{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T17:43:28Z","timestamp":1743097408793,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":22,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819709021"},{"type":"electronic","value":"9789819709038"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-981-97-0903-8_22","type":"book-chapter","created":{"date-parts":[[2024,2,29]],"date-time":"2024-02-29T11:02:50Z","timestamp":1709204570000},"page":"221-231","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Multimodal Depression Recognition Using Audio and Visual"],"prefix":"10.1007","author":[{"given":"Xia","family":"Xu","sequence":"first","affiliation":[]},{"given":"Guanhong","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Xueqian","family":"Mao","sequence":"additional","affiliation":[]},{"given":"Qinghua","family":"Lu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,3,1]]},"reference":[{"key":"22_CR1","doi-asserted-by":"publisher","first-page":"764374","DOI":"10.3389\/fpsyt.2022.764374","volume":"13","author":"\u00c5 Hammar","year":"2022","unstructured":"Hammar, \u00c5., Ronold, E.H., Rekkedal, G.\u00c5.: Cognitive impairment and neurocognitive profiles in major depression\u2014a clinical perspective. Front. Psychiatry 13, 764374 (2022)","journal-title":"Front. Psychiatry"},{"key":"22_CR2","unstructured":"WHO: Depression key facts. World Health Organization (2023). https:\/\/www.who.int\/news-room\/fact-sheets\/detail\/depression"},{"key":"22_CR3","doi-asserted-by":"publisher","first-page":"255","DOI":"10.1093\/fampra\/cmr092","volume":"29","author":"I Schumann","year":"2012","unstructured":"Schumann, I., Schneider, A., Kantert, C., L\u00f6we, B., Linde, K.: Physicians\u2019 attitudes, diagnostic process and barriers regarding depression diagnosis in primary care: a systematic review of qualitative studies. Fam. Pract. 29, 255\u2013263 (2012)","journal-title":"Fam. Pract."},{"key":"22_CR4","unstructured":"World Health Organization. Depression and Other Common Mental Disorders: Global Health Estimates. World Health Organization (2017)"},{"issue":"7","key":"22_CR5","doi-asserted-by":"publisher","first-page":"580","DOI":"10.1016\/j.biopsych.2012.03.015","volume":"72","author":"JC Mundt","year":"2012","unstructured":"Mundt, J.C., Vogel, A.P., Feltner, D.E., Lenderking, W.R.: Vocal acoustic biomarkers of depression severity and treatment response. Biol. Psychiat. 72(7), 580\u2013587 (2012)","journal-title":"Biol. Psychiat."},{"key":"22_CR6","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":"22_CR7","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."},{"key":"22_CR8","doi-asserted-by":"crossref","unstructured":"Ma, X., Yang, H., Chen, Q., Huang, D., Wang, Y.: Depaudionet: an efficient deep model for audio based depression classification. In: Proceedings of the 6th International Workshop on Audio\/Visual Emotion Challenge, pp. 35\u201342 (2016)","DOI":"10.1145\/2988257.2988267"},{"key":"22_CR9","doi-asserted-by":"crossref","unstructured":"Girard, J.M., Cohn, J.F., Mahoor, M.H., Mavadati, S., Rosenwald, D.P.: Social risk and depression: evidence from manual and automatic facial expression analysis. In: 2013 10th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG), pp. 1\u20138. IEEE (2013)","DOI":"10.1109\/FG.2013.6553748"},{"issue":"4","key":"22_CR10","doi-asserted-by":"publisher","first-page":"445","DOI":"10.1109\/TAFFC.2017.2724035","volume":"10","author":"A Pampouchidou","year":"2017","unstructured":"Pampouchidou, A., et al.: Automatic assessment of depression based on visual cues: a systematic review. IEEE Trans. Affect. Comput. 10(4), 445\u2013470 (2017)","journal-title":"IEEE Trans. Affect. Comput."},{"issue":"17","key":"22_CR11","doi-asserted-by":"publisher","first-page":"3693","DOI":"10.3390\/s19173693","volume":"19","author":"M Gavrilescu","year":"2019","unstructured":"Gavrilescu, M., Vizireanu, N.: Predicting depression, anxiety, and stress levels from videos using the facial action coding system. Sensors 19(17), 3693 (2019)","journal-title":"Sensors"},{"issue":"6","key":"22_CR12","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1109\/MSP.2017.2738401","volume":"34","author":"D Ramachandram","year":"2017","unstructured":"Ramachandram, D., Taylor, G.W.: Deep multimodal learning: a survey on recent advances and trends. IEEE Signal Process. Mag. 34(6), 96\u2013108 (2017)","journal-title":"IEEE Signal Process. Mag."},{"key":"22_CR13","doi-asserted-by":"crossref","unstructured":"Meng, H., Huang, D., Wang, H., Yang, H., Ai-Shuraifi, M., Wang, Y.: Depression recognition based on dynamic facial and vocal expression features using partial least square regression. In: Proceedings of the 3rd ACM International Workshop on Audio\/Visual Emotion Challenge, pp. 21\u201330 (2013)","DOI":"10.1145\/2512530.2512532"},{"key":"22_CR14","doi-asserted-by":"crossref","unstructured":"Alghowinem, S., Goecke, R., Wagner, M., Parkerx, G., Breakspear, M.: Head pose and movement analysis as an indicator of depression. In: 2013 Humaine Association Conference on Affective Computing and Intelligent Interaction, pp. 283\u2013288. IEEE (2013)","DOI":"10.1109\/ACII.2013.53"},{"key":"22_CR15","doi-asserted-by":"publisher","first-page":"40","DOI":"10.1016\/j.csl.2018.08.004","volume":"55","author":"JR Williamson","year":"2019","unstructured":"Williamson, J.R., Young, D., Nierenberg, A.A., Niemi, J., Helfer, B.S., Quatieri, T.F.: Tracking depression severity from audio and video based on speech articulatory coordination. Comput. Speech Lang. 55, 40\u201356 (2019)","journal-title":"Comput. Speech Lang."},{"issue":"2","key":"22_CR16","doi-asserted-by":"publisher","first-page":"201","DOI":"10.1109\/TAFFC.2014.2326393","volume":"5","author":"D Bone","year":"2014","unstructured":"Bone, D., Lee, C.C., Narayanan, S.: Robust unsupervised arousal rating: a rule-based framework with knowledge-inspired vocal features. IEEE Trans. Affect. Comput. 5(2), 201\u2013213 (2014)","journal-title":"IEEE Trans. Affect. Comput."},{"key":"22_CR17","doi-asserted-by":"crossref","unstructured":"Eyben, F., Weninger, F., Schuller, B.: Affect recognition in real-life acoustic conditions-a new perspective on feature selection. In: Proceedings INTERSPEECH 2013, 14th Annual Conference of the International Speech Communication Association, Lyon, France (2013)","DOI":"10.21437\/Interspeech.2013-484"},{"issue":"12","key":"22_CR18","first-page":"251","volume":"36","author":"SP Zhai","year":"2019","unstructured":"Zhai, S.P., Yang, Y.Y.: Bilingual text sentiment analysis based on attention mechanism Bi-LSTM. Comput. Appl. Softw. 36(12), 251\u2013255 (2019)","journal-title":"Comput. Appl. Softw."},{"key":"22_CR19","unstructured":"Bai, S., Kolter, J.Z., Koltun, V.: An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. arXiv preprint arXiv:1803.01271 (2018)"},{"key":"22_CR20","doi-asserted-by":"crossref","unstructured":"Lea, C., Flynn, M.D., Vidal, R., Reiter, A., Hager, G.D.: Temporal convolutional networks for action segmentation and detection, pp. 156\u2013165 (2017)","DOI":"10.1109\/CVPR.2017.113"},{"key":"22_CR21","doi-asserted-by":"crossref","unstructured":"Chao, Y.W., Vijayanarasimhan, S., Seybold, B., Ross, D.A., Deng, J., Sukthankar, R.: Rethinking the faster R-CNN architecture for temporal action localization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1130\u20131139 (2018)","DOI":"10.1109\/CVPR.2018.00124"},{"key":"22_CR22","doi-asserted-by":"crossref","unstructured":"Khorram, S., Aldeneh, Z., Dimitriadis, D., McInnis, M., Provost, E.M.: Capturing long-term temporal dependencies with convolutional networks for continuous emotion recognition. arXiv preprint arXiv:1708.07050 (2017)","DOI":"10.21437\/Interspeech.2017-548"}],"container-title":["Communications in Computer and Information Science","Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-0903-8_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,29]],"date-time":"2024-02-29T11:14:49Z","timestamp":1709205289000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-0903-8_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9789819709021","9789819709038"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-0903-8_22","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"1 March 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Applied Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Nanning","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 December 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 December 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icai12023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.icai.org.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}