{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T22:05:54Z","timestamp":1789077954991,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032368454","type":"print"},{"value":"9783032368461","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\/978-3-032-36846-1_2","type":"book-chapter","created":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T21:05:51Z","timestamp":1789074351000},"page":"18-35","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["SpEmoC: A Balanced Speaker-Segment Multimodal Emotion Benchmark"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-3134-108X","authenticated-orcid":false,"given":"Sania","family":"Bano","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5962-2659","authenticated-orcid":false,"given":"Shahzad","family":"Ahmad","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5672-3537","authenticated-orcid":false,"given":"Santosh Kumar","family":"Vipparthi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9068-5845","authenticated-orcid":false,"given":"Sukalpa","family":"Chanda","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3384-4368","authenticated-orcid":false,"given":"Subrahmanyam","family":"Murala","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,11]]},"reference":[{"key":"2_CR1","doi-asserted-by":"crossref","unstructured":"Albanie, S., Nagrani, A., Vedaldi, A., Zisserman, A.: Emotion recognition in speech using cross-modal transfer in the wild. In: Proceedings of the 26th ACM International Conference on Multimedia, pp. 292\u2013301 (2018)","DOI":"10.1145\/3240508.3240578"},{"key":"2_CR2","unstructured":"Baevski, A., Zhou, Y., Mohamed, A., Auli, M.: Wav2Vec 2.0: a framework for self-supervised learning of speech representations. Adv. Neural. Inf. Process. Syst. 33, 12449\u201312460 (2020)"},{"key":"2_CR3","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1007\/s10579-008-9076-6","volume":"42","author":"C Busso","year":"2008","unstructured":"Busso, C., et al.: IEMOCAP: interactive emotional dyadic motion capture database. Lang. Resour. Eval. 42, 335\u2013359 (2008)","journal-title":"Lang. Resour. Eval."},{"key":"2_CR4","doi-asserted-by":"publisher","first-page":"110805","DOI":"10.52202\/079017-3518","volume":"37","author":"Z Cheng","year":"2024","unstructured":"Cheng, Z., et al.: Emotion-LLaMA: multimodal emotion recognition and reasoning with instruction tuning. Adv. Neural. Inf. Process. Syst. 37, 110805\u2013110853 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"3\u20134","key":"2_CR5","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1080\/02699939208411068","volume":"6","author":"P Ekman","year":"1992","unstructured":"Ekman, P.: An argument for basic emotions. Cognit. Emot. 6(3\u20134), 169\u2013200 (1992)","journal-title":"Cognit. Emot."},{"issue":"3","key":"2_CR6","doi-asserted-by":"publisher","first-page":"572","DOI":"10.1016\/j.patcog.2010.09.020","volume":"44","author":"M El Ayadi","year":"2011","unstructured":"El Ayadi, M., Kamel, M.S., Karray, F.: Survey on speech emotion recognition: features, classification schemes, and databases. Pattern Recogn. 44(3), 572\u2013587 (2011)","journal-title":"Pattern Recogn."},{"key":"2_CR7","doi-asserted-by":"crossref","unstructured":"Fang, Y., Huang, W., Wan, G., Su, K., Ye, M.: EMOE: modality-specific enhanced dynamic emotion experts. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 14314\u201314324 (2025)","DOI":"10.1109\/CVPR52734.2025.01335"},{"key":"2_CR8","doi-asserted-by":"crossref","unstructured":"Feng, S., et al.: EmoWOZ: a large-scale corpus and labelling scheme for emotion recognition in task-oriented dialogue systems. In: Proceedings of the Thirteenth Language Resources and Evaluation Conference, pp. 4096\u20134113 (2022)","DOI":"10.63317\/22qkb85u5ig2"},{"key":"2_CR9","unstructured":"FFmpeg Developers: FFMPeg. https:\/\/ffmpeg.org (2025). Accessed 29 June 2026"},{"key":"2_CR10","unstructured":"G\u00f3mez-Zaragoz\u00e1, L., del Amor, R., Castro-Bleda, M.J., Naranjo, V., Raya, M.A., Mar\u00edn-Morales, J.: EMOVOME: a dataset for emotion recognition in spontaneous real-life speech. arXiv preprint arXiv:2403.02167 (2024)"},{"key":"2_CR11","doi-asserted-by":"crossref","unstructured":"Hazarika, D., Zimmermann, R., Poria, S.: MISA: modality-invariant and-specific representations for multimodal sentiment analysis. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 1122\u20131131 (2020)","DOI":"10.1145\/3394171.3413678"},{"key":"2_CR12","doi-asserted-by":"crossref","unstructured":"Landis, J.R., Koch, G.G.: The measurement of observer agreement for categorical data. biometrics, pp. 159\u2013174 (1977)","DOI":"10.2307\/2529310"},{"key":"2_CR13","doi-asserted-by":"crossref","unstructured":"Lee, J., Kim, S., Kim, S., Park, J., Sohn, K.: Context-aware emotion recognition networks. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10143\u201310152 (2019)","DOI":"10.1109\/ICCV.2019.01024"},{"key":"2_CR14","doi-asserted-by":"crossref","unstructured":"Li, S., Deng, W., Du, J.: Reliable crowdsourcing and deep locality-preserving learning for expression recognition in the wild. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2852\u20132861 (2017)","DOI":"10.1109\/CVPR.2017.277"},{"key":"2_CR15","doi-asserted-by":"crossref","unstructured":"Livingstone, S.R., Russo, F.A.: The Ryerson audio-visual database of emotional speech and song (RAVDESS): a dynamic, multimodal set of facial and vocal expressions in North American English. PLoS ONE 13(5), e0196391 (2018)","DOI":"10.1371\/journal.pone.0196391"},{"key":"2_CR16","doi-asserted-by":"crossref","unstructured":"Lucey, P., Cohn, J.F., Prkachin, K.M., Solomon, P.E., Matthews, I.: Painful data: the UNBC-McMaster shoulder pain expression archive database. In: 2011 IEEE International Conference on Automatic Face & Gesture Recognition (FG), pp. 57\u201364 (2011)","DOI":"10.1109\/FG.2011.5771462"},{"key":"2_CR17","doi-asserted-by":"crossref","unstructured":"Nojavanasghari, B., Hughes, T., Morency, L.P.: EmoReact: a multimodal approach and dataset for recognizing emotional responses in children. In: Proceedings of the 18th ACM International Conference on Multimodal Interaction (ICMI), pp. 137\u2013144 (2016)","DOI":"10.1145\/2993148.2993168"},{"key":"2_CR18","unstructured":"Picard, R.W.: Affective Computing. MIT Press, Cambridge, MA (1997). https:\/\/direct.mit.edu\/books\/monograph\/4296\/Affective-Computing. Accessed 29 June 2026"},{"key":"2_CR19","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1016\/j.inffus.2017.02.003","volume":"37","author":"S Poria","year":"2017","unstructured":"Poria, S., Cambria, E., Bajpai, R., Hussain, A.: A review of affective computing: from unimodal analysis to multimodal fusion. Info. Fus. 37, 98\u2013125 (2017)","journal-title":"Info. Fus."},{"key":"2_CR20","doi-asserted-by":"crossref","unstructured":"Poria, S., Hazarika, D., Majumder, N., Naik, G., Cambria, E., Mihalcea, R.: MELD: a multimodal multi-party dataset for emotion recognition in conversations. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 527\u2013536 (2019)","DOI":"10.18653\/v1\/P19-1050"},{"key":"2_CR21","unstructured":"Radford, A., Kim, J.W., Xu, T., Brockman, G., McLeavey, C., Sutskever, I.: Robust speech recognition via large-scale weak supervision. In: International Conference on Machine Learning, pp. 28492\u201328518. PMLR (2023)"},{"key":"2_CR22","unstructured":"Sanh, V., Debut, L., Chaumond, J., Wolf, T.: DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter (2019). arXiv:1910.01108 arXiv preprint"},{"issue":"9\u201310","key":"2_CR23","doi-asserted-by":"publisher","first-page":"1062","DOI":"10.1016\/j.specom.2011.01.011","volume":"53","author":"B Schuller","year":"2011","unstructured":"Schuller, B., Batliner, A., Steidl, S., Seppi, D.: Recognising realistic emotions and affect in speech: state of the art and lessons learnt from the first challenge. Speech Commun. 53(9\u201310), 1062\u20131087 (2011)","journal-title":"Speech Commun."},{"key":"2_CR24","doi-asserted-by":"crossref","unstructured":"Sun, H., et al.: EmotionTalk: an interactive Chinese multimodal emotion dataset with rich annotations. In: Findings of the Association for Computational Linguistics: ACL 2026, pp. 9054\u20139071 (2026)","DOI":"10.18653\/v1\/2026.findings-acl.440"},{"key":"2_CR25","doi-asserted-by":"crossref","unstructured":"Tsai, Y.H.H., Bai, S., Liang, P.P., Kolter, J.Z., Morency, L.P., Salakhutdinov, R.: Multimodal transformer for unaligned multimodal language sequences. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 6558\u20136569 (2019)","DOI":"10.18653\/v1\/P19-1656"},{"key":"2_CR26","doi-asserted-by":"crossref","unstructured":"Varghese, R., Sambath, M.: YOLOv8: a novel object detection algorithm with enhanced performance and robustness. In: 2024 International Conference on Advances in Data Engineering and Intelligent Computing Systems (ADICS), pp. 1\u20136. IEEE (2024)","DOI":"10.1109\/ADICS58448.2024.10533619"},{"issue":"3","key":"2_CR27","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1109\/MIS.2013.34","volume":"28","author":"M W\u00f6llmer","year":"2013","unstructured":"W\u00f6llmer, M., et al.: YouTube Movie Reviews: sentiment analysis in an audio-visual context. IEEE Intell. Syst. 28(3), 46\u201353 (2013)","journal-title":"IEEE Intell. Syst."},{"key":"2_CR28","doi-asserted-by":"crossref","unstructured":"Zadeh, A.B., Liang, P.P., Poria, S., Cambria, E., Morency, L.P.: Multimodal language analysis in the wild: CMU-MOSEI dataset and interpretable dynamic fusion graph. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, (vol. 1: Long Papers), pp. 2236\u20132246 (2018)","DOI":"10.18653\/v1\/P18-1208"},{"key":"2_CR29","doi-asserted-by":"crossref","unstructured":"Zeng, J., Shan, S., Chen, X.: Facial expression recognition with inconsistently annotated datasets. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 222\u2013237 (2018)","DOI":"10.1007\/978-3-030-01261-8_14"},{"key":"2_CR30","doi-asserted-by":"crossref","unstructured":"Zhang, S., Pan, Y., Wang, J.Z.: Learning emotion representations from verbal and nonverbal communication. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18993\u201319004 (2023)","DOI":"10.1109\/CVPR52729.2023.01821"},{"key":"2_CR31","doi-asserted-by":"crossref","unstructured":"Zhao, J., ET AL.: M3ED: multi-modal multi-scene multi-label emotional dialogue database. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics, (vol. 1: Long Papers), pp. 5699\u20135710 (2022)","DOI":"10.18653\/v1\/2022.acl-long.391"},{"key":"2_CR32","doi-asserted-by":"crossref","unstructured":"Zhou, Q., et al.: Token-level contrastive learning with modality-aware prompting for multimodal intent recognition. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a038, pp. 17114\u201317122 (2024)","DOI":"10.1609\/aaai.v38i15.29656"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-36846-1_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T21:05:58Z","timestamp":1789074358000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-36846-1_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032368454","9783032368461"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-36846-1_2","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":"11 September 2026","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":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","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":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}