{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T12:29:48Z","timestamp":1771244988868,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":30,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819569496","type":"print"},{"value":"9789819569502","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-981-95-6950-2_7","type":"book-chapter","created":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T11:58:44Z","timestamp":1771243124000},"page":"89-102","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["WavGateMamba: A Frequency-Enhanced and\u00a0Gated Mamba Model for\u00a0Multimodal Depression Detection"],"prefix":"10.1007","author":[{"given":"Haiyang","family":"Ye","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dengshi","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yulin","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Fang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"YuXin","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,2,17]]},"reference":[{"key":"7_CR1","doi-asserted-by":"crossref","unstructured":"Malhi, G.S., Mann, J.J.: Depression. Lancet (London, England) 392(10161), 2299\u20132312 (2018)","DOI":"10.1016\/S0140-6736(18)31948-2"},{"key":"7_CR2","unstructured":"Wang, H.G., et al.: Sad-time: a spatiotemporal-fused network for depression detection with automated multi-scale depth-wise and time-interval-related common feature extractor (2024)"},{"key":"7_CR3","unstructured":"Gu, A., Dao, T.: MAMBA: linear-time sequence modeling with selective state spaces. ArXiv, abs\/2312.00752 (2023)"},{"key":"7_CR4","doi-asserted-by":"crossref","unstructured":"Ye, J., Zhang, J., Shan, H.: Progressive fusion mamba for multimodal depression detection, Depmamba (2024)","DOI":"10.1109\/ICASSP49660.2025.10889975"},{"key":"7_CR5","doi-asserted-by":"crossref","unstructured":"Oorloff, T., et al.: Audio-visual feature fusion for video deepfake detection. IEEE AVFF (2024)","DOI":"10.1109\/CVPR52733.2024.02559"},{"key":"7_CR6","doi-asserted-by":"crossref","unstructured":"Fan, H., et al.: Transformer-based multimodal feature enhancement networks for multimodal depression detection integrating video, audio and remote photoplethysmograph signals. Inf. Fus., 104 (2024)","DOI":"10.1016\/j.inffus.2023.102161"},{"key":"7_CR7","doi-asserted-by":"crossref","unstructured":"Zhang, L., Zhang, S., Zhang, X., Zhao, Y.: A multimodal artificial intelligence model for depression severity detection based on audio and video signals. Electronics 14(7), 2079-9292 (2025)","DOI":"10.3390\/electronics14071464"},{"key":"7_CR8","doi-asserted-by":"publisher","unstructured":"Ramalakshmi, N.R., Kumar, M.G., Raghavi, S.: Automated depression detection using CNN and transformer-based pre-trained language models. In: International Conference on Computer, Communication, and Signal Processing (2025). https:\/\/doi.org\/10.1007\/978-3-031-73617-9_4","DOI":"10.1007\/978-3-031-73617-9_4"},{"key":"7_CR9","doi-asserted-by":"crossref","unstructured":"Zhao, J., Jin, Q.: A two-stage depression recognition model based on improved YOLOv5 and spatial-temporal CNN-transformer network. In: 2024 IEEE Cyber Science and Technology Congress (CyberSciTech)","DOI":"10.1109\/CyberSciTech64112.2024.00058"},{"key":"7_CR10","doi-asserted-by":"publisher","unstructured":"Chen, Q., Li, J., Fang, X.: Dual triple attention guided CNN-VMamba for medical image segmentation. Multimedia Syst. 30, 275 (2024). https:\/\/doi.org\/10.1007\/s00530-024-01498-3","DOI":"10.1007\/s00530-024-01498-3"},{"key":"7_CR11","doi-asserted-by":"crossref","unstructured":"Bi, H., Yu, G., He, Y., Liu, W., Zheng, Z.: VM-BHINet: vision mamba bimanual hand interaction network for 3D interacting hand mesh recovery from a single RGB image (2025)","DOI":"10.1145\/3728308"},{"key":"7_CR12","doi-asserted-by":"crossref","unstructured":"Intriago, A., Paspatis, A., Liberati, F., Konstantinou, C.: Admittance identification of grid-forming inverters using time and frequency-domain techniques (2025)","DOI":"10.1109\/PowerTech59965.2025.11180468"},{"key":"7_CR13","doi-asserted-by":"crossref","unstructured":"Korti\u0161, J., Maliar, L., Daniel, \u013d.: Estimation of natural frequencies of the laboratory truss structure with output only subspace and frequency-domain techniques. In: MATEC Web of Conferences (2020)","DOI":"10.1051\/matecconf\/202031300003"},{"key":"7_CR14","doi-asserted-by":"crossref","unstructured":"Grandhe, P., Sreenivasa\u00a0Reddy He, E.: A novel method for content based 3D medical image retrieval system using dual tree m-band wavelets transform and multiclass support vector machine. J. Adv. Res. Dyn. Control Syst. (2020)","DOI":"10.5373\/JARDCS\/V12I3\/20201192"},{"key":"7_CR15","doi-asserted-by":"publisher","unstructured":"Chalasani, T., Smolic, A.: Egocentric hand gesture recognition on untrimmed videos using state activation gate LSTMS (2022). https:\/\/doi.org\/10.1007\/978-3-031-37660-3_25","DOI":"10.1007\/978-3-031-37660-3_25"},{"key":"7_CR16","unstructured":"Tajima, Y., Inoue, N., Sekikawa, Y., Sato, I. and Yokota, R.: Masked gated linear unit (2025)"},{"key":"7_CR17","doi-asserted-by":"crossref","unstructured":"Wu, J., et al.: DuagNet: an unrestricted multimodal speech recognition framework using dual adaptive gating fusion. Appl. Intell. (2024)","DOI":"10.1007\/s10489-024-06119-0"},{"key":"7_CR18","doi-asserted-by":"crossref","unstructured":"Kwak, D., Jang, Y., Kim, S., Chung, J.S.: EDNet: a distortion-agnostic speech enhancement framework with gating mamba mechanism and phase shift-invariant training (2025)","DOI":"10.1109\/TASLPRO.2026.3662487"},{"key":"7_CR19","doi-asserted-by":"crossref","unstructured":"Pampouchidou, A., et al.: Facial geometry and speech analysis for depression detection. In: Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pp. 1433\u20131436 (2017)","DOI":"10.1109\/EMBC.2017.8037103"},{"key":"7_CR20","doi-asserted-by":"crossref","unstructured":"Yin, S., Liang, C., Ding, H., Wang, S.: A multi-modal hierarchical recurrent neural network for depression detection. In: Ringeval, F., Schuller, B.W., Valstar, M.F., Cummins, N., Cowie, R., Pantic, M. (eds.) Proceedings of the International Audio\/Visual Emotion Challenge and Workshop (AVEC), pp. 65\u201371 (2019)","DOI":"10.1145\/3347320.3357696"},{"key":"7_CR21","doi-asserted-by":"crossref","unstructured":"Kazakos, E., Nagrani, A., Zisserman, A., Damen, D.: EPIC-fusion: audio-visual temporal binding for egocentric action recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 5491\u20135500 (2019)","DOI":"10.1109\/ICCV.2019.00559"},{"issue":"3","key":"7_CR22","doi-asserted-by":"publisher","first-page":"577","DOI":"10.1016\/j.dcan.2023.03.007","volume":"10","author":"Y Tao","year":"2024","unstructured":"Tao, Y., Yang, M., Yushan, W., Lee, K., Kline, A.S., Bin, H.: Depressive semantic awareness from vlog facial and vocal streams via spatio-temporal transformer. Digit. Commun. Netw. 10(3), 577\u2013585 (2024)","journal-title":"Digit. Commun. Netw."},{"key":"7_CR23","doi-asserted-by":"crossref","unstructured":"Zadeh, A., Chen, M., Poria, S., Cambria, E., Morency, L.P.: Tensor fusion network for multimodal sentiment analysis. In: Palmer, M., Hwa, R., Riedel, S. (eds.) Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1103\u20131114 (2017)","DOI":"10.18653\/v1\/D17-1115"},{"key":"7_CR24","doi-asserted-by":"crossref","unstructured":"Yoon, J., Kang, C., Kim, S., Han, J.: D-Vlog: multimodal Vlog dataset for depression detection. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 12226\u201312234 (2022)","DOI":"10.1609\/aaai.v36i11.21483"},{"key":"7_CR25","doi-asserted-by":"publisher","unstructured":"Shangguan, Z.,\u00a0Li, X.,\u00a0Dong, Y.,\u00a0Yuan, X.: Automatic depression detection using attention-based deep multiple instance learning. In: International Conference on Heterogeneous Networking for Quality, Reliability, Security and Robustness, pp. 40\u201351. Springer (2023). https:\/\/doi.org\/10.1007\/978-3-031-65126-7_4","DOI":"10.1007\/978-3-031-65126-7_4"},{"key":"7_CR26","doi-asserted-by":"publisher","DOI":"10.1016\/j.dsp.2023.103986","volume":"137","author":"L Zhou","year":"2023","unstructured":"Zhou, L., Liu, Z., Yuan, X., Shangguan, Z., Li, Y., Hu, B.: CAIINet: neural network based on contextual attention and information interaction mechanism for depression detection. Digit. Sig. Process. 137, 103986 (2023)","journal-title":"Digit. Sig. Process."},{"key":"7_CR27","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2024.106490","volume":"96","author":"L He","year":"2024","unstructured":"He, L., et al.: DepressFormer: leveraging video SWIN transformer and fine-grained local features for depression scale estimation. Biomed. Signal Process. Control 96, 106490 (2024)","journal-title":"Biomed. Signal Process. Control"},{"key":"7_CR28","doi-asserted-by":"crossref","unstructured":"Kowalewski, M.,\u00a0Stroinski, M.,\u00a0Kwarciak, K.,\u00a0Laptiev, V.,\u00a0Hemmerling, D.: End-to-end multimodal system for depression detection from online recordings. In: 45th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), pp. 1\u20134. IEEE (2023)","DOI":"10.1109\/EMBC40787.2023.10340782"},{"key":"7_CR29","doi-asserted-by":"publisher","first-page":"669","DOI":"10.1109\/TNSRE.2022.3224135","volume":"31","author":"L Zhou","year":"2022","unstructured":"Zhou, L., Liu, Z., Shangguan, Z., Yuan, X., Li, Y., Bin, H.: TAMFN: Time-aware Attention Multimodal Fusion Network for depression detection. IEEE Trans. Neural Syst. Rehabil. Eng. 31, 669\u2013679 (2022)","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"7_CR30","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2025.103632","volume":"126","author":"L He","year":"2024","unstructured":"He, L., et al.: LMVD: a large-scale multimodal vlog dataset for depression detection in the wild. Inf. Fus. 126, 103632 (2024)","journal-title":"Inf. Fus."}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-6950-2_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T11:58:48Z","timestamp":1771243128000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-6950-2_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819569496","9789819569502"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-6950-2_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"17 February 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MMM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multimedia Modeling","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Prague","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Czech Republic","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 January 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31 January 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"32","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/mmm2026.cz\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}