{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:35:24Z","timestamp":1742913324731,"version":"3.40.3"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031442155"},{"type":"electronic","value":"9783031442162"}],"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\/978-3-031-44216-2_42","type":"book-chapter","created":{"date-parts":[[2023,9,21]],"date-time":"2023-09-21T07:02:58Z","timestamp":1695279778000},"page":"512-523","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Multimodal Cross-Attention Graph Network for\u00a0Desire Detection"],"prefix":"10.1007","author":[{"given":"Ruitong","family":"Gu","sequence":"first","affiliation":[]},{"given":"Xin","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Qinghong","family":"Yang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,9,22]]},"reference":[{"key":"42_CR1","doi-asserted-by":"crossref","unstructured":"Caron, M., et al.: Emerging properties in self-supervised vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9650\u20139660 (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"42_CR2","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1016\/j.neucom.2013.02.041","volume":"122","author":"CY Chang","year":"2013","unstructured":"Chang, C.Y., Chang, C.W., Zheng, J.Y., Chung, P.C.: Physiological emotion analysis using support vector regression. Neurocomputing 122, 79\u201387 (2013)","journal-title":"Neurocomputing"},{"key":"42_CR3","doi-asserted-by":"crossref","unstructured":"Chauhan, D.S., Dhanush, S., Ekbal, A., Bhattacharyya, P.: Sentiment and emotion help sarcasm? A multi-task learning framework for multi-modal sarcasm, sentiment and emotion analysis. In: Proceedings of the Annual Meeting of the Association for Computational Linguistics, pp. 4351\u20134360 (2020)","DOI":"10.18653\/v1\/2020.acl-main.401"},{"key":"42_CR4","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":"42_CR5","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: International Conference on Learning Representations (2020)"},{"key":"42_CR6","doi-asserted-by":"crossref","unstructured":"Hasan, M.K., Rahman, W., Zadeh, A., Zhong, J., Tanveer, M.I., Morency, L.P., et al.: UR-FUNNY: a multimodal language dataset for understanding humor. arXiv preprint arXiv:1904.06618 (2019)","DOI":"10.18653\/v1\/D19-1211"},{"key":"42_CR7","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1016\/j.inffus.2018.10.009","volume":"51","author":"MM Hassan","year":"2019","unstructured":"Hassan, M.M., Alam, M.G.R., Uddin, M.Z., Huda, S., Almogren, A., Fortino, G.: Human emotion recognition using deep belief network architecture. Inf. Fusion 51, 10\u201318 (2019)","journal-title":"Inf. Fusion"},{"key":"42_CR8","doi-asserted-by":"crossref","unstructured":"Hearst, M.A.: Automatic acquisition of hyponyms from large text corpora. In: COLING 1992 Volume 2: The 14th International Conference on Computational Linguistics (1992)","DOI":"10.3115\/992133.992154"},{"key":"42_CR9","doi-asserted-by":"crossref","unstructured":"Jia, A., He, Y., Zhang, Y., Uprety, S., Song, D., Lioma, C.: Beyond emotion: a multi-modal dataset for human desire understanding. In: Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 1512\u20131522 (2022)","DOI":"10.18653\/v1\/2022.naacl-main.108"},{"key":"42_CR10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11633-022-1372-x","volume":"20","author":"L Jing","year":"2023","unstructured":"Jing, L., Li, Y., Xu, J., Yu, Y., Shen, P., Song, X.: Vision enhanced generative pre-trained language model for multimodal sentence summarization. Mach. Intell. Res. 20, 1\u201310 (2023)","journal-title":"Mach. Intell. Res."},{"key":"42_CR11","doi-asserted-by":"crossref","unstructured":"Jing, L., Song, X., Lin, X., Zhao, Z., Zhou, W., Nie, L.: Stylized data-to-text generation: a case study in the e-commerce domain. ACM Trans. Inf. Syst. (2023)","DOI":"10.1145\/3603374"},{"key":"42_CR12","doi-asserted-by":"crossref","unstructured":"Jing, L., Song, X., Ouyang, K., Jia, M., Nie, L.: Multi-source semantic graph-based multimodal sarcasm explanation generation. arXiv preprint arXiv:2306.16650 (2023)","DOI":"10.18653\/v1\/2023.acl-long.635"},{"key":"42_CR13","doi-asserted-by":"crossref","unstructured":"Jing, L., Tian, M., Chen, X., Sun, T., Guan, W., Song, X.: CI-OCM: counterfactural inference towards unbiased outfit compatibility modeling. In: Proceedings of the 1st Workshop on Multimedia Computing towards Fashion Recommendation, pp. 31\u201338. Association for Computing Machinery (2022)","DOI":"10.1145\/3552468.3555363"},{"issue":"4","key":"42_CR14","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3524499","volume":"55","author":"X Li","year":"2022","unstructured":"Li, X., et al.: EEG based emotion recognition: a tutorial and review. ACM Comput. Surv. 55(4), 1\u201357 (2022)","journal-title":"ACM Comput. Surv."},{"key":"42_CR15","doi-asserted-by":"crossref","unstructured":"Liang, B., et al.: Multi-modal sarcasm detection via cross-modal graph convolutional network. In: Proceedings of the Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 1767\u20131777 (2022)","DOI":"10.18653\/v1\/2022.acl-long.124"},{"key":"42_CR16","doi-asserted-by":"crossref","unstructured":"Nie, L., Jia, M., Song, X., Wu, G., Cheng, H., Gu, J.: Multimodal activation: awakening dialog robots without wake words. In: The 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 491\u2013500. ACM (2021)","DOI":"10.1145\/3404835.3462964"},{"key":"42_CR17","doi-asserted-by":"crossref","unstructured":"Qiao, Y., Jing, L., Song, X., Chen, X., Zhu, L., Nie, L.: Mutual-enhanced incongruity learning network for multi-modal sarcasm detection. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 37, pp. 9507\u20139515 (2023)","DOI":"10.1609\/aaai.v37i8.26138"},{"issue":"11","key":"42_CR18","doi-asserted-by":"publisher","first-page":"2673","DOI":"10.1109\/78.650093","volume":"45","author":"M Schuster","year":"1997","unstructured":"Schuster, M., Paliwal, K.K.: Bidirectional recurrent neural networks. IEEE Trans. Signal Process. 45(11), 2673\u20132681 (1997)","journal-title":"IEEE Trans. Signal Process."},{"key":"42_CR19","doi-asserted-by":"crossref","unstructured":"Song, X., Jing, L., Lin, D., Zhao, Z., Chen, H., Nie, L.: V2P: vision-to-prompt based multi-modal product summary generation. In: The International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 992\u20131001. ACM (2022)","DOI":"10.1145\/3477495.3532076"},{"key":"42_CR20","doi-asserted-by":"crossref","unstructured":"Sun, T., Wang, W., Jing, L., Cui, Y., Song, X., Nie, L.: Counterfactual reasoning for out-of-distribution multimodal sentiment analysis. In: The ACM International Conference on Multimedia, pp. 15\u201323. ACM (2022)","DOI":"10.1145\/3503161.3548211"},{"key":"42_CR21","doi-asserted-by":"crossref","unstructured":"Xiao, L., Wu, X., Wu, W., Yang, J., He, L.: Multi-channel attentive graph convolutional network with sentiment fusion for multimodal sentiment analysis. In: IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 4578\u20134582. IEEE (2022)","DOI":"10.1109\/ICASSP43922.2022.9747542"},{"key":"42_CR22","doi-asserted-by":"crossref","unstructured":"Xu, B., Fu, Y., Jiang, Y.G., Li, B., Sigal, L.: Video emotion recognition with transferred deep feature encodings. In: Proceedings of the ACM on International Conference on Multimedia Retrieval, pp. 15\u201322 (2016)","DOI":"10.1145\/2911996.2912006"},{"key":"42_CR23","doi-asserted-by":"publisher","first-page":"51522","DOI":"10.1109\/ACCESS.2019.2909919","volume":"7","author":"G Xu","year":"2019","unstructured":"Xu, G., Meng, Y., Qiu, X., Yu, Z., Wu, X.: Sentiment analysis of comment texts based on BiLSTM. IEEE Access 7, 51522\u201351532 (2019)","journal-title":"IEEE Access"},{"key":"42_CR24","doi-asserted-by":"crossref","unstructured":"Yang, X., Feng, S., Zhang, Y., Wang, D.: Multimodal sentiment detection based on multi-channel graph neural networks. In: Proceedings of the Annual Meeting of the Association for Computational Linguistics and the International Joint Conference on Natural Language Processing, pp. 328\u2013339 (2021)","DOI":"10.18653\/v1\/2021.acl-long.28"},{"issue":"12","key":"42_CR25","doi-asserted-by":"publisher","first-page":"3696","DOI":"10.1109\/TFUZZ.2021.3072492","volume":"29","author":"Y Zhang","year":"2021","unstructured":"Zhang, Y., et al.: CFN: a complex-valued fuzzy network for sarcasm detection in conversations. IEEE Trans. Fuzzy Syst. 29(12), 3696\u20133710 (2021)","journal-title":"IEEE Trans. Fuzzy Syst."},{"key":"42_CR26","doi-asserted-by":"crossref","unstructured":"Zhao, S., Yao, H., Yang, Y., Zhang, Y.: Affective image retrieval via multi-graph learning. In: Proceedings of the ACM International Conference on Multimedia, pp. 1025\u20131028 (2014)","DOI":"10.1145\/2647868.2655035"},{"issue":"3","key":"42_CR27","doi-asserted-by":"publisher","first-page":"1110","DOI":"10.1109\/TCYB.2018.2797176","volume":"49","author":"WL Zheng","year":"2018","unstructured":"Zheng, W.L., Liu, W., Lu, Y., Lu, B.L., Cichocki, A.: Emotionmeter: a multimodal framework for recognizing human emotions. IEEE Trans. Cybern. 49(3), 1110\u20131122 (2018)","journal-title":"IEEE Trans. Cybern."}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2023"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-44216-2_42","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,21]],"date-time":"2023-09-21T07:09:22Z","timestamp":1695280162000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-44216-2_42"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031442155","9783031442162"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-44216-2_42","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":"22 September 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICANN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Heraklion","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":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"32","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/e-nns.org\/icann2023\/","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":"easyacademia.org","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"947","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":"426","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":"22","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":"45% - 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":"2.4","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":"4","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)"}},{"value":"type of other papers accepted  : 9 Abstract","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}