{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T08:53:11Z","timestamp":1763196791229,"version":"3.45.0"},"publisher-location":"Singapore","reference-count":23,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819533480","type":"print"},{"value":"9789819533497","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,11,16]],"date-time":"2025-11-16T00:00:00Z","timestamp":1763251200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,16]],"date-time":"2025-11-16T00:00:00Z","timestamp":1763251200000},"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\/978-981-95-3349-7_30","type":"book-chapter","created":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T08:50:07Z","timestamp":1763196607000},"page":"389-402","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["DiGTF: A Difference-Guided Two-Stage Fusion Framework for\u00a0Multimodal Sentiment Analysis"],"prefix":"10.1007","author":[{"given":"Hui","family":"Liu","sequence":"first","affiliation":[]},{"given":"Minghua","family":"Nuo","sequence":"additional","affiliation":[]},{"given":"Rui","family":"Li","sequence":"additional","affiliation":[]},{"given":"Chengyi","family":"Zhou","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,11,16]]},"reference":[{"key":"30_CR1","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: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pp. 756\u2013767 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.49"},{"key":"30_CR2","doi-asserted-by":"crossref","unstructured":"Wu, S., Wang, X., Wang, L., He, D., Dang, J.: Enriching multimodal sentiment analysis through textual emotional descriptions of visual-audio content. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 1601\u20131609 (2025)","DOI":"10.1609\/aaai.v39i2.32152"},{"key":"30_CR3","doi-asserted-by":"crossref","unstructured":"Zhuang, Y., Zhang, Y., Hu, Z., Zhang, X., Deng, J., Ren, F.: GLoMo: global-local modal fusion for multimodal sentiment analysis. In: Proceedings of the 32nd ACM International Conference on Multimedia, pp. 1800\u20131809 (2024)","DOI":"10.1145\/3664647.3681527"},{"key":"30_CR4","doi-asserted-by":"crossref","unstructured":"Zhu, A., Hu, M., Wang, X., Yang, J., Tang, Y., Ren, F.: KEBR: knowledge enhanced self-supervised balanced representation for multimodal sentiment analysis. In: Proceedings of the 32nd ACM International Conference on Multimedia, pp. 5732\u20135741 (2024)","DOI":"10.1145\/3664647.3681163"},{"key":"30_CR5","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 Conference. Association for Computational Linguistics. Meeting, vol.\u00a02019, p.\u00a06558. NIH Public Access (2019)","DOI":"10.18653\/v1\/P19-1656"},{"key":"30_CR6","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":"30_CR7","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. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 2247\u20132256 (2018)","DOI":"10.18653\/v1\/P18-1209"},{"key":"30_CR8","doi-asserted-by":"crossref","unstructured":"Han, W., Chen, H., Poria, S.: Improving multimodal fusion with hierarchical mutual information maximization for multimodal sentiment analysis. In: Proceedings of EMNLP, pp. 9180\u20139192 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.723"},{"key":"30_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: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 10790\u201310797 (2021)","DOI":"10.1609\/aaai.v35i12.17289"},{"key":"30_CR10","doi-asserted-by":"crossref","unstructured":"Li, D., Wang, Y., Funakoshi, K., Okumura, M.: JOYFUL: joint modality fusion and graph contrastive learning for multimodal emotion recognition. In: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pp. 16051\u201316069 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.996"},{"key":"30_CR11","doi-asserted-by":"crossref","unstructured":"Li, M., et al.: Correlation-decoupled knowledge distillation for multimodal sentiment analysis with incomplete modalities. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12458\u201312468 (2024)","DOI":"10.1109\/CVPR52733.2024.01184"},{"key":"30_CR12","doi-asserted-by":"crossref","unstructured":"Yang, D., Huang, S., Kuang, H., Du, Y., Zhang, L.: Disentangled representation learning for multimodal emotion recognition. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 1642\u20131651 (2022)","DOI":"10.1145\/3503161.3547754"},{"key":"30_CR13","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":"30_CR14","doi-asserted-by":"crossref","unstructured":"Yang, J., Yu, Y., Niu, D., Guo, W., Xu, Y.: ConFEDE: contrastive feature decomposition for multimodal sentiment analysis. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 7617\u20137630 (2023)","DOI":"10.18653\/v1\/2023.acl-long.421"},{"key":"30_CR15","doi-asserted-by":"crossref","unstructured":"Wang, P., Zhou, Q., Wu, Y., Chen, T., Hu, J.: DLF: disentangled-language-focused multimodal sentiment analysis. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 21180\u201321188 (2025)","DOI":"10.1609\/aaai.v39i20.35416"},{"key":"30_CR16","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102663","volume":"114","author":"Y Zhou","year":"2025","unstructured":"Zhou, Y., Liang, X., Chen, H., Zhao, Y., Chen, X., Yu, L.: Triple disentangled representation learning for multimodal affective analysis. Inf. Fusion 114, 102663 (2025)","journal-title":"Inf. Fusion"},{"key":"30_CR17","doi-asserted-by":"crossref","unstructured":"Ma, X., et al.: STNet: spatial and temporal feature fusion network for change detection in remote sensing images. In: 2023 IEEE International Conference on Multimedia and Expo (ICME), pp. 2195\u20132200 (2023)","DOI":"10.1109\/ICME55011.2023.00375"},{"key":"30_CR18","doi-asserted-by":"crossref","unstructured":"Chen, G., et al.: CGMDRNet: cross-guided modality difference reduction network for RGB-T salient object detection. IEEE Trans. Circuits Syst. Video Technol., 6308\u20136323 (2022)","DOI":"10.1109\/TCSVT.2022.3166914"},{"key":"30_CR19","unstructured":"Zadeh, A., Zellers, R., Pincus, E., Morency, L.P.: MOSI: multimodal corpus of sentiment intensity and subjectivity analysis in online opinion videos. arXiv (2016). Computation and Language"},{"key":"30_CR20","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 (Volume 1: Long Papers), pp. 2236\u20132246 (2018)","DOI":"10.18653\/v1\/P18-1208"},{"key":"30_CR21","doi-asserted-by":"crossref","unstructured":"Yu, W., 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"},{"key":"30_CR22","doi-asserted-by":"crossref","unstructured":"Rahman, W., et al.: Integrating multimodal information in large pretrained transformers. In: Proceedings of the Conference. Association for Computational Linguistics. Meeting, vol.\u00a02020, p.\u00a02359. NIH Public Access (2020)","DOI":"10.18653\/v1\/2020.acl-main.214"},{"key":"30_CR23","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 multimodal sequences. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2554\u20132562 (2021)","DOI":"10.1109\/CVPR46437.2021.00258"}],"container-title":["Lecture Notes in Computer Science","Natural Language Processing and Chinese Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-3349-7_30","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T08:50:11Z","timestamp":1763196611000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-3349-7_30"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,16]]},"ISBN":["9789819533480","9789819533497"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-3349-7_30","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,16]]},"assertion":[{"value":"16 November 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"NLPCC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"CCF International Conference on Natural Language Processing and Chinese Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Urumqi","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":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7 August 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 August 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"nlpcc2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/tcci.ccf.org.cn\/conference\/2025\/index.php","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}