{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T13:37:51Z","timestamp":1742996271945,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":27,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819985647"},{"type":"electronic","value":"9789819985654"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-981-99-8565-4_23","type":"book-chapter","created":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T06:03:13Z","timestamp":1701410593000},"page":"235-245","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["AVMFAC: Acoustic Visual Multi-scale Feature Aggregation Conformer for Multimodal Sentiment Analysis"],"prefix":"10.1007","author":[{"given":"Qiuyan","family":"Zheng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,12,2]]},"reference":[{"key":"23_CR1","doi-asserted-by":"crossref","unstructured":"Hazarika, D., Zimmermann, R., Poria, S.: MISA: modality-invariant and -specific representations for multimodal sentiment analysis. CoRR abs\/2005.03545 (2020). arXiv:2005.03545 https:\/\/arxiv.org\/abs\/2005.03545","DOI":"10.1145\/3394171.3413678"},{"key":"23_CR2","doi-asserted-by":"publisher","unstructured":"Li, X., Chen, M.: Multimodal sentiment analysis with multi-perspective fusion network focusing on sense attentive language. In: Sun, M., Li, S., Zhang, Y., Liu, Y., He, S., Rao, G. (eds.) Chinese Computational Linguistics. CCL 2020. LNCS, vol. 12522, pp. 359\u2013373. Springer, Cham. https:\/\/doi.org\/10.1007\/978-3-030-63031-7_26","DOI":"10.1007\/978-3-030-63031-7_26"},{"key":"23_CR3","unstructured":"Luo, H., Ji, L., Huang, Y., Wang, B., Ji, S., Li, T.: ScaleVLAD: improving multimodal sentiment analysis via multi-scale fusion of locally descriptors. arXiv preprint arXiv:2112.01368 (2021)"},{"key":"23_CR4","unstructured":"Shahin Amiriparian, S., et al.: On the impact of word error rate on acoustic-linguistic speech emotion recognition: an update for the deep learning era. arXiv preprint arXiv:2104.10121 (2021)"},{"key":"23_CR5","doi-asserted-by":"crossref","unstructured":"Wu, Y., et al.: Sentiment word aware multimodal refinement for multimodal sentiment analysis with ASR errors. arXiv preprint arXiv:2203.00257 (2022).","DOI":"10.18653\/v1\/2022.findings-acl.109"},{"key":"23_CR6","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, vol. 2019, pp. 6558\u20136569 (2019)","DOI":"10.18653\/v1\/P19-1656"},{"key":"23_CR7","doi-asserted-by":"crossref","unstructured":"Zadeh, A., Chen, M., Poria, S., Cambria, E., Morency, L.P.: Tensor fusion network for multimodal sentiment analysis. arXiv preprint arXiv:1707.07250 (2017)","DOI":"10.18653\/v1\/D17-1115"},{"key":"23_CR8","doi-asserted-by":"crossref","unstructured":"Zadeh, A., Liang, P.P., Mazumder, N., Poria, S., Cambria, E., Morency, L.P.: Memory fusion network for multi-view sequential learning. arXiv preprint arXiv:1802.00927 (2018)","DOI":"10.1609\/aaai.v32i1.12021"},{"key":"23_CR9","doi-asserted-by":"crossref","unstructured":"Williams, J., Kleinegesse, S., Comanescu, R., Radu, O.: Recognizing emotions in video using multimodal DNN feature fusion. In: Proceedings of Grand Challenge and Workshop on Human Multimodal Language (Challenge-HML). Association for Computational Linguistics, pp. 11\u201319 (2018)","DOI":"10.18653\/v1\/W18-3302"},{"key":"23_CR10","doi-asserted-by":"crossref","unstructured":"Liu, Z., Shen, Y., Lakshminarasimhan, V.B., Liang, P.P., Zadeh, A., Morency, L.-P.: Efficient low-rank multimodal fusion with modality-specific factors. arXiv preprint arXiv:1806.00064 (2018)","DOI":"10.18653\/v1\/P18-1209"},{"key":"23_CR11","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)"},{"key":"23_CR12","doi-asserted-by":"crossref","unstructured":"Rahman, W., et al.: Integrating multimodal information in large pretrained transformers. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 2359\u20132369 (2020)","DOI":"10.18653\/v1\/2020.acl-main.214"},{"key":"23_CR13","doi-asserted-by":"crossref","unstructured":"Liu, Y., Yuan, Z., Mao, H., et al.: Make acoustic and visual cues matter: CH-SIMS v2. 0 dataset and AV-Mixup consistent module. In: Proceedings of the 2022 International Conference on Multimodal Interaction, pp. 247\u2013258 (2022)","DOI":"10.1145\/3536221.3556630"},{"key":"23_CR14","doi-asserted-by":"crossref","unstructured":"Yu, W., Xu, H., Yuan, Z., Wu, J.: Learning modality-specific representations with self-supervised multi-task learning for multimodal sentiment analysis. arXiv preprint arXiv:2102.04830 (2021)","DOI":"10.1609\/aaai.v35i12.17289"},{"key":"23_CR15","first-page":"5036","volume":"2020","author":"A Gulati","year":"2020","unstructured":"Gulati, A., et al.: Conformer: convolution-augmented transformer for speech recognition. Proc. Interspeech 2020, 5036\u20135040 (2020)","journal-title":"Proc. Interspeech"},{"key":"23_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: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (2022)","DOI":"10.18653\/v1\/2022.acl-demo.20"},{"key":"23_CR17","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"23_CR18","doi-asserted-by":"crossref","unstructured":"Eyben, F., et al.: The Geneva minimalistic acoustic parameter set (GeMAPS) for voice research and affective computing. IEEE Trans. Affect, Comput. 7(2), 190\u2013202 (2015)","DOI":"10.1109\/TAFFC.2015.2457417"},{"key":"23_CR19","doi-asserted-by":"crossref","unstructured":"Eyben, F., W\u00f6llmer, M., Schuller, B.: OpenSMILE: the Munich versatile and fast open-source audio feature extractor. In: Proceedings of the 18th ACM International Conference on Multimedia, pp. 1459\u20131462 (2010)","DOI":"10.1145\/1873951.1874246"},{"key":"23_CR20","doi-asserted-by":"crossref","unstructured":"Dai, Z., Yang, Z., Yang, Y., Carbonell, J., Le, Q.V., Salakhutdinov, R.: Transformer-XL: attentive language models beyond a fixed-length context. arXiv preprint arXiv:1901.02860 (2019)","DOI":"10.18653\/v1\/P19-1285"},{"key":"23_CR21","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998\u20136008 (2017)"},{"key":"23_CR22","doi-asserted-by":"crossref","unstructured":"Okabe, K., Koshinaka, T., Shinoda, K.: Attentive statistics pooling for deep speaker embedding. arXiv preprint arXiv:1803.10963 (2018)","DOI":"10.21437\/Interspeech.2018-993"},{"key":"23_CR23","doi-asserted-by":"crossref","unstructured":"Koizumi, Y., et al.: DF-conformer: Integrated architecture of Conv-TasNet and conformer using linear complexity self-attention for speech enhancement. In: 2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), pp. 161\u2013165. IEEE (2021)","DOI":"10.1109\/WASPAA52581.2021.9632794"},{"key":"23_CR24","doi-asserted-by":"crossref","unstructured":"Chen, S., et al.: Continuous speech separation with conformer. In: ICASSP 2021\u20132021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5749\u20135753. IEEE (2021)","DOI":"10.1109\/ICASSP39728.2021.9413423"},{"key":"23_CR25","doi-asserted-by":"crossref","unstructured":"Peng, Z., Huang, W., Gu, S., et al.: Conformer: Local features coupling global representations for visual recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 367\u2013376 (2021)","DOI":"10.1109\/ICCV48922.2021.00042"},{"key":"23_CR26","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Lv, Z., Wu, H., et al.: MFA-conformer: multi-scale feature aggregation conformer for automatic speaker verification. arXiv preprint arXiv:2203.15249 (2022)","DOI":"10.21437\/Interspeech.2022-563"},{"key":"23_CR27","doi-asserted-by":"crossref","unstructured":"Yu, W., Xu, H., Meng, F., et al.: CH-SIMS: a Chinese multimodal sentiment analysis dataset with fine-grained annotation of modality. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 3718\u20133727 (2020)","DOI":"10.18653\/v1\/2020.acl-main.343"}],"container-title":["Lecture Notes in Computer Science","Biometric Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-8565-4_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,5]],"date-time":"2023-12-05T00:11:46Z","timestamp":1701735106000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-8565-4_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9789819985647","9789819985654"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-8565-4_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"2 December 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CCBR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Biometric Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Xuzhou","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":"1 December 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3 December 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccbr2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ccbr99.cn\/","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":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"79","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":"41","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":"52% - 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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}