{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T05:13:34Z","timestamp":1780636414546,"version":"3.54.1"},"publisher-location":"Cham","reference-count":34,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031915802","type":"print"},{"value":"9783031915819","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-91581-9_8","type":"book-chapter","created":{"date-parts":[[2025,5,27]],"date-time":"2025-05-27T11:22:34Z","timestamp":1748344954000},"page":"101-116","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["MVP: Multimodal Emotion Recognition Based on\u00a0Video and\u00a0Physiological Signals"],"prefix":"10.1007","author":[{"given":"Valeriya","family":"Strizhkova","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hadi","family":"Kachmar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hava","family":"Chaptoukaev","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Raphael","family":"Kalandadze","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Natia","family":"Kukhilava","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tatia","family":"Tsmindashvili","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nibras","family":"Abo-Alzahab","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maria A.","family":"Zuluaga","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michal","family":"Balazia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Antitza","family":"Dantcheva","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fran\u00e7ois","family":"Br\u00e9mond","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Laura M.","family":"Ferrari","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,5,12]]},"reference":[{"key":"8_CR1","unstructured":"Amos, B., Ludwiczuk, B., Satyanarayanan, M.: Openface: a general-purpose face recognition library with mobile applications. CMU School Comput. Sci. (2016)"},{"key":"8_CR2","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2022.103544","volume":"75","author":"S Bagherzadeh","year":"2022","unstructured":"Bagherzadeh, S., Maghooli, K., Shalbaf, A., Maghsoudi, A.: Recognition of emotional states using frequency effective connectivity maps through transfer learning approach from electroencephalogram signals. Biomed. Signal Process. Control 75, 103544 (2022)","journal-title":"Biomed. Signal Process. Control"},{"key":"8_CR3","doi-asserted-by":"crossref","unstructured":"Baltrusaitis, T., Zadeh, A., Lim, Y.C., Morency, L.P.: Openface 2.0: facial behavior analysis toolkit. In: 2018 13th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2018), pp. 59\u201366. IEEE (2018)","DOI":"10.1109\/FG.2018.00019"},{"key":"8_CR4","doi-asserted-by":"crossref","unstructured":"Cai, Z., et al.: Marlin: masked autoencoder for facial video representation learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2023)","DOI":"10.1109\/CVPR52729.2023.00150"},{"key":"8_CR5","unstructured":"Chaptoukaev, H., et al.: StressID: a multimodal dataset for stress identification. In: Thirty-seventh Conference on Neural Information Processing Systems Datasets and Benchmarks Track (2023). https:\/\/openreview.net\/forum?id=qWsQi9DGJb"},{"key":"8_CR6","doi-asserted-by":"crossref","unstructured":"Delbrouck, J.B., Tits, N., Brousmiche, M., Dupont, S.: A transformer-based joint-encoding for emotion recognition and sentiment analysis. In: Annual Meeting of the Association for Computational Linguistics (ACL) (2020)","DOI":"10.18653\/v1\/2020.challengehml-1.1"},{"key":"8_CR7","doi-asserted-by":"crossref","unstructured":"Ebrahimi\u00a0Kahou, S., Michalski, V., Konda, K., Memisevic, R., Pal, C.: Recurrent neural networks for emotion recognition in video. In: Proceedings of the 2015 ACM on International Conference on Multimodal Interaction, pp. 467\u2013474 (2015)","DOI":"10.1145\/2818346.2830596"},{"key":"8_CR8","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1016\/j.entcs.2019.04.009","volume":"343","author":"M Egger","year":"2019","unstructured":"Egger, M., Ley, M., Hanke, S.: Emotion recognition from physiological signal analysis: a review. Electron. Notes Theor. Comput. Sci. 343, 35\u201355 (2019)","journal-title":"Electron. Notes Theor. Comput. Sci."},{"key":"8_CR9","doi-asserted-by":"crossref","unstructured":"Ekman, P., Friesen, W.V.: Facial action coding system. Environ. Psychol. Nonverbal Behav. (1978)","DOI":"10.1037\/t27734-000"},{"key":"8_CR10","doi-asserted-by":"publisher","unstructured":"Elalamy, R., Fanourakis, M., Chanel, G.: Multi-modal emotion recognition using recurrence plots and transfer learning on physiological signals. In: 2021 9th International Conference on Affective Computing and Intelligent Interaction (ACII), pp.\u00a01\u20137 (2021). https:\/\/doi.org\/10.1109\/ACII52823.2021.9597442","DOI":"10.1109\/ACII52823.2021.9597442"},{"key":"8_CR11","doi-asserted-by":"crossref","unstructured":"Han, W., Chen, H., Gelbukh, A., Zadeh, A., Philippe Morency, L., Poria, S.: Bi-bimodal modality fusion for correlation-controlled multimodal sentiment analysis. In: ACM International Conference on Multimodal Interaction (ICMI) (2021)","DOI":"10.1145\/3462244.3479919"},{"key":"8_CR12","doi-asserted-by":"crossref","unstructured":"Jerritta, S., Murugappan, M., Nagarajan, R., Wan, K.: Physiological signals based human emotion recognition: a review. In: 2011 IEEE 7th International Colloquium on Signal Processing and its Applications, pp. 410\u2013415. IEEE (2011)","DOI":"10.1109\/CSPA.2011.5759912"},{"key":"8_CR13","doi-asserted-by":"crossref","unstructured":"Jia, Z., Lin, Y., Wang, J., Feng, Z., Xie, X., Chen, C.: Hetemotionnet: two-stream heterogeneous graph recurrent neural network for multi-modal emotion recognition. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 1047\u20131056 (2021)","DOI":"10.1145\/3474085.3475583"},{"issue":"3","key":"8_CR14","doi-asserted-by":"publisher","first-page":"235","DOI":"10.30773\/pi.2017.08.17","volume":"15","author":"HG Kim","year":"2018","unstructured":"Kim, H.G., Cheon, E.J., Bai, D.S., Lee, Y.H., Koo, B.H.: Stress and heart rate variability: a meta-analysis and review of the literature. Psychiatry Investig. 15(3), 235 (2018)","journal-title":"Psychiatry Investig."},{"issue":"1","key":"8_CR15","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1109\/T-AFFC.2011.15","volume":"3","author":"S Koelstra","year":"2011","unstructured":"Koelstra, S., et al.: DEAP: a database for emotion analysis; using physiological signals. IEEE Trans. Affect. Comput. 3(1), 18\u201331 (2011)","journal-title":"IEEE Trans. Affect. Comput."},{"key":"8_CR16","doi-asserted-by":"crossref","unstructured":"Mao, H., Yuan, Z., Xu, H., Yu, W., Liu, Y., Gao, K.: M-SENA: an integrated platform for multimodal sentiment analysis. In: Annual Meeting of the Association for Computational Linguistics System Demonstration Track (ACL) (2022)","DOI":"10.18653\/v1\/2022.acl-demo.20"},{"key":"8_CR17","unstructured":"Miranda-Correa, J.A., Abadi, M.K., Sebe, N., Patras, I.: Amigos: a dataset for affect, personality and mood research on individuals and groups. IEEE Trans. Affect. Comput. (2017)"},{"issue":"8","key":"8_CR18","doi-asserted-by":"publisher","first-page":"9320","DOI":"10.1007\/s11227-022-05026-w","volume":"79","author":"A Moin","year":"2023","unstructured":"Moin, A., Aadil, F., Ali, Z., Kang, D.: Emotion recognition framework using multiple modalities for an effective human-computer interaction. J. Supercomput. 79(8), 9320\u20139349 (2023)","journal-title":"J. Supercomput."},{"key":"8_CR19","doi-asserted-by":"crossref","unstructured":"Perveen, N., Mohan, C.K.: Configural representation of facial action units for spontaneous facial expression recognition in the wild. In: VISIGRAPP (4: VISAPP), pp. 93\u2013102 (2020)","DOI":"10.5220\/0009099700930102"},{"key":"8_CR20","doi-asserted-by":"publisher","unstructured":"Ross, K., Hungler, P., Etemad, A.: Unsupervised multi-modal representation learning for affective computing with multi-corpus wearable data. J. Ambient. Intell. Humaniz. Comput. 1\u201326 (2021). https:\/\/doi.org\/10.1007\/s12652-021-03462-9","DOI":"10.1007\/s12652-021-03462-9"},{"issue":"6","key":"8_CR21","doi-asserted-by":"publisher","first-page":"1161","DOI":"10.1037\/h0077714","volume":"39","author":"JA Russell","year":"1980","unstructured":"Russell, J.A.: A circumplex model of affect. J. Pers. Soc. Psychol. 39(6), 1161 (1980)","journal-title":"J. Pers. Soc. Psychol."},{"key":"8_CR22","doi-asserted-by":"crossref","unstructured":"S\u00e1nchez-Reolid, R., L\u00f3pez, M.T., Fern\u00e1ndez-Caballero, A.: Machine learning for stress detection from electrodermal activity: A scoping review. Preprints (2020)","DOI":"10.20944\/preprints202011.0043.v1"},{"issue":"7","key":"8_CR23","doi-asserted-by":"publisher","first-page":"2074","DOI":"10.3390\/s18072074","volume":"18","author":"L Shu","year":"2018","unstructured":"Shu, L., et al.: A review of emotion recognition using physiological signals. Sensors 18(7), 2074 (2018)","journal-title":"Sensors"},{"issue":"1","key":"8_CR24","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1109\/TAFFC.2019.2916015","volume":"13","author":"S Siddharth","year":"2019","unstructured":"Siddharth, S., Jung, T.P., Sejnowski, T.J.: Utilizing deep learning towards multi-modal bio-sensing and vision-based affective computing. IEEE Trans. Affect. Comput. 13(1), 96\u2013107 (2019)","journal-title":"IEEE Trans. Affect. Comput."},{"key":"8_CR25","doi-asserted-by":"crossref","unstructured":"Strizhkova, V., Ferrari, L., Kachmar, H., Dantcheva, A., Bremond, F.: Video representation learning for conversational facial expression recognition guided by multiple angles reconstruction. In: IEEE Conference on Computer Vision and Pattern Recognition Workshop (CVPRW) (2024)","DOI":"10.1109\/CVPRW63382.2024.00472"},{"key":"8_CR26","doi-asserted-by":"crossref","unstructured":"Baltru\u0161aitis, T., Peter\u00a0Robinson, L.P.M.: Openface: an open source facial behavior analysis toolkit. In: 2016 IEEE Winter Conference on Applications of Computer Vision (WACV) (2016)","DOI":"10.1109\/WACV.2016.7477553"},{"key":"8_CR27","unstructured":"Tong, Z., Song, Y., Wang, J., Wang, L.: Videomae: masked autoencoders are data-efficient learners for self-supervised video pre-training. In: Advances in Neural Information Processing Systems (NeurIPS) (2022)"},{"issue":"9","key":"8_CR28","doi-asserted-by":"publisher","first-page":"3248","DOI":"10.3390\/s22093248","volume":"22","author":"A Topic","year":"2022","unstructured":"Topic, A., Russo, M., Stella, M., Saric, M.: Emotion recognition using a reduced set of EEG channels based on holographic feature maps. Sensors 22(9), 3248 (2022)","journal-title":"Sensors"},{"key":"8_CR29","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems (NeurIPS) (2017)"},{"key":"8_CR30","doi-asserted-by":"crossref","unstructured":"Vazquez-Rodriguez, J., Lefebvre, G., Cumin, J., Crowley, J.L.: Emotion recognition with pre-trained transformers using multimodal signals. In: 2022 10th International Conference on Affective Computing and Intelligent Interaction (ACII), pp.\u00a01\u20138. IEEE (2022)","DOI":"10.1109\/ACII55700.2022.9953852"},{"key":"8_CR31","doi-asserted-by":"crossref","unstructured":"Vazquez-Rodriguez, J., Lefebvre, G., Cumin, J., Crowley, J.L.: Transformer-based self-supervised learning for emotion recognition. In: International Conference on Pattern Recognition (ICPR) (2022)","DOI":"10.1109\/ICPR56361.2022.9956027"},{"key":"8_CR32","doi-asserted-by":"crossref","unstructured":"Wang, L., et al.: Videomae v2: scaling video masked autoencoders with dual masking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2023)","DOI":"10.1109\/CVPR52729.2023.01398"},{"key":"8_CR33","doi-asserted-by":"crossref","unstructured":"Zhang, T., et al.: Multi-task learning framework for emotion recognition in-the-wild. In: European Conference on Computer Vision Workshop (ECCVW) (2022)","DOI":"10.1007\/978-3-031-25075-0_11"},{"key":"8_CR34","doi-asserted-by":"crossref","unstructured":"Zhang, W., et al.: Transformer-based multimodal information fusion for facial expression analysis. In: IEEE Conference on Computer Vision and Pattern Recognition Workshop (CVPRW) (2022)","DOI":"10.1109\/CVPRW56347.2022.00271"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-91581-9_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T16:08:24Z","timestamp":1757174904000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-91581-9_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031915802","9783031915819"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-91581-9_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"12 May 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}