{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,6]],"date-time":"2025-08-06T12:58:25Z","timestamp":1754485105601,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":45,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819981809"},{"type":"electronic","value":"9789819981816"}],"license":[{"start":{"date-parts":[[2023,11,27]],"date-time":"2023-11-27T00:00:00Z","timestamp":1701043200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,11,27]],"date-time":"2023-11-27T00:00:00Z","timestamp":1701043200000},"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\/978-981-99-8181-6_21","type":"book-chapter","created":{"date-parts":[[2023,11,26]],"date-time":"2023-11-26T23:02:30Z","timestamp":1701039750000},"page":"270-281","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["PMFNet: A Progressive Multichannel Fusion Network for Multimodal Sentiment Analysis"],"prefix":"10.1007","author":[{"given":"Jiaming","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chuanqi","family":"Tao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Donghai","family":"Guan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,11,27]]},"reference":[{"key":"21_CR1","doi-asserted-by":"crossref","unstructured":"Morency, L.P., Mihalcea, R., Doshi, P.: Towards multimodal sentiment analysis: harvesting opinions from the web. In: Proceedings of the 13th International Conference on Multimodal Interfaces, pp. 169\u2013176 (2011)","DOI":"10.1145\/2070481.2070509"},{"key":"21_CR2","doi-asserted-by":"crossref","unstructured":"Hazarika, D., Zimmermann, R., Poria, S.: MISA: modality-invariant and \u2013specific 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":"21_CR3","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. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 10790\u201310797 (2021)","DOI":"10.1609\/aaai.v35i12.17289"},{"key":"21_CR4","doi-asserted-by":"crossref","unstructured":"Lin, R., Hu, H.: Multimodal contrastive learning via uni-Modal coding and cross-Modal prediction for multimodal sentiment analysis. In: Findings of the Association for Computational Linguistics, EMNLP 2022, pp. 511\u2013523 (2022)","DOI":"10.18653\/v1\/2022.findings-emnlp.36"},{"key":"21_CR5","unstructured":"Devlin, J., Chang, M., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, vol. 1, pp. 4171\u20134186 (2019)"},{"key":"21_CR6","doi-asserted-by":"crossref","unstructured":"Degottex, G., Kane, J., Drugman, T., Raitio, T., Scherer, S.: COVAREP \u2013 a collaborative voice analysis repository for speech technologies. In: 2014 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 960\u2013964 (2014)","DOI":"10.1109\/ICASSP.2014.6853739"},{"key":"21_CR7","unstructured":"Facial expression analysis. https:\/\/imotions.com\/"},{"key":"21_CR8","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1038\/35044552","volume":"1","author":"J Magee","year":"2000","unstructured":"Magee, J.: Dendritic integration of excitatory synaptic input. Nat. Rev. Neurosci. 1, 181\u2013190 (2000)","journal-title":"Nat. Rev. Neurosci."},{"issue":"4","key":"21_CR9","doi-asserted-by":"publisher","first-page":"494","DOI":"10.1016\/j.conb.2010.07.009","volume":"20","author":"T Branco","year":"2010","unstructured":"Branco, T., H\u00e4usser, M.: The single dendritic branch as a fundamental functional unit in the nervous system. Curr. Opin. Neurobiol. 20(4), 494\u2013502 (2010)","journal-title":"Curr. Opin. Neurobiol."},{"key":"21_CR10","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, vol. 30, pp. 6000\u20136010 (2017)"},{"key":"21_CR11","unstructured":"Nagrani, A., Yang, S., Arnab, A., Jansen, A., Schmid, C., Sun, C.: Attention bottlenecks for multimodal fusion. In: Advances in Neural Information Processing Systems, vol. 34, pp. 14200\u201314213 (2021)"},{"key":"21_CR12","doi-asserted-by":"crossref","unstructured":"Han, W., Chen, H., Gelbukh, A., Zadeh, A., Morency, L.P., Poria, S.: Bi-bimodal modality fusion for correlation-controlled multimodal sentiment analysis. In: Proceedings of the 2021 International Conference on Multimodal Interaction, pp. 6\u201315 (2021)","DOI":"10.1145\/3462244.3479919"},{"key":"21_CR13","doi-asserted-by":"publisher","first-page":"961","DOI":"10.1038\/nn1305","volume":"7","author":"S Williams","year":"2004","unstructured":"Williams, S.: Spatial compartmentalization and functional impact of conductance in pyramidal neurons. Nat. Neurosci. 7, 961\u2013967 (2004)","journal-title":"Nat. Neurosci."},{"key":"21_CR14","doi-asserted-by":"publisher","first-page":"2101","DOI":"10.1038\/s41467-020-15867-9","volume":"11","author":"Y Ran","year":"2020","unstructured":"Ran, Y., Huang, Z., Baden, T., et al.: Type-specific dendritic integration in mouse retinal ganglion cells. Nat. Commun. 11, 2101 (2020)","journal-title":"Nat. Commun."},{"issue":"12","key":"21_CR15","doi-asserted-by":"publisher","first-page":"e1004014","DOI":"10.1371\/journal.pcbi.1004014","volume":"10","author":"S Li","year":"2014","unstructured":"Li, S., Liu, N., Zhang, X., Zhou, D., Cai, D.: Bilinearity in spatiotemporal integration of synaptic inputs. PLoS Comput. Biol. 10(12), e1004014 (2014)","journal-title":"PLoS Comput. Biol."},{"key":"21_CR16","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. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 5634\u20135641 (2018)","DOI":"10.1609\/aaai.v32i1.12021"},{"key":"21_CR17","doi-asserted-by":"crossref","unstructured":"Zadeh, A., Chen, M., Poria, S., Cambria, E., Morency, L.P.: Tensor fusion network for multimodal sentiment analysis. In: Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pp. 1103\u20131114 (2017)","DOI":"10.18653\/v1\/D17-1115"},{"key":"21_CR18","doi-asserted-by":"crossref","unstructured":"Tsai, Y.H., Bai, S., Liang, P.P., Kolter, J.Z., Morency, L.P., Salakhutdinov, R.: Multimodal transformer for unaligned multimodal language sequences. In: Conference of the Association for Computational Linguistics, vol. 1, pp. 6558\u20136569 (2019)","DOI":"10.18653\/v1\/P19-1656"},{"key":"21_CR19","doi-asserted-by":"crossref","unstructured":"Paraskevopoulos, G., Georgiou, E., Potamianos, A.: MMLatch: bottom-up top-down fusion for multimodal sentiment analysis. In: IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 4573\u20134577 (2022)","DOI":"10.1109\/ICASSP43922.2022.9746418"},{"key":"21_CR20","doi-asserted-by":"crossref","unstructured":"Caglayan, O., Madhyastha, P.S., Specia, L., Barrault, L.: Probing the need for visual context in multimodal machine translation. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, vol. 1, pp.4159\u20134170 (2019)","DOI":"10.18653\/v1\/N19-1422"},{"key":"21_CR21","doi-asserted-by":"crossref","unstructured":"Paraskevopoulos, G., Parthasarathy, S., Khare, A., Sundaram, S.: Multimodal and multiresolution speech recognition with transformers. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 2381\u20132387 (2020)","DOI":"10.18653\/v1\/2020.acl-main.216"},{"key":"21_CR22","doi-asserted-by":"crossref","unstructured":"You, Q., Jin, H., Wang, Z., Fang, C., Luo, J.: Image captioning with semantic attention. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 4651\u20134659 (2016)","DOI":"10.1109\/CVPR.2016.503"},{"key":"21_CR23","doi-asserted-by":"crossref","unstructured":"Agrawal, A., Lu, J., Antol, S., Mitchell, M., et al.: VQA: visual question answering. In: IEEE International Conference on Computer Vision, pp. 2425\u20132433 (2015)","DOI":"10.1109\/ICCV.2015.279"},{"key":"21_CR24","doi-asserted-by":"crossref","unstructured":"Seo, P.H., Nagrani, A., Schmid, C.: Look before you speak: visually contextualized utterances. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16872\u201316882 (2021)","DOI":"10.1109\/CVPR46437.2021.01660"},{"key":"21_CR25","doi-asserted-by":"crossref","unstructured":"Ye, L., Rochan, M., Liu, Z., Wang, Y.: Cross-modal self-attention network for referring image segmentation. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10494\u201310503 (2019)","DOI":"10.1109\/CVPR.2019.01075"},{"key":"21_CR26","doi-asserted-by":"crossref","unstructured":"Sun, C., Myers, A., Vondrick, C., Murphy, K., Schmid, C.: VideoBERT: a joint model for video and language representation learning. In: IEEE\/CVF International Conference on Computer Vision, pp. 7463\u20137472 (2019)","DOI":"10.1109\/ICCV.2019.00756"},{"key":"21_CR27","doi-asserted-by":"crossref","unstructured":"Yuan, Z., Li, W., Xu, H., Yu, W.: Transformer-based feature reconstruction network for robust multimodal sentiment analysis. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 4400\u20134407 (2021)","DOI":"10.1145\/3474085.3475585"},{"key":"21_CR28","unstructured":"Tolstikhin, I.O., et al.: MLP-mixer: an all-MLP architecture for vision. In: Advances in Neural Information Processing Systems, vol. 34, pp. 24261\u201324272 (2021)"},{"issue":"4","key":"21_CR29","doi-asserted-by":"crossref","first-page":"5314","DOI":"10.1109\/TPAMI.2022.3206148","volume":"45","author":"H Touvron","year":"2021","unstructured":"Touvron, H., Bojanowski, P., Caron, M., Cord, M., El-Nouby, A., Grave, E., et al.: ResMLP: feedforward networks for image classification with data-efficient training. IEEE Trans. Pattern Anal. Mach. Intell. 45(4), 5314\u20135321 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"21_CR30","unstructured":"Liu, H., Dai, Z., So, D.R., Le, Q.V.: Pay attention to MLPs. In: Advances in Neural Information Processing Systems, vol. 34, pp. 9204\u20139215 (2021)"},{"key":"21_CR31","unstructured":"Chen, S., Xie, E., Ge, C., Liang, D., Luo, P.: CycleMLP: a MLP-like architecture for dense prediction. In: International Conference on Learning Representations (2022)"},{"key":"21_CR32","doi-asserted-by":"crossref","unstructured":"Guo, J., et al.: Hire-MLP: vision MLP via hierarchical rearrangement. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 816\u2013826 (2022)","DOI":"10.1109\/CVPR52688.2022.00090"},{"key":"21_CR33","unstructured":"Nie, Y., et al.: MLP architectures for vision-and-language modeling: an empirical study. arXiv preprint arXiv:2112.04453 (2021)"},{"key":"21_CR34","unstructured":"Oord, A.V., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)"},{"key":"21_CR35","unstructured":"Bromley, J., et al.: Signature verification using a \u201csiamese\u201d time delay neural network. In: Proceedings of the 6th International Conference on Neural Information Processing Systems, pp. 737\u2013744 (1993)"},{"issue":"6","key":"21_CR36","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":"21_CR37","unstructured":"Zadeh, A., 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, pp. 2236\u20132246 (2018)"},{"key":"21_CR38","doi-asserted-by":"crossref","unstructured":"Liu, Z., Shen, Y., Lakshminarasimhan, V. B., Liang, P.P., Zadeh, A., et al.: Efficient low-rank multimodal fusion with modality-specific factors. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, pp. 2247\u20132256 (2018)","DOI":"10.18653\/v1\/P18-1209"},{"key":"21_CR39","unstructured":"Tsai, Y.H., Liang, P.P., Zadeh, A., Morency, L.P., Salakhutdinov, R.: Learning factorized multimodal representations. In: International Conference on Learning Representations (2019)"},{"key":"21_CR40","doi-asserted-by":"crossref","unstructured":"Wang, Y., Shen, Y., Liu, Z., Liang, P.P., Zadeh, A., Morency, L.P.: Words can shift: dynamically adjusting word representations using nonverbal behaviors. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 7216\u20137223 (2019)","DOI":"10.1609\/aaai.v33i01.33017216"},{"key":"21_CR41","doi-asserted-by":"crossref","unstructured":"Pham, H., Liang, P.P., Manzini, T., Morency, L.P., et al.: Found in translation: learning robust joint representations by cyclic translations between modalities. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 6892\u20136899 (2019)","DOI":"10.1609\/aaai.v33i01.33016892"},{"key":"21_CR42","doi-asserted-by":"crossref","unstructured":"Sun, Z., Sarma, P.K., Sethares, W.A., et al.: Learning relationships between text, audio, and video via deep canonical correlation for multimodal language analysis. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 8992\u20138999 (2020)","DOI":"10.1609\/aaai.v34i05.6431"},{"key":"21_CR43","doi-asserted-by":"crossref","unstructured":"Lv, F., Chen, X., Huang, Y., Duan, L., Lin, G.: Progressive modality reinforcement for human multimodal emotion recognition from unaligned multi-modal sequences. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2554\u20132562 (2021)","DOI":"10.1109\/CVPR46437.2021.00258"},{"key":"21_CR44","doi-asserted-by":"crossref","unstructured":"Cheng, J., Fostiropoulos, I., Boehm, B.W., Soleymani, M.: Multimodal phased transformer for sentiment analysis. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp. 2447\u20132458 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.189"},{"key":"21_CR45","doi-asserted-by":"crossref","unstructured":"Wu, Y., Lin, Z., Zhao, Y., Qin, B., Zhu, L.: A text-centered shared-private framework via cross-modal prediction for multimodal sentiment analysis. In:\u00a0Findings of the Association for Computational Linguistics, ACL-IJCNLP 2021, pp. 4730\u20134738 (2021)","DOI":"10.18653\/v1\/2021.findings-acl.417"}],"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\/978-981-99-8181-6_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T10:57:19Z","timestamp":1730631439000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-8181-6_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,27]]},"ISBN":["9789819981809","9789819981816"],"references-count":45,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-8181-6_21","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2023,11,27]]},"assertion":[{"value":"27 November 2023","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":"Changsha","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":"20 November 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 November 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/iconip2023.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1274","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":"650","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":"51% - 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":"4.14","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":"2.46","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)"}}]}}