{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T19:20:41Z","timestamp":1757618441459,"version":"3.44.0"},"publisher-location":"Singapore","reference-count":27,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819681792"},{"type":"electronic","value":"9789819681808"}],"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\/978-981-96-8180-8_9","type":"book-chapter","created":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T09:16:21Z","timestamp":1750324581000},"page":"105-116","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["QSMT: Query-Shared Multimodal Transformer for\u00a0Multimodal Sentiment Analysis"],"prefix":"10.1007","author":[{"given":"Huazhong","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuanhan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jihong","family":"Ding","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenxuan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,6,20]]},"reference":[{"key":"9_CR1","doi-asserted-by":"publisher","first-page":"306","DOI":"10.1016\/j.inffus.2023.02.028","volume":"95","author":"L Zhu","year":"2023","unstructured":"Zhu, L., Zhu, Z., Zhang, C., Xu, Y., Kong, X.: Multimodal sentiment analysis based on fusion methods: a survey. Inf. Fusion 95, 306\u2013325 (2023)","journal-title":"Inf. Fusion"},{"key":"9_CR2","doi-asserted-by":"crossref","unstructured":"Williams, J., Kleinegesse, S., Comanescu, R., Radu, O.: Recognizing emotions in video using multimodal DNN feature fusion. In: Challenge-HML, pp.\u00a011\u201319 (2018)","DOI":"10.18653\/v1\/W18-3302"},{"key":"9_CR3","doi-asserted-by":"crossref","unstructured":"Poria, S., Cambria, E., Hazarika, D., Mazumder, N., Zadeh, A., Morency, L.-P.: Multi-level multiple attentions for contextual multimodal sentiment analysis. In: ICDM, pp.\u00a01033\u20131038 (2017)","DOI":"10.1109\/ICDM.2017.134"},{"key":"9_CR4","doi-asserted-by":"crossref","unstructured":"Zadeh, A., Chen, M., Poria, S., Cambria, E., Morency, L.-P.: Tensor fusion network for multimodal sentiment analysis. In: EMNLP, pp.\u00a01103\u20131114 (2017)","DOI":"10.18653\/v1\/D17-1115"},{"key":"9_CR5","doi-asserted-by":"crossref","unstructured":"Liu, Z., Shen, Y.: Efficient low-rank multimodal fusion with modality-specific factors. In: ACL, pp.\u00a02247\u20132256 (2018)","DOI":"10.18653\/v1\/P18-1209"},{"key":"9_CR6","doi-asserted-by":"crossref","unstructured":"Mai, S., Hu, H., Xing, S.: Divide, conquer and combine: hierarchical feature fusion network with local and global perspectives for multimodal affective computing. In: ACL, pp.\u00a0481\u2013492 (2019)","DOI":"10.18653\/v1\/P19-1046"},{"key":"9_CR7","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: ACL, pp.\u00a06558\u20136569 (2019)","DOI":"10.18653\/v1\/P19-1656"},{"key":"9_CR8","doi-asserted-by":"crossref","unstructured":"Zhang, H., Wang, Y., Yin, G., Liu, K., Liu, Y., Yu, T.: Learning language-guided adaptive hyper-modality representation for multimodal sentiment analysis. In: EMNLP, pp.\u00a0756\u2013767 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.49"},{"key":"9_CR9","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: AAAI, pp.\u00a010790\u201310797 (2021)","DOI":"10.1609\/aaai.v35i12.17289"},{"key":"9_CR10","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.109259","volume":"136","author":"D Wang","year":"2023","unstructured":"Wang, D., Guo, X., Tian, Y., Liu, J., He, L., Luo, X.: TETFN: a text enhanced transformer fusion network for multimodal sentiment analysis. Pattern Recognit. 136, 109259 (2023)","journal-title":"Pattern Recognit."},{"key":"9_CR11","doi-asserted-by":"crossref","unstructured":"Hwang, Y., Kim, J.-H.: Self-supervised unimodal label generation strategy using recalibrated modality representations for multimodal sentiment analysis. In: EACL, pp.\u00a035\u201346 (2023)","DOI":"10.18653\/v1\/2023.findings-eacl.2"},{"key":"9_CR12","doi-asserted-by":"publisher","first-page":"424","DOI":"10.1016\/j.inffus.2022.09.025","volume":"91","author":"A Gandhi","year":"2023","unstructured":"Gandhi, A., Adhvaryu, K., Poria, S., Cambria, E., Hussain, A.: Multimodal sentiment analysis: a systematic review of history, datasets, multimodal fusion methods, applications, challenges and future directions. Inf. Fusion 91, 424\u2013444 (2023)","journal-title":"Inf. Fusion"},{"key":"9_CR13","doi-asserted-by":"crossref","unstructured":"Poria, S., Cambria, E., Gelbukh, A.: Deep convolutional neural network textual features and multiple kernel learning for utterance-level multimodal sentiment analysis. In: EMNLP, pp.\u00a02539\u20132544 (2015)","DOI":"10.18653\/v1\/D15-1303"},{"key":"9_CR14","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: AAAI, pp.\u00a05634\u20135641 (2018)","DOI":"10.1609\/aaai.v32i1.12021"},{"key":"9_CR15","doi-asserted-by":"crossref","unstructured":"Wang, H., Meghawat, A., Morency, L.P., Xing, E.P.: Select-additive learning: improving generalization in multimodal sentiment analysis. In: ICME, pp.\u00a0949\u2013954 (2017)","DOI":"10.1109\/ICME.2017.8019301"},{"key":"9_CR16","doi-asserted-by":"crossref","unstructured":"Liang, P.P., Liu, Z., Tsai, Y.H.H., Zhao, Q., Salakhutdinov, R., Morency, L.: Learning representations from imperfect time series data via tensor rank regularization. In: ACL, pp.\u00a02236\u20132246 (2019)","DOI":"10.18653\/v1\/P19-1152"},{"key":"9_CR17","doi-asserted-by":"crossref","unstructured":"Rahman, W., et al.: Integrating multimodal information in large pretrained transformers. In: ACL, pp.\u00a02359\u20132369 (2020)","DOI":"10.18653\/v1\/2020.acl-main.214"},{"key":"9_CR18","doi-asserted-by":"crossref","unstructured":"Guo, J., Tang, J., Dai, W., Ding, Y., Kong, W.: Dynamically adjust word representations using unaligned multimodal information. In: ACM MM, pp.\u00a03394\u20133402 (2022)","DOI":"10.1145\/3503161.3548137"},{"key":"9_CR19","doi-asserted-by":"crossref","unstructured":"Cheng, J., Fostiropoulos, I., Boehm, B., Soleymani, M.: Multimodal phased transformer for sentiment analysis. In: EMNLP, pp.\u00a02447\u20132458 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.189"},{"key":"9_CR20","doi-asserted-by":"crossref","unstructured":"Hazarika, D., Zimmermann, R., Poria, S.: MISA: modality-invariant and-specific representations for multimodal sentiment analysis. In: ACM MM, pp.\u00a01122\u20131131 (2020)","DOI":"10.1145\/3394171.3413678"},{"key":"9_CR21","unstructured":"Devlin, J., Chang, M.-W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: NAACL-HLT, pp.\u00a04171\u20134186 (2019)"},{"key":"9_CR22","doi-asserted-by":"crossref","unstructured":"McFee, B., et al.: librosa: audio and music signal analysis in python. In: SciPy, pp.\u00a018\u201324 (2015)","DOI":"10.25080\/Majora-7b98e3ed-003"},{"key":"9_CR23","doi-asserted-by":"crossref","unstructured":"Baltru\u0161aitis, T., Robinson, P., Morency, L.-P.: Openface: an open source facial behavior analysis toolkit. In: WACV, pp.\u00a01\u201310 (2016)","DOI":"10.1109\/WACV.2016.7477553"},{"key":"9_CR24","unstructured":"Graves, A.: Long short-term memory. In: NeurIPS, pp.\u00a01\u20138 (2009)"},{"key":"9_CR25","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NeurIPS, pp.\u00a05998\u20136008 (2017)"},{"key":"9_CR26","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, 82\u201388 (2016)","journal-title":"IEEE Intell. Syst."},{"key":"9_CR27","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: ACL, pp.\u00a02236\u20132246 (2018)"}],"container-title":["Lecture Notes in Computer Science","Advances in Knowledge Discovery and Data Mining"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-8180-8_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T20:47:49Z","timestamp":1757191669000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-8180-8_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819681792","9789819681808"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-8180-8_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"20 June 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PAKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific-Asia Conference on Knowledge Discovery and Data Mining","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sydney, NSW","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australia","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":"10 June 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 June 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pakdd2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/pakdd2025.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}