{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T06:11:19Z","timestamp":1784182279186,"version":"3.55.0"},"reference-count":52,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T00:00:00Z","timestamp":1784160000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T00:00:00Z","timestamp":1784160000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100019492","name":"National Natural Science Foundation of China-China Academy of General Technology Joint Fund for Basic Research","doi-asserted-by":"crossref","award":["62272192"],"award-info":[{"award-number":["62272192"]}],"id":[{"id":"10.13039\/501100019492","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1007\/s00530-026-02509-1","type":"journal-article","created":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T05:53:40Z","timestamp":1784181220000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["IAEC-DepressNet: Identity-Adaptive and Emotionally Consistent Multimodal Depression Detection Network"],"prefix":"10.1007","volume":"32","author":[{"given":"Xingyu","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiyang","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiangxin","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanchun","family":"Liang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5115-8137","authenticated-orcid":false,"given":"Xiaohu","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,16]]},"reference":[{"issue":"4","key":"2509_CR1","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1521\/pedi.1994.8.4.257","volume":"8","author":"PH Soloff","year":"1994","unstructured":"Soloff, P.H., Lis, J.A., Kelly, T., Cornelius, J., Ulrich, R.: Self-mutilation and suicidal behavior in borderline personality disorder. J. Pers. Disord. 8(4), 257\u2013267 (1994)","journal-title":"J. Pers. Disord."},{"issue":"1\u20133","key":"2509_CR2","doi-asserted-by":"publisher","first-page":"163","DOI":"10.1016\/j.jad.2008.06.026","volume":"114","author":"K Kroenke","year":"2009","unstructured":"Kroenke, K., Strine, T.W., Spitzer, R.L., Williams, J.B., Berry, J.T., Mokdad, A.H.: The phq-8 as a measure of current depression in the general population. J. Affect. Disord. 114(1\u20133), 163\u2013173 (2009)","journal-title":"J. Affect. Disord."},{"key":"2509_CR3","doi-asserted-by":"publisher","first-page":"103107","DOI":"10.1016\/j.bspc.2021.103107","volume":"71","author":"E Rejaibi","year":"2022","unstructured":"Rejaibi, E., Komaty, A., Meriaudeau, F., Agrebi, S., Othmani, A.: Mfcc-based recurrent neural network for automatic clinical depression recognition and assessment from speech. Biomed. Signal Process. Control 71, 103107 (2022)","journal-title":"Biomed. Signal Process. Control"},{"key":"2509_CR4","doi-asserted-by":"crossref","unstructured":"Zhang, P., Wu, M., Dinkel, H., Yu, K.: Depa: Self-supervised audio embedding for depression detection. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 135\u2013143. (2021)","DOI":"10.1145\/3474085.3479236"},{"key":"2509_CR5","doi-asserted-by":"publisher","first-page":"128209","DOI":"10.1016\/j.neucom.2024.128209","volume":"601","author":"X Xu","year":"2024","unstructured":"Xu, X., Wang, Y., Wei, X., Wang, F., Zhang, X.: Attention-based acoustic feature fusion network for depression detection. Neurocomputing 601, 128209 (2024)","journal-title":"Neurocomputing"},{"key":"2509_CR6","doi-asserted-by":"crossref","unstructured":"Wu, W., Zhang, C., Woodland, P.C.: Self-supervised representations in speech-based depression detection. In: ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1\u20135. IEEE\u00a0(2023)","DOI":"10.1109\/ICASSP49357.2023.10094910"},{"key":"2509_CR7","unstructured":"He, S., Ji, Z., Zhou, Y., Xu, C.: Spatio-temporal modeling for depression recognition from longitudinal video data. In: Proceedings of the ACM International Conference on Multimedia, (2021)"},{"key":"2509_CR8","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3164306","author":"A Gupta","year":"2022","unstructured":"Gupta, A., Dey, L., Gupta, P.: Depression analysis using multi-scale cnn and bi-lstm on facial video frames. IEEE Trans. Affect. Comput. (2022). https:\/\/doi.org\/10.1109\/TAFFC.2022.3164306","journal-title":"IEEE Trans. Affect. Comput."},{"key":"2509_CR9","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1016\/j.patrec.2022.04.016","volume":"158","author":"Y Zhao","year":"2022","unstructured":"Zhao, Y., Wang, W., Hu, C.: Depression recognition via facial expression with attention mechanism in videos. Pattern Recogn. Lett. 158, 24\u201330 (2022)","journal-title":"Pattern Recogn. Lett."},{"key":"2509_CR10","doi-asserted-by":"publisher","first-page":"165","DOI":"10.1016\/j.neucom.2020.10.015","volume":"422","author":"L He","year":"2021","unstructured":"He, L., Chan, J.C.-W., Wang, Z.: Automatic depression recognition using cnn with attention mechanism from videos. Neurocomputing 422, 165\u2013175 (2021)","journal-title":"Neurocomputing"},{"key":"2509_CR11","doi-asserted-by":"publisher","first-page":"117512","DOI":"10.1016\/j.eswa.2022.117512","volume":"204","author":"M Niu","year":"2022","unstructured":"Niu, M., He, L., Li, Y., Liu, B.: Depressioner: Facial dynamic representation for automatic depression level prediction. Expert Syst. Appl. 204, 117512 (2022)","journal-title":"Expert Syst. Appl."},{"key":"2509_CR12","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1016\/j.inffus.2021.10.012","volume":"80","author":"L He","year":"2022","unstructured":"He, L., Niu, M., Tiwari, P., Marttinen, P., Su, R., Jiang, J., Guo, C., Wang, H., Ding, S., Wang, Z., et al.: Deep learning for depression recognition with audiovisual cues: a review. Inf. Fus. 80, 56\u201386 (2022)","journal-title":"Inf. Fus."},{"key":"2509_CR13","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7132\u20137141. (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"2509_CR14","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-020-00280-0","author":"A Toisoul","year":"2021","unstructured":"Toisoul, A., Kossaifi, J., Bulat, A., Tzimiropoulos, G., Pantic, M.: Estimation of continuous valence and arousal levels from faces in naturalistic conditions. Nat. Mach. Intell. (2021). https:\/\/doi.org\/10.1038\/s42256-020-00280-0","journal-title":"Nat. Mach. Intell."},{"issue":"1","key":"2509_CR15","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1109\/MSP.2017.2765202","volume":"35","author":"A Creswell","year":"2018","unstructured":"Creswell, A., White, T., Dumoulin, V., Arulkumaran, K., Sengupta, B., Bharath, A.A.: Generative adversarial networks: an overview. IEEE Signal Process. Mag. 35(1), 53\u201365 (2018)","journal-title":"IEEE Signal Process. Mag."},{"issue":"4","key":"2509_CR16","doi-asserted-by":"publisher","first-page":"3313","DOI":"10.1109\/TKDE.2021.3130191","volume":"35","author":"J Gui","year":"2023","unstructured":"Gui, J., Sun, Z., Wen, Y., Tao, D., Ye, J.: A review on generative adversarial networks: Algorithms, theory, and applications. IEEE Trans. Knowl. Data Eng. 35(4), 3313\u20133332 (2023). https:\/\/doi.org\/10.1109\/TKDE.2021.3130191","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"2509_CR17","doi-asserted-by":"publisher","unstructured":"Dhall, A., Goecke, R.: A temporally piece-wise fisher vector approach for depression analysis. In: 2015 International Conference on Affective Computing and Intelligent Interaction (ACII), pp. 255\u2013259 (2015). https:\/\/doi.org\/10.1109\/ACII.2015.7344580","DOI":"10.1109\/ACII.2015.7344580"},{"issue":"3","key":"2509_CR18","doi-asserted-by":"publisher","first-page":"1581","DOI":"10.1109\/TAFFC.2020.3021755","volume":"13","author":"WC De Melo","year":"2020","unstructured":"De Melo, W.C., Granger, E., Hadid, A.: A deep multiscale spatiotemporal network for assessing depression from facial dynamics. IEEE Trans. Affect. Comput. 13(3), 1581\u20131592 (2020)","journal-title":"IEEE Trans. Affect. Comput."},{"key":"2509_CR19","doi-asserted-by":"publisher","unstructured":"Melo, W.C., Granger, E., Hadid, A.: Combining global and local convolutional 3d networks for detecting depression from facial expressions. In: 2019 14th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2019), pp. 1\u20138 (2019). https:\/\/doi.org\/10.1109\/FG.2019.8756568","DOI":"10.1109\/FG.2019.8756568"},{"key":"2509_CR20","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1016\/j.jbi.2018.05.007","volume":"83","author":"L He","year":"2018","unstructured":"He, L., Cao, C.: Automated depression analysis using convolutional neural networks from speech. J. Biomed. Inform. 83, 103\u2013111 (2018)","journal-title":"J. Biomed. Inform."},{"issue":"1","key":"2509_CR21","doi-asserted-by":"publisher","first-page":"446","DOI":"10.1109\/TAI.2023.3243596","volume":"5","author":"A Hajavi","year":"2023","unstructured":"Hajavi, A., Etemad, A.: Audio representation learning by distilling video as privileged information. IEEE Trans. Artif. Intell. 5(1), 446\u2013456 (2023)","journal-title":"IEEE Trans. Artif. Intell."},{"issue":"1","key":"2509_CR22","doi-asserted-by":"publisher","first-page":"133","DOI":"10.1109\/TAFFC.2020.3035535","volume":"14","author":"S Alghowinem","year":"2020","unstructured":"Alghowinem, S., Gedeon, T., Goecke, R., Cohn, J.F., Parker, G.: Interpretation of depression detection models via feature selection methods. IEEE Trans. Affect. Comput. 14(1), 133\u2013152 (2020)","journal-title":"IEEE Trans. Affect. Comput."},{"issue":"12","key":"2509_CR23","doi-asserted-by":"publisher","first-page":"3714","DOI":"10.3390\/s24123714","volume":"24","author":"Z Zhang","year":"2024","unstructured":"Zhang, Z., Zhang, S., Ni, D., Wei, Z., Yang, K., Jin, S., Huang, G., Liang, Z., Zhang, L., Li, L., et al.: Multimodal sensing for depression risk detection: integrating audio, video, and text data. Sensors 24(12), 3714 (2024)","journal-title":"Sensors"},{"key":"2509_CR24","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyt.2025.1508772","volume":"16","author":"N Jin","year":"2025","unstructured":"Jin, N., Ye, R., Li, P.: Diagnosis of depression based on facial multimodal data. Front. Psych. 16, 1508772 (2025)","journal-title":"Front. Psych."},{"key":"2509_CR25","doi-asserted-by":"crossref","unstructured":"Lv, F., Chen, X., Huang, Y., Duan, L., Lin, G.: Progressive modality reinforcement for human multimodal emotion recognition from unaligned multimodal sequences. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2554\u20132562. (2021)","DOI":"10.1109\/CVPR46437.2021.00258"},{"key":"2509_CR26","doi-asserted-by":"crossref","unstructured":"Meng, T., Zhang, F., Shou, Y., Shao, H., Ai, W., Li, K.: Masked graph learning with recurrent alignment for multimodal emotion recognition in conversation. In: IEEE\/ACM Transactions on Audio, Speech, and Language Processing (2024)","DOI":"10.1109\/TASLP.2024.3434495"},{"key":"2509_CR27","doi-asserted-by":"publisher","first-page":"3592","DOI":"10.1109\/TASLP.2021.3129331","volume":"29","author":"B Chen","year":"2021","unstructured":"Chen, B., Cao, Q., Hou, M., Zhang, Z., Lu, G., Zhang, D.: Multimodal emotion recognition with temporal and semantic consistency. IEEE\/ACM Trans. Audio, Speech, Lang. Process. 29, 3592\u20133603 (2021)","journal-title":"IEEE\/ACM Trans. Audio, Speech, Lang. Process."},{"issue":"4","key":"2509_CR28","doi-asserted-by":"publisher","first-page":"2156","DOI":"10.1109\/TAFFC.2022.3216993","volume":"13","author":"L Goncalves","year":"2022","unstructured":"Goncalves, L., Busso, C.: Robust audiovisual emotion recognition: aligning modalities, capturing temporal information, and handling missing features. IEEE Trans. Affect. Comput. 13(4), 2156\u20132170 (2022)","journal-title":"IEEE Trans. Affect. Comput."},{"issue":"9","key":"2509_CR29","doi-asserted-by":"publisher","first-page":"5318","DOI":"10.1109\/TCSVT.2023.3247822","volume":"33","author":"M Hou","year":"2023","unstructured":"Hou, M., Zhang, Z., Liu, C., Lu, G.: Semantic alignment network for multi-modal emotion recognition. IEEE Trans. Circuits Syst. Video Technol. 33(9), 5318\u20135329 (2023)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"2509_CR30","doi-asserted-by":"crossref","unstructured":"Han, H., Miao, K., Zheng, Q., Luo, M.: Noisy correspondence learning with meta similarity correction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7517\u20137526. (2023)","DOI":"10.1109\/CVPR52729.2023.00726"},{"key":"2509_CR31","doi-asserted-by":"crossref","unstructured":"Han, H., Zheng, Q., Dai, G., Luo, M., Wang, J.: Learning to rematch mismatched pairs for robust cross-modal retrieval. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 26679\u201326688. (2024)","DOI":"10.1109\/CVPR52733.2024.02519"},{"key":"2509_CR32","doi-asserted-by":"publisher","first-page":"7761","DOI":"10.1109\/TMM.2024.3371220","volume":"26","author":"H Han","year":"2024","unstructured":"Han, H., Zheng, Q., Luo, M., Miao, K., Tian, F., Chen, Y.: Noise-tolerant learning for audio-visual action recognition. IEEE Trans. Multimed. 26, 7761\u20137774 (2024)","journal-title":"IEEE Trans. Multimed."},{"key":"2509_CR33","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2025.3559533","author":"H Han","year":"2025","unstructured":"Han, H., Luo, M., Liu, H., Nan, F., Liu, J.: A unified optimal transport framework for cross-modal retrieval with noisy labels. IEEE Trans. Neural Netw. Learn. Syst. (2025). https:\/\/doi.org\/10.1109\/TNNLS.2025.3559533","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"2509_CR34","doi-asserted-by":"publisher","first-page":"104561","DOI":"10.1016\/j.bspc.2022.104561","volume":"82","author":"M Fang","year":"2023","unstructured":"Fang, M., Peng, S., Liang, Y., Hung, C.-C., Liu, S.: A multimodal fusion model with multi-level attention mechanism for depression detection. Biomed. Signal Process. Control 82, 104561 (2023). https:\/\/doi.org\/10.1016\/j.bspc.2022.104561","journal-title":"Biomed. Signal Process. Control"},{"key":"2509_CR35","doi-asserted-by":"publisher","first-page":"102161","DOI":"10.1016\/j.inffus.2023.102161","volume":"104","author":"H Fan","year":"2024","unstructured":"Fan, H., Zhang, X., Xu, Y., Fang, J., Zhang, S., Zhao, X., Yu, J.: Transformer-based multimodal feature enhancement networks for multimodal depression detection integrating video, audio and remote photoplethysmograph signals. Inf. Fus. 104, 102161 (2024)","journal-title":"Inf. Fus."},{"key":"2509_CR36","doi-asserted-by":"crossref","unstructured":"Lei, J., Yang, Q., Li, B., Zhang, W.: Ccfn: Depression detection via multimodal fusion with complex-valued capsule network. In: 2024 International Joint Conference on Neural Networks (IJCNN), pp. 1\u20136. IEEE (2024)","DOI":"10.1109\/IJCNN60899.2024.10650262"},{"key":"2509_CR37","doi-asserted-by":"crossref","unstructured":"Thirunavukkarasu, J., Jebamathi, M.S., Varshaa, P., Nisha, M., Sri, M.N.: Deep multimodal fusion for depression detection: Integrating facial emotion recognition, eeg signals and audio cues. In: 2024 International Conference on Advances in Computing, Communication and Applied Informatics (ACCAI), pp. 1\u20137. IEEE (2024)","DOI":"10.1109\/ACCAI61061.2024.10602143"},{"key":"2509_CR38","doi-asserted-by":"crossref","unstructured":"Ye, J., Zhang, J., Shan, H.: Depmamba: Progressive fusion mamba for multimodal depression detection. In: ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1\u20135.\u00a0IEEE (2025)","DOI":"10.1109\/ICASSP49660.2025.10889975"},{"key":"2509_CR39","doi-asserted-by":"crossref","unstructured":"Ilias, L., Askounis, D.: A cross-attention layer coupled with multimodal fusion methods for recognizing depression from spontaneous speech. In: Proc. Interspeech 2024, pp. 912\u2013916. (2024)","DOI":"10.21437\/Interspeech.2024-188"},{"key":"2509_CR40","doi-asserted-by":"crossref","unstructured":"Wang, X., Bo, L., Fuxin, L.: Adaptive wing loss for robust face alignment via heatmap regression. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6971\u20136981. (2019)","DOI":"10.1109\/ICCV.2019.00707"},{"issue":"4","key":"2509_CR41","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1109\/TASSP.1980.1163420","volume":"28","author":"S Davis","year":"1980","unstructured":"Davis, S., Mermelstein, P.: Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences. IEEE Trans. Acoust. Speech Signal Process. 28(4), 357\u2013366 (1980)","journal-title":"IEEE Trans. Acoust. Speech Signal Process."},{"issue":"2","key":"2509_CR42","doi-asserted-by":"publisher","first-page":"190","DOI":"10.1109\/TAFFC.2015.2457417","volume":"7","author":"F Eyben","year":"2015","unstructured":"Eyben, F., Scherer, K.R., Schuller, B.W., Sundberg, J., Andr\u00e9, E., Busso, C., Devillers, L.Y., Epps, J., Laukka, P., Narayanan, S.S., et al.: The geneva minimalistic acoustic parameter set (gemaps) for voice research and affective computing. IEEE Trans. Affect. Comput. 7(2), 190\u2013202 (2015)","journal-title":"IEEE Trans. Affect. Comput."},{"key":"2509_CR43","doi-asserted-by":"publisher","unstructured":"Valstar, M., Schuller, B., Smith, K., Almaev, T., Eyben, F., Krajewski, J., Cowie, R., Pantic, M.: Avec 2014 - 3d dimensional affect and depression recognition challenge. AVEC 2014 - Proceedings of the 4th International Workshop on Audio\/Visual Emotion Challenge, Workshop of MM 2014 (2014). https:\/\/doi.org\/10.1145\/2661806.2661807","DOI":"10.1145\/2661806.2661807"},{"key":"2509_CR44","doi-asserted-by":"crossref","unstructured":"Ringeval, F., Schuller, B., Valstar, M., Gratch, J., Cowie, R., Scherer, S., Mozgai, S., Cummins, N., Schmitt, M., Pantic, M.: Avec 2017: Real-life depression, and affect recognition workshop and challenge. In: Proceedings of the 7th Annual Workshop on Audio\/visual Emotion Challenge, pp. 3\u20139. (2017)","DOI":"10.1145\/3133944.3133953"},{"key":"2509_CR45","doi-asserted-by":"crossref","unstructured":"Ringeval, F., Schuller, B., Valstar, M., Cummins, N., Cowie, R., Tavabi, L., Schmitt, M., Alisamir, S., Amiriparian, S., Messner, E.-M.: Avec 2019 workshop and challenge: state-of-mind, detecting depression with ai, and cross-cultural affect recognition. In: Proceedings of the 9th International on Audio\/visual Emotion Challenge and Workshop, pp. 3\u201312. (2019)","DOI":"10.1145\/3347320.3357688"},{"key":"2509_CR46","doi-asserted-by":"crossref","unstructured":"P\u00e9rez\u00a0Espinosa, H., Escalante, H.J., Villase\u00f1or-Pineda, L., Montes-y-G\u00f3mez, M., Pinto-Aveda\u00f1o, D., Reyez-Meza, V.: Fusing affective dimensions and audio-visual features from segmented video for depression recognition: Inaoe-buap\u2019s participation at avec\u201914 challenge. In: Proceedings of the 4th International Workshop on Audio\/visual Emotion Challenge, pp. 49\u201355 (2014)","DOI":"10.1145\/2661806.2661815"},{"key":"2509_CR47","doi-asserted-by":"crossref","unstructured":"Kaya, H., \u00c7illi, F., Salah, A.A.: Ensemble cca for continuous emotion prediction. In: Proceedings of the 4th International Workshop on Audio\/Visual Emotion Challenge, pp. 19\u201326. (2014)","DOI":"10.1145\/2661806.2661814"},{"key":"2509_CR48","doi-asserted-by":"crossref","unstructured":"Williamson, J.R., Quatieri, T.F., Helfer, B.S., Ciccarelli, G., Mehta, D.D.: Vocal and facial biomarkers of depression based on motor incoordination and timing. In: Proceedings of the 4th International Workshop on Audio\/visual Emotion Challenge, pp. 65\u201372. (2014)","DOI":"10.1145\/2661806.2661809"},{"key":"2509_CR49","doi-asserted-by":"crossref","unstructured":"Cholet, S., Paugam-Moisy, H., Regis, S.: Bidirectional associative memory for multimodal fusion: a depression evaluation case study. In: 2019 International Joint Conference on Neural Networks (IJCNN), pp. 1\u20136. IEEE (2019)","DOI":"10.1109\/IJCNN.2019.8852089"},{"key":"2509_CR50","doi-asserted-by":"crossref","unstructured":"Pan, Y., Jiang, J., Jiang, K., Liu, X.: Disentangled-multimodal privileged knowledge distillation for depression recognition with incomplete multimodal data. In: Proceedings of the 32nd ACM International Conference on Multimedia, pp. 5712\u20135721 (2024)","DOI":"10.1145\/3664647.3681227"},{"issue":"1","key":"2509_CR51","doi-asserted-by":"publisher","first-page":"294","DOI":"10.1109\/TAFFC.2020.3031345","volume":"14","author":"M Niu","year":"2020","unstructured":"Niu, M., Tao, J., Liu, B., Huang, J., Lian, Z.: Multimodal spatiotemporal representation for automatic depression level detection. IEEE Trans. Affect. Comput. 14(1), 294\u2013307 (2020)","journal-title":"IEEE Trans. Affect. Comput."},{"key":"2509_CR52","doi-asserted-by":"publisher","DOI":"10.1109\/taffc.2023.3296318","author":"Y Pan","year":"2024","unstructured":"Pan, Y., Shang, Y., Shao, Z., Liu, T., Guo, G., Ding, H.: Integrating deep facial priors into landmarks for privacy preserving multimodal depression recognition. IEEE Trans. Affect. Comput. (2024). https:\/\/doi.org\/10.1109\/taffc.2023.3296318","journal-title":"IEEE Trans. Affect. Comput."}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-026-02509-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-026-02509-1","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-026-02509-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T05:53:46Z","timestamp":1784181226000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-026-02509-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,16]]},"references-count":52,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2026,8]]}},"alternative-id":["2509"],"URL":"https:\/\/doi.org\/10.1007\/s00530-026-02509-1","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,16]]},"assertion":[{"value":"30 January 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 June 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 July 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no conflict of interest.","order":1,"name":"Ethics","label":"Conflict of interest","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"447"}}