{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T13:25:35Z","timestamp":1778592335763,"version":"3.51.4"},"publisher-location":"Cham","reference-count":23,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030057091","type":"print"},{"value":"9783030057107","type":"electronic"}],"license":[{"start":{"date-parts":[[2018,12,8]],"date-time":"2018-12-08T00:00:00Z","timestamp":1544227200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-030-05710-7_22","type":"book-chapter","created":{"date-parts":[[2018,12,7]],"date-time":"2018-12-07T07:48:55Z","timestamp":1544168935000},"page":"264-276","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Joint Visual-Textual Sentiment Analysis Based on Cross-Modality Attention Mechanism"],"prefix":"10.1007","author":[{"given":"Xuelin","family":"Zhu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Biwei","family":"Cao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuai","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiuxin","family":"Cao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,12,8]]},"reference":[{"key":"22_CR1","doi-asserted-by":"crossref","unstructured":"Wang, L., Li, Y., Huang, J., et al.: Learning two-branch neural networks for image-text matching tasks. IEEE Trans. Pattern Anal. Mach. Intell. (2018)","DOI":"10.1109\/TPAMI.2018.2797921"},{"key":"22_CR2","doi-asserted-by":"crossref","unstructured":"You, Q., Jin, H., Luo, J.: Visual sentiment analysis by attending on local image regions. In: AAAI, pp. 231\u2013237 (2017)","DOI":"10.1609\/aaai.v31i1.10501"},{"issue":"4","key":"22_CR3","doi-asserted-by":"publisher","first-page":"652","DOI":"10.1109\/TPAMI.2016.2587640","volume":"39","author":"O Vinyals","year":"2017","unstructured":"Vinyals, O., Toshev, A., Bengio, S., et al.: Show and tell: lessons learned from the 2015 MSCOCO image captioning challenge. IEEE Trans. Pattern Anal. Mach. Intell. 39(4), 652\u2013663 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"22_CR4","doi-asserted-by":"crossref","unstructured":"Chen, X., Wang, Y., Liu, Q.: Visual and textual sentiment analysis using deep fusion convolutional neural networks. In: 2017 IEEE International Conference on Image Processing (ICIP), pp. 1557\u20131561. IEEE (2017)","DOI":"10.1109\/ICIP.2017.8296543"},{"key":"22_CR5","doi-asserted-by":"crossref","unstructured":"You, Q., Cao, L., Jin, H., et al.: Robust visual-textual sentiment analysis: when attention meets tree-structured recursive neural networks. In: Proceedings of the 2016 ACM on Multimedia Conference, pp. 1008\u20131017. ACM (2016)","DOI":"10.1145\/2964284.2964288"},{"key":"22_CR6","doi-asserted-by":"crossref","unstructured":"You, Q., Luo, J., Jin, H., et al.: Cross-modality consistent regression for joint visual textual sentiment analysis of social multimedia. In: Proceedings of the Ninth ACM International Conference on Web Search and Data Mining, pp. 13\u201322. ACM (2016)","DOI":"10.1145\/2835776.2835779"},{"key":"22_CR7","doi-asserted-by":"crossref","unstructured":"Katsurai, M., Satoh, S.: Image sentiment analysis using latent correlations among visual, textual, and sentiment views. In: 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2837\u20132841. IEEE (2016)","DOI":"10.1109\/ICASSP.2016.7472195"},{"issue":"4","key":"22_CR8","doi-asserted-by":"publisher","first-page":"479","DOI":"10.1007\/s00530-014-0407-8","volume":"22","author":"D Cao","year":"2016","unstructured":"Cao, D., Ji, R., Lin, D., et al.: A cross-media public sentiment analysis system for microblog. Multimedia Syst. 22(4), 479\u2013486 (2016)","journal-title":"Multimedia Syst."},{"key":"22_CR9","doi-asserted-by":"crossref","unstructured":"Yang, Z., Yang, D., Dyer, C., et al.: Hierarchical attention networks for document classification. In: 2016 Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 1480\u20131489 (2016)","DOI":"10.18653\/v1\/N16-1174"},{"key":"22_CR10","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., et al.: Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2818\u20132826 (2016)","DOI":"10.1109\/CVPR.2016.308"},{"issue":"11","key":"22_CR11","doi-asserted-by":"publisher","first-page":"2008","DOI":"10.1109\/TMM.2015.2482228","volume":"17","author":"L Pang","year":"2015","unstructured":"Pang, L., Zhu, S., Ngo, C.W.: Deep multimodal learning for affective analysis and retrieval. IEEE Trans. Multimedia 17(11), 2008\u20132020 (2015)","journal-title":"IEEE Trans. Multimedia"},{"key":"22_CR12","unstructured":"Xu, K., Ba, J., Kiros, R., et al.: Show, attend and tell: neural image caption generation with visual attention. In: International Conference on Machine Learning, pp. 2048\u20132057 (2015)"},{"key":"22_CR13","doi-asserted-by":"crossref","unstructured":"Ma, L., Lu, Z., Shang, L., et al.: Multimodal convolutional neural networks for matching image and sentence. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2623\u20132631 (2015)","DOI":"10.1109\/ICCV.2015.301"},{"key":"22_CR14","doi-asserted-by":"crossref","unstructured":"Campos, V., Salvador, A., Giro-i-Nieto, X., et al.: Diving deep into sentiment: understanding fine-tuned CNNs for visual sentiment prediction. In: Proceedings of the 1st International Workshop on Affect and Sentiment in Multimedia, pp. 57\u201362. ACM (2015)","DOI":"10.1145\/2813524.2813530"},{"key":"22_CR15","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: International Conference on Machine Learning, pp. 448\u2013456 (2015)"},{"key":"22_CR16","doi-asserted-by":"crossref","unstructured":"Wang, M., Cao, D., Li, L., et al.: Microblog sentiment analysis based on cross-media bag-of-words model. In: Proceedings of International Conference on Internet Multi-media Computing and Service, p. 76. ACM (2014)","DOI":"10.1145\/2632856.2632912"},{"key":"22_CR17","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate arXiv preprint arXiv:1409.0473 (2014)"},{"key":"22_CR18","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, C.: Glove: global vectors for word representation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1532\u20131543 (2014)","DOI":"10.3115\/v1\/D14-1162"},{"key":"22_CR19","doi-asserted-by":"crossref","unstructured":"You, Q., Luo, J.: Towards social imagematics: sentiment analysis in social multimedia. In: Proceedings of the Thirteenth International Workshop on Multimedia Data Mining, p. 3. ACM (2013)","DOI":"10.1145\/2501217.2501220"},{"key":"22_CR20","doi-asserted-by":"crossref","unstructured":"Chen, T., Lu, D., Kan, M.Y., et al.: Understanding and classifying image tweets. In: Proceedings of the 21st ACM International Conference on Multimedia, pp. 781\u2013784. ACM (2013)","DOI":"10.1145\/2502081.2502203"},{"key":"22_CR21","doi-asserted-by":"crossref","unstructured":"Socher, R., Perelygin, A., Wu, J., et al.: Recursive deep models for semantic compositionality over a sentiment treebank. In: Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, pp. 1631\u20131642 (2013)","DOI":"10.18653\/v1\/D13-1170"},{"key":"22_CR22","doi-asserted-by":"crossref","unstructured":"Borth, D., Ji, R., Chen, T., et al.: Large-scale visual sentiment ontology and detectors using adjective noun pairs. In: Proceedings of the 21st ACM International Conference on Multimedia, pp. 223\u2013232. ACM (2013)","DOI":"10.1145\/2502081.2502282"},{"key":"22_CR23","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing systems, pp. 1097\u20131105 (2012)"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-05710-7_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T10:14:49Z","timestamp":1775297689000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-05710-7_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,12,8]]},"ISBN":["9783030057091","9783030057107"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-05710-7_22","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,12,8]]},"assertion":[{"value":"8 December 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MMM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multimedia Modeling","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Thessaloniki","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Greece","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 January 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 January 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/mmm2019.iti.gr\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double blind for full papers and workshop papers, single blind for other paper types","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"204","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"96","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"47% - 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"}},{"value":"2.67","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"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"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"6 demonstration papers, 5 industry papers, 6 workshop papers, and 6 Video Browser Showdown papers were also accepted.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}}]}}