{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,22]],"date-time":"2026-08-22T13:22:32Z","timestamp":1787404952426,"version":"build-2736575974"},"publisher-location":"Singapore","reference-count":35,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819540907","type":"print"},{"value":"9789819540914","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,11,9]],"date-time":"2025-11-09T00:00:00Z","timestamp":1762646400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,9]],"date-time":"2025-11-09T00:00:00Z","timestamp":1762646400000},"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\/978-981-95-4091-4_6","type":"book-chapter","created":{"date-parts":[[2025,11,8]],"date-time":"2025-11-08T20:08:04Z","timestamp":1762632484000},"page":"80-93","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["MKDF: Knowledge Distillation Based Lightweight Multimodal Framework for\u00a0Emotion Recognition"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-2234-8799","authenticated-orcid":false,"given":"Yiwen","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-0200-2309","authenticated-orcid":false,"given":"Yujian","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-0582-9078","authenticated-orcid":false,"given":"Bingtian","family":"Qiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3687-117X","authenticated-orcid":false,"given":"Cheng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-5704-7817","authenticated-orcid":false,"given":"Zeyu","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3764-4622","authenticated-orcid":false,"given":"Shanliang","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,11,9]]},"reference":[{"key":"6_CR1","doi-asserted-by":"crossref","unstructured":"Aslam, M.H., Zeeshan, M.O., Pedersoli, M., Koerich, A.L., Bacon, S., Granger, E.: Privileged knowledge distillation for dimensional emotion recognition in the wild. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3338\u20133347 (2023)","DOI":"10.1109\/CVPRW59228.2023.00336"},{"key":"6_CR2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.126236","volume":"270","author":"E Boitel","year":"2025","unstructured":"Boitel, E., Mohasseb, A., Haig, E.: Mist: multimodal emotion recognition using deberta for text, semi-cnn for speech, resnet-50 for facial, and 3d-cnn for motion analysis. Expert Syst. Appl. 270, 126236 (2025)","journal-title":"Expert Syst. Appl."},{"key":"6_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. Res. Eval. 42, 335\u2013359 (2008)","journal-title":"Lang. Res. Eval."},{"key":"6_CR4","doi-asserted-by":"crossref","unstructured":"Chen, F., Shao, J., Zhu, S., Shen, H.T.: Multivariate, multi-frequency and multimodal: rethinking graph neural networks for emotion recognition in conversation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10761\u201310770 (2023)","DOI":"10.1109\/CVPR52729.2023.01036"},{"key":"6_CR5","doi-asserted-by":"crossref","unstructured":"Cui, L., Yang, S.: Enhancing multimodal sentiment recognition based on cross-modal contrastive learning. In: 2024 IEEE International Conference on Multimedia and Expo (ICME), pp.\u00a01\u20136. IEEE (2024)","DOI":"10.1109\/ICME57554.2024.10688113"},{"key":"6_CR6","unstructured":"Dosovitskiy, A., et al.: An image is worth 16$$\\times $$16 words: transformers for image recognition at scale. In: International Conference on Learning Representations (2021)"},{"key":"6_CR7","doi-asserted-by":"crossref","unstructured":"Gong, Y., Lai, C.I., Chung, Y.A., Glass, J.: SSAST: self-supervised audio spectrogram transformer. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a036, pp. 10699\u201310709 (2022)","DOI":"10.1609\/aaai.v36i10.21315"},{"key":"6_CR8","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"6_CR9","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)"},{"key":"6_CR10","doi-asserted-by":"crossref","unstructured":"Howard, A., et\u00a0al.: Searching for mobilenetv3. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1314\u20131324 (2019)","DOI":"10.1109\/ICCV.2019.00140"},{"key":"6_CR11","doi-asserted-by":"crossref","unstructured":"Hu, D., Bao, Y., Wei, L., Zhou, W., Hu, S.: Supervised adversarial contrastive learning for emotion recognition in conversations. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics, vol. 1: Long Papers, pp. 10835\u201310852 (2023)","DOI":"10.18653\/v1\/2023.acl-long.606"},{"key":"6_CR12","doi-asserted-by":"crossref","unstructured":"Hu, D., Hou, X., Wei, L., Jiang, L., Mo, Y.: Mm-dfn: multimodal dynamic fusion network for emotion recognition in conversations. In: ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7037\u20137041. IEEE (2022)","DOI":"10.1109\/ICASSP43922.2022.9747397"},{"key":"6_CR13","doi-asserted-by":"crossref","unstructured":"Hu, D., Wei, L., Huai, X.: DialogueCRN: contextual reasoning networks for emotion recognition in conversations. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, vol. 1: Long Papers, pp. 7042\u20137052 (2021)","DOI":"10.18653\/v1\/2021.acl-long.547"},{"key":"6_CR14","doi-asserted-by":"crossref","unstructured":"Joshi, A., Bhat, A., Jain, A., Singh, A., Modi, A.: COGMEN: COntextualized GNN based multimodal emotion recognitioN. In: Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 4148\u20134164 (2022)","DOI":"10.18653\/v1\/2022.naacl-main.306"},{"key":"6_CR15","doi-asserted-by":"crossref","unstructured":"Li, B., et al.: Revisiting disentanglement and fusion on modality and context in conversational multimodal emotion recognition. In: Proceedings of the 31st ACM International Conference on Multimedia, pp. 5923\u20135934 (2023)","DOI":"10.1145\/3581783.3612053"},{"key":"6_CR16","doi-asserted-by":"crossref","unstructured":"Li, J., Yu, R., Huang, H., Yan, H.: Unimodal-driven distillation in multimodal emotion recognition with dynamic fusion. arXiv preprint arXiv:2503.23721 (2025)","DOI":"10.1109\/ICME59968.2025.11209909"},{"issue":"1","key":"6_CR17","doi-asserted-by":"publisher","first-page":"130","DOI":"10.1109\/TAFFC.2023.3261279","volume":"15","author":"J Li","year":"2023","unstructured":"Li, J., Wang, X., Lv, G., Zeng, Z.: Ga2mif: graph and attention based two-stage multi-source information fusion for conversational emotion detection. IEEE Trans. Affect. Comput. 15(1), 130\u2013143 (2023)","journal-title":"IEEE Trans. Affect. Comput."},{"key":"6_CR18","doi-asserted-by":"publisher","unstructured":"Li, J., Wang, X., Zeng, Z.: Tracing intricate cues in dialogue: joint graph structure and sentiment dynamics for multimodal emotion recognition. IEEE Trans. Pattern Anal. Mach. Intell. 1\u201318 (2025). https:\/\/doi.org\/10.1109\/TPAMI.2025.3581236","DOI":"10.1109\/TPAMI.2025.3581236"},{"key":"6_CR19","doi-asserted-by":"crossref","unstructured":"Li, J., Peng, J.: End-to-end multimodal emotion recognition based on facial expressions and remote photoplethysmography signals. IEEE J. Biomed. Health Inf. (2024)","DOI":"10.1109\/JBHI.2024.3430310"},{"key":"6_CR20","doi-asserted-by":"crossref","unstructured":"Li, Z., et al.: Curriculum temperature for knowledge distillation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a037, pp. 1504\u20131512 (2023)","DOI":"10.1609\/aaai.v37i2.25236"},{"key":"6_CR21","first-page":"1","volume":"73","author":"H Liu","year":"2024","unstructured":"Liu, H., et al.: EEG-based multimodal emotion recognition: a machine learning perspective. IEEE Trans. Inst. Meas. 73, 1\u201329 (2024)","journal-title":"IEEE Trans. Inst. Meas."},{"key":"6_CR22","doi-asserted-by":"crossref","unstructured":"Liu, Z., Mao, H., Wu, C.Y., Feichtenhofer, C., Darrell, T., Xie, S.: A convnet for the 2020s. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11976\u201311986 (2022)","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"6_CR23","doi-asserted-by":"crossref","unstructured":"Ma, H., Wang, J., Lin, H., Zhang, B., Zhang, Y., Xu, B.: A transformer-based model with self-distillation for multimodal emotion recognition in conversations. IEEE Trans. Multimedia (2023)","DOI":"10.1109\/TMM.2023.3271019"},{"key":"6_CR24","doi-asserted-by":"crossref","unstructured":"Ma, N., Zhang, X., Zheng, H.T., Sun, J.: Shufflenet v2: practical guidelines for efficient cnn architecture design. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 116\u2013131 (2018)","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"6_CR25","doi-asserted-by":"crossref","unstructured":"Pan, J., Fang, W., Zhang, Z., Chen, B., Zhang, Z., Wang, S.: Multimodal emotion recognition based on facial expressions, speech, and EEG. IEEE Open J. Eng. Med. Biol. (2023)","DOI":"10.1109\/OJEMB.2023.3240280"},{"key":"6_CR26","unstructured":"Shou, Y., Ai, W., Du, J., Meng, T., Liu, H., Yin, N.: Efficient long-distance latent relation-aware graph neural network for multi-modal emotion recognition in conversations. arXiv preprint arXiv:2407.00119 (2024)"},{"key":"6_CR27","unstructured":"Tan, M., Le, Q.: Efficientnet: rethinking model scaling for convolutional neural networks. In: International Conference on Machine Learning, pp. 6105\u20136114. PMLR (2019)"},{"issue":"8","key":"6_CR28","doi-asserted-by":"publisher","first-page":"1301","DOI":"10.1109\/JSTSP.2017.2764438","volume":"11","author":"P Tzirakis","year":"2017","unstructured":"Tzirakis, P., Trigeorgis, G., Nicolaou, M.A., Schuller, B.W., Zafeiriou, S.: End-to-end multimodal emotion recognition using deep neural networks. IEEE J. Sel. Topics Signal Process. 11(8), 1301\u20131309 (2017)","journal-title":"IEEE J. Sel. Topics Signal Process."},{"key":"6_CR29","unstructured":"Wadekar, S.N., Chaurasia, A.: Mobilevitv3: mobile-friendly vision transformer with simple and effective fusion of local, global and input features. arXiv preprint arXiv:2209.15159 (2022)"},{"key":"6_CR30","doi-asserted-by":"crossref","unstructured":"Wu, M., et al.: Multimodal emotion recognition based on EEG and EOG signals evoked by the video-odor stimuli. IEEE Trans. Neural Syst. Rehabil. Eng. (2024)","DOI":"10.1109\/TNSRE.2024.3457580"},{"issue":"22","key":"6_CR31","doi-asserted-by":"publisher","first-page":"35812","DOI":"10.1109\/JIOT.2024.3363176","volume":"11","author":"N Ying","year":"2024","unstructured":"Ying, N., Jiang, Y., Guo, C., Zhou, D., Zhao, J.: A multimodal driver emotion recognition algorithm based on the audio and video signals in internet of vehicles platform. IEEE Internet Things J. 11(22), 35812\u201335824 (2024)","journal-title":"IEEE Internet Things J."},{"issue":"6","key":"6_CR32","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1109\/MIS.2016.94","volume":"31","author":"A Zadeh","year":"2016","unstructured":"Zadeh, A., Zellers, R., Pincus, E., Morency, L.P.: Multimodal sentiment intensity analysis in videos: facial gestures and verbal messages. IEEE Intell. Syst. 31(6), 82\u201388 (2016)","journal-title":"IEEE Intell. Syst."},{"key":"6_CR33","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":"6_CR34","doi-asserted-by":"publisher","first-page":"3771","DOI":"10.1109\/TASLP.2023.3316458","volume":"31","author":"Z Zhao","year":"2023","unstructured":"Zhao, Z., Wang, Y., Shen, G., Xu, Y., Zhang, J.: Tdfnet: transformer-based deep-scale fusion network for multimodal emotion recognition. IEEE\/ACM Trans. Audio Speech Lang. Process. 31, 3771\u20133782 (2023)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"6_CR35","doi-asserted-by":"crossref","unstructured":"Zhu, C., Sun, C., Liu, Y., Chen, J., Luo, K.: Enhancing speech emotion recognition with speech dynamic modeling and multi-modal knowledge distillation. In: ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.\u00a01\u20135. IEEE (2025)","DOI":"10.1109\/ICASSP49660.2025.10889655"}],"container-title":["Communications in Computer and Information Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-4091-4_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,22]],"date-time":"2026-08-22T12:29:01Z","timestamp":1787401741000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-4091-4_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,9]]},"ISBN":["9789819540907","9789819540914"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-4091-4_6","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,9]]},"assertion":[{"value":"9 November 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Okinawa","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 November 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 November 2025","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":"iconip2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iconip2025.apnns.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}