{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:56:28Z","timestamp":1778082988055,"version":"3.51.4"},"publisher-location":"Singapore","reference-count":23,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819703753","type":"print"},{"value":"9789819703760","type":"electronic"}],"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\/978-981-97-0376-0_16","type":"book-chapter","created":{"date-parts":[[2024,2,11]],"date-time":"2024-02-11T09:02:09Z","timestamp":1707642129000},"page":"211-220","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["An Investigation of\u00a0Video Vision Transformers for\u00a0Depression Severity Estimation from\u00a0Facial Video Data"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2557-7928","authenticated-orcid":false,"given":"Ghazal","family":"Bargshady","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2279-7041","authenticated-orcid":false,"given":"Roland","family":"Goecke","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,2,12]]},"reference":[{"issue":"1","key":"16_CR1","doi-asserted-by":"publisher","first-page":"262","DOI":"10.1109\/TAFFC.2018.2870884","volume":"12","author":"M Al Jazaery","year":"2018","unstructured":"Al Jazaery, M., Guo, G.: Video-based depression level analysis by encoding deep spatiotemporal features. IEEE Trans. Affect. Comput. 12(1), 262\u2013268 (2018)","journal-title":"IEEE Trans. Affect. Comput."},{"key":"16_CR2","doi-asserted-by":"crossref","unstructured":"Almaev, T.R., Valstar, M.F.: Local gabor binary patterns from three orthogonal planes for automatic facial expression recognition. In: 2013 Humaine Association Conference on Affective Computing and Intelligent Interaction, pp. 356\u2013361. IEEE (2013)","DOI":"10.1109\/ACII.2013.65"},{"key":"16_CR3","doi-asserted-by":"crossref","unstructured":"Arnab, A., Dehghani, M., Heigold, G., Sun, C., Lu\u010di\u0107, M., Schmid, C.: Vivit: a video vision transformer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6836\u20136846 (2021)","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"16_CR4","doi-asserted-by":"crossref","unstructured":"Bosch, A., Zisserman, A., Munoz, X.: Representing shape with a spatial pyramid kernel. In: Proceedings of the 6th ACM International Conference on Image and Video Retrieval, pp. 401\u2013408 (2007)","DOI":"10.1145\/1282280.1282340"},{"key":"16_CR5","doi-asserted-by":"crossref","unstructured":"Cummins, N., Joshi, J., Dhall, A., Sethu, V., Goecke, R., Epps, J.: Diagnosis of depression by behavioural signals: a multimodal approach. In: Proceedings of the 3rd ACM International Workshop on Audio\/Visual Emotion Challenge, pp. 11\u201320 (2013)","DOI":"10.1145\/2512530.2512535"},{"key":"16_CR6","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: Proceedings of the International Conference on Learning Representations (ICLR) (2021)"},{"key":"16_CR7","doi-asserted-by":"crossref","unstructured":"Du, Z., Li, W., Huang, D., Wang, Y.: Encoding visual behaviors with attentive temporal convolution for depression prediction. In: 2019 14th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2019), pp. 1\u20137. IEEE (2019)","DOI":"10.1109\/FG.2019.8756584"},{"key":"16_CR8","unstructured":"Fiorentini, G., Ertugrul, I.O., Salah, A.A.: Fully-attentive and interpretable: vision and video vision transformers for pain detection. arXiv preprint arXiv:2210.15769 (2022)"},{"key":"16_CR9","unstructured":"Haque, A., Guo, M., Miner, A.S., Fei-Fei, L.: Measuring depression symptom severity from spoken language and 3d facial expressions. arXiv preprint arXiv:1811.08592 (2018)"},{"issue":"3","key":"16_CR10","doi-asserted-by":"publisher","first-page":"668","DOI":"10.1109\/TCDS.2017.2721552","volume":"10","author":"A Jan","year":"2017","unstructured":"Jan, A., Meng, H., Gaus, Y.F.B.A., Zhang, F.: Artificial intelligent system for automatic depression level analysis through visual and vocal expressions. IEEE Trans. Cogn. Dev. Syst. 10(3), 668\u2013680 (2017)","journal-title":"IEEE Trans. Cogn. Dev. Syst."},{"key":"16_CR11","doi-asserted-by":"crossref","unstructured":"Laptev, I., Marszalek, M., Schmid, C., Rozenfeld, B.: Learning realistic human actions from movies. In: 2008 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1\u20138. IEEE (2008)","DOI":"10.1109\/CVPR.2008.4587756"},{"key":"16_CR12","doi-asserted-by":"crossref","unstructured":"Li, X., Guo, W., Yang, H.: Depression severity prediction from facial expression based on the drr_depressionnet network. In: 2020 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), pp. 2757\u20132764. IEEE (2020)","DOI":"10.1109\/BIBM49941.2020.9313597"},{"issue":"3","key":"16_CR13","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":"16_CR14","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"},{"issue":"12","key":"16_CR15","doi-asserted-by":"publisher","first-page":"1049","DOI":"10.1016\/j.patrec.2009.03.003","volume":"30","author":"H Meng","year":"2009","unstructured":"Meng, H., Pears, N.: Descriptive temporal template features for visual motion recognition. Pattern Recogn. Lett. 30(12), 1049\u20131058 (2009)","journal-title":"Pattern Recogn. Lett."},{"key":"16_CR16","doi-asserted-by":"crossref","unstructured":"Valstar, M., et al.: Avec 2014: 3d dimensional affect and depression recognition challenge. In: Proceedings of the 4th International Workshop on Audio\/Visual Emotion Challenge, pp. 3\u201310 (2014)","DOI":"10.1145\/2661806.2661807"},{"key":"16_CR17","doi-asserted-by":"crossref","unstructured":"Valstar, M., et al.: Avec 2013: the continuous audio\/visual emotion and depression recognition challenge. In: Proceedings of the 3rd ACM International Workshop on Audio\/Visual Emotion Challenge, pp. 3\u201310 (2013)","DOI":"10.1145\/2512530.2512533"},{"key":"16_CR18","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"issue":"7","key":"16_CR19","doi-asserted-by":"publisher","first-page":"1432","DOI":"10.1109\/TIFS.2015.2414392","volume":"10","author":"L Wen","year":"2015","unstructured":"Wen, L., Li, X., Guo, G., Zhu, Y.: Automated depression diagnosis based on facial dynamic analysis and sparse coding. IEEE Trans. Inf. Forensics Secur. 10(7), 1432\u20131441 (2015)","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"16_CR20","doi-asserted-by":"publisher","unstructured":"Ye, J., Fu, G., Liu, Y., Cheng, G., Wang, Q.: Dep-ViT: uncertainty suppression model based on facial expression recognition in depression patients. In: Pimenidis, E., Angelov, P., Jayne, C., Papaleonidas, A., Aydin, M. (eds.) Artificial Neural Networks and Machine Learning - ICANN 2022. ICANN 2022. LNCS, Part III, vol. 13531, pp. 113\u2013124 Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-15934-3_10","DOI":"10.1007\/978-3-031-15934-3_10"},{"key":"16_CR21","unstructured":"Yu, F., Koltun, V.: Multi-scale context aggregation by dilated convolutions. In: 2016 Proceedings of International Conference on Learning Representations, pp. 1\u201313 (2016)"},{"issue":"3","key":"16_CR22","doi-asserted-by":"publisher","first-page":"542","DOI":"10.1109\/TAFFC.2018.2828819","volume":"11","author":"X Zhou","year":"2018","unstructured":"Zhou, X., Jin, K., Shang, Y., Guo, G.: Visually interpretable representation learning for depression recognition from facial images. IEEE Trans. Affect. Comput. 11(3), 542\u2013552 (2018)","journal-title":"IEEE Trans. Affect. Comput."},{"issue":"4","key":"16_CR23","doi-asserted-by":"publisher","first-page":"578","DOI":"10.1109\/TAFFC.2017.2650899","volume":"9","author":"Y Zhu","year":"2017","unstructured":"Zhu, Y., Shang, Y., Shao, Z., Guo, G.: Automated depression diagnosis based on deep networks to encode facial appearance and dynamics. IEEE Trans. Affect. Comput. 9(4), 578\u2013584 (2017)","journal-title":"IEEE Trans. Affect. Comput."}],"container-title":["Lecture Notes in Computer Science","Image and Video Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-0376-0_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,11]],"date-time":"2024-02-11T09:04:30Z","timestamp":1707642270000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-0376-0_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9789819703753","9789819703760"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-0376-0_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"12 February 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PSIVT","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific-Rim Symposium on Image and Video Technology","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Auckland","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"New Zealand","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":"22 November 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 November 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"psivt2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/psivt2023.aut.ac.nz\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Easy Chair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"75","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"34","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"45% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}