{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,24]],"date-time":"2026-05-24T10:04:49Z","timestamp":1779617089521,"version":"3.53.1"},"publisher-location":"Singapore","reference-count":22,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819698837","type":"print"},{"value":"9789819698844","type":"electronic"}],"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\/978-981-96-9884-4_23","type":"book-chapter","created":{"date-parts":[[2025,7,25]],"date-time":"2025-07-25T12:25:39Z","timestamp":1753446339000},"page":"272-283","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Text-Oriented Event Extraction Combining Spectrogram"],"prefix":"10.1007","author":[{"given":"Liyao","family":"Xing","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhongqing","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peifeng","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,7,26]]},"reference":[{"issue":"5","key":"23_CR1","doi-asserted-by":"publisher","first-page":"6301","DOI":"10.1109\/TNNLS.2022.3213168","volume":"35","author":"Q Li","year":"2024","unstructured":"Li, Q., et al.: A survey on deep learning event extraction: approaches and applications. IEEE Trans. Neural Netw. Learn. Syst. 35(5), 6301\u20136321 (2024)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"23_CR2","doi-asserted-by":"crossref","unstructured":"Li, M., et al.: Cross-media structured common space for multimedia event extraction. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 2557\u20132568 (2020)","DOI":"10.18653\/v1\/2020.acl-main.230"},{"key":"23_CR3","doi-asserted-by":"crossref","unstructured":"Chen, B., et al.: Joint multimedia event extraction from video and article. In: Findings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp. 74\u201388 (2021)","DOI":"10.18653\/v1\/2021.findings-emnlp.8"},{"key":"23_CR4","doi-asserted-by":"crossref","unstructured":"Zhang, T., et al.: Improving event extraction via multimodal integration. In: Proceedings of the 25th ACM International Conference on Multimedia, pp. 270\u2013278 (2017)","DOI":"10.1145\/3123266.3123294"},{"key":"23_CR5","doi-asserted-by":"crossref","unstructured":"Tong, M., et al.: Image enhanced event detection in news articles. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 9040\u20139047 (2020)","DOI":"10.1609\/aaai.v34i05.6437"},{"key":"23_CR6","doi-asserted-by":"crossref","unstructured":"Liu, J., Chen, Y., Xu, J.: Multimedia event extraction from news with a unified contrastive learning framework. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 1945\u20131953 (2022)","DOI":"10.1145\/3503161.3548132"},{"key":"23_CR7","doi-asserted-by":"crossref","unstructured":"Li, M., et al.: CLIP-event: connecting text and images with event structures. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16399\u201316408 (2022)","DOI":"10.1109\/CVPR52688.2022.01593"},{"key":"23_CR8","doi-asserted-by":"crossref","unstructured":"Wang, S., Ju, M., Zhang, Y., Zheng, Y., Wang, M., Qi, G.: Cross-modal contrastive learning for event extraction. In: Proceedings of the 28th International Conference on Database Systems for Advanced Applications, pp. 699\u2013715 (2023)","DOI":"10.1007\/978-3-031-30675-4_51"},{"key":"23_CR9","doi-asserted-by":"crossref","unstructured":"Du, Z., Li, Y., Guo, X., Sun, Y., Li, B.: Training multimedia event extraction with generated images and captions. In: Proceedings of the 31st ACM International Conference on Multimedia, pp. 5504\u20135513 (2023)","DOI":"10.1145\/3581783.3612526"},{"key":"23_CR10","doi-asserted-by":"crossref","unstructured":"Doddington, G., Mitchell, A., Przybocki, M., Ramshaw, L., Strassel, S., Weischedel, R.: The automatic content extraction (ACE) program tasks, data, and evaluation. In: Proceedings of the 4th International Conference on Language Resources and Evaluation, vol. 2, pp. 837\u2013840 (2004)","DOI":"10.63317\/4o6ysc5sicba"},{"key":"23_CR11","doi-asserted-by":"crossref","unstructured":"Wadden, D., Wennberg, U., Luan, Y., Hajishirzi, H.: Entity, relation, and event extraction with contextualized span representations. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, pp. 5783\u20135788 (2019)","DOI":"10.18653\/v1\/D19-1585"},{"key":"23_CR12","doi-asserted-by":"crossref","unstructured":"Lu, Y., et al.: Text2Event: controllable sequence-to-structure generation for end-to-end event extraction. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, vol. 34, pp. 2795\u20132806 (2021)","DOI":"10.18653\/v1\/2021.acl-long.217"},{"key":"23_CR13","unstructured":"Paolini, G., et al.: Structured prediction as translation between augmented natural languages. In: Proceedings of the 9th International Conference on Learning Representations (2021)"},{"issue":"6","key":"23_CR14","doi-asserted-by":"publisher","first-page":"3983","DOI":"10.1007\/s11280-023-01216-5","volume":"26","author":"T Wu","year":"2023","unstructured":"Wu, T., Shiri, F., Kang, J., Qi, G., Haffari, G., Li, Y.-F.: KC-GEE: knowledge-based conditioning for generative event extraction. World Wide Web 26(6), 3983\u20133999 (2023)","journal-title":"World Wide Web"},{"key":"23_CR15","doi-asserted-by":"crossref","unstructured":"Gao, J., Yu, C., Wang, W., Zhao, H., Xu, R.: Mask-then-fill: a flexible and effective data augmentation framework for event extraction. In: Findings of the 2022 Conference on Empirical Methods in Natural Language Processing, pp. 4537\u20134544 (2022)","DOI":"10.18653\/v1\/2022.findings-emnlp.332"},{"key":"23_CR16","doi-asserted-by":"crossref","unstructured":"Ouyang, L., Wu, J., Jiang, X., et al.: Training language models to follow instructions with human feedback. In: Advances in Neural Information Processing Systems, vol. 35, pp. 27730\u201327744 (2022)","DOI":"10.52202\/068431-2011"},{"key":"23_CR17","unstructured":"Touvron, H., Martin, L., Stone, K., et al.: Llama 2: Open Foundation and Fine-Tuned Chat Models. arXiv preprint arXiv:2307.09288 (2023)"},{"key":"23_CR18","unstructured":"Chu, Y., et al.: Qwen2-Audio Technical Report. arXiv preprint arXiv:2407.10759 (2024)"},{"key":"23_CR19","unstructured":"Baevski, A., Zhou, Y., Mohamed, A., Auli, M.: wav2vec 2.0: a framework for self-supervised learning of speech representations. In: Advances in Neural Information Processing Systems, pp. 12449\u201312460 (2020)"},{"key":"23_CR20","unstructured":"Radford, A., Kim, J.W., Xu, T., Brockman, G., McLeavey, C., Sutskever, I.: Robust speech recognition via large-scale weak supervision. In: Proceedings of the 40th International Conference on Machine Learning, pp. 28492\u201328518 (2023)"},{"key":"23_CR21","unstructured":"Shen, K., et al.: NaturalSpeech 2: latent diffusion models are natural and zero-shot speech and singing synthesizers. In: Proceedings of the 12th International Conference on Learning Representations (2024)"},{"key":"23_CR22","doi-asserted-by":"publisher","first-page":"3451","DOI":"10.1109\/TASLP.2021.3122291","volume":"29","author":"W-N Hsu","year":"2021","unstructured":"Hsu, W.-N., Bolte, B., Tsai, Y.-H.H., Lakhotia, K., Salakhutdinov, R., Mohamed, A.: HuBERT: self-supervised speech representation learning by masked prediction of hidden units. IEEE\/ACM Trans. Audio Speech Lang. Process. 29, 3451\u20133460 (2021)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-9884-4_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,24]],"date-time":"2026-05-24T09:46:04Z","timestamp":1779615964000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-9884-4_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819698837","9789819698844"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-9884-4_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"26 July 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Ningbo","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":"26 July 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 July 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/icg\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}