimodal sentiment analysis and depression estimation","author":"Sun","year":"2022"},{"key":"10.1016\/j.knosys.2025.114793_bib0051","first-page":"82","article-title":"A multimodal fusion model with multi-level attention mechanism for depression detection","author":"Fang","year":"2023","journal-title":"Biomed. Signal. Process. Control"},{"issue":"1","key":"10.1016\/j.knosys.2025.114793_bib0052","doi-asserted-by":"crossref","DOI":"10.1038\/s44184-024-00112-8","article-title":"Harnessing multimodal approaches for depression detection using large language models and facial expressions","volume":"3","author":"Sadeghi","year":"2024","journal-title":"NPJ Ment. Health Res."},{"key":"10.1016\/j.knosys.2025.114793_bib0053","first-page":"1","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.knosys.2025.114793_bib0054","doi-asserted-by":"crossref","unstructured":"B\u00fcssow, R., Algorithm Contin Morlet wavelet transform Mechtech System Signal Processing, 2007. 21(8): p. 2970\u20132979.","DOI":"10.1016\/j.ymssp.2007.06.001"},{"issue":"1","key":"10.1016\/j.knosys.2025.114793_bib0055","doi-asserted-by":"crossref","first-page":"298","DOI":"10.1109\/TAFFC.2019.2951656","article-title":"PersEmoN: a deep network for joint analysis of apparent personality, emotion and their relationship","volume":"13","author":"Zhang","year":"2022","journal-title":"IEEe Trans. Affect. Comput."},{"issue":"1","key":"10.1016\/j.knosys.2025.114793_bib0056","doi-asserted-by":"crossref","first-page":"178","DOI":"10.1109\/TAFFC.2021.3064601","article-title":"Self-supervised learning of person-specific facial dynamics for automatic personality recognition","volume":"14","author":"Song","year":"2023","journal-title":"IEEe Trans. Affect. Comput."},{"key":"10.1016\/j.knosys.2025.114793_bib0057","first-page":"239","article-title":"OCEAN-AI framework with EmoFormer cross-hemiface attention approach for personality traits assessment","author":"Ryumina","year":"2024","journal-title":"Expert. Syst. Appl."},{"key":"10.1016\/j.knosys.2025.114793_bib0058","first-page":"238","article-title":"Towards job screening and personality traits estimation from video transcriptions","author":"Bounab","year":"2024","journal-title":"Expert. Syst. Appl."}],"container-title":["Knowledge-Based Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705125018313?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705125018313?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T19:37:45Z","timestamp":1765222665000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0950705125018313"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11]]},"references-count":58,"alternative-id":["S0950705125018313"],"URL":"https:\/\/doi.org\/10.1016\/j.knosys.2025.114793","relation":{},"ISSN":["0950-7051"],"issn-type":[{"type":"print","value":"0950-7051"}],"subject":[],"published":{"date-parts":[[2025,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"FractalMM architecture: Fractal feature fusion for privacy-preserved multimodal depression recognition","name":"articletitle","label":"Article Title"},{"value":"Knowledge-Based Systems","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.knosys.2025.114793","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 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":"114793"}}