{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T08:04:00Z","timestamp":1742976240591,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":30,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819794393"},{"type":"electronic","value":"9789819794409"}],"license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"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\/978-981-97-9440-9_23","type":"book-chapter","created":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T17:05:21Z","timestamp":1730394321000},"page":"290-302","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Sequential Structured Fusion of\u00a0Image and\u00a0Text for\u00a0Enhanced Multimodal Abstractive Summarization"],"prefix":"10.1007","author":[{"given":"Rui","family":"He","sequence":"first","affiliation":[]},{"given":"Minjie","family":"Qiang","sequence":"additional","affiliation":[]},{"given":"Hongling","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Zhongqing","family":"Wang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,1]]},"reference":[{"key":"23_CR1","doi-asserted-by":"crossref","unstructured":"Li, H., et al.: Multi-modal summarization for asynchronous collection of text, image, audio and video. In: EMNLP, pp. 1092\u20131102 (2017)","DOI":"10.18653\/v1\/D17-1114"},{"key":"23_CR2","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"23_CR3","doi-asserted-by":"crossref","unstructured":"Lewis, M., et al.: BART: denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. In: ACL (2020)","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"23_CR4","first-page":"1","volume":"21","author":"C Raffel","year":"2020","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21, 1\u201367 (2020)","journal-title":"J. Mach. Learn. Res."},{"key":"23_CR5","unstructured":"Zhang, J., et al.: PEGASUS: pre-training with extracted gap-sentences for abstractive summarization. In: ICML, vol. 119, pp. 11328\u201311339 (2020)"},{"key":"23_CR6","doi-asserted-by":"crossref","unstructured":"Liang, Y., et al.: Summary-oriented vision modeling for multimodal abstractive summarization. In: ACL (2023)","DOI":"10.18653\/v1\/2023.acl-long.165"},{"key":"23_CR7","doi-asserted-by":"crossref","unstructured":"Chen, J., Zhuge, H.: Abstractive text-image summarization using multi-modal attentional hierarchical RNN. In: EMNLP (2018)","DOI":"10.18653\/v1\/D18-1438"},{"key":"23_CR8","doi-asserted-by":"publisher","first-page":"1553","DOI":"10.1109\/TMM.2013.2267205","volume":"15","author":"G Evangelopoulos","year":"2013","unstructured":"Evangelopoulos, G., et al.: Multimodal saliency and fusion for movie summarization based on aural, visual, and textual attention. IEEE Trans. Multimedia 15, 1553\u20131568 (2013)","journal-title":"IEEE Trans. Multimedia"},{"key":"23_CR9","doi-asserted-by":"crossref","unstructured":"Li, H., Zhu, J., Liu, T., Zhang, J., Zong, C.: Multi-modal sentence summarization with modality attention and image filtering. In: IJCAI (2018)","DOI":"10.24963\/ijcai.2018\/577"},{"key":"23_CR10","unstructured":"Sanabria, R., et al.: How2: a large-scale dataset for multimodal language understanding. CoRR abs\/1811.00347 (2018)"},{"key":"23_CR11","doi-asserted-by":"crossref","unstructured":"Zhu, J., et al.: MSMO: multimodal summarization with multimodal output. In: ACL (2018)","DOI":"10.18653\/v1\/D18-1448"},{"key":"23_CR12","doi-asserted-by":"crossref","unstructured":"Li, H., et al.: Aspect-aware multimodal summarization for Chinese e-commerce products. In: AAAI (2020)","DOI":"10.1609\/aaai.v34i05.6332"},{"key":"23_CR13","doi-asserted-by":"crossref","unstructured":"Fu, X., Wang, J., Yang, Z.: MM-AVS: a full-scale dataset for multi-modal summarization. In: NAACL-HLT (2021)","DOI":"10.18653\/v1\/2021.naacl-main.473"},{"key":"23_CR14","doi-asserted-by":"crossref","unstructured":"Liu, N., et al.: Multistage fusion with forget gate for multimodal summarization in open-domain videos. In: EMNLP, pp. 1834\u20131845 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.144"},{"key":"23_CR15","doi-asserted-by":"crossref","unstructured":"Yu, T., et al.: Vision guided generative pretrained language models for multimodal abstractive summarization. In: EMNLP (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.326"},{"key":"23_CR16","doi-asserted-by":"crossref","unstructured":"Palaskar, S., Libovick\u00fd, J., Gella, S., Metze, F.: Multi-modal abstractive summarization for how2 videos. CoRR abs\/1906.07901 (2019)","DOI":"10.18653\/v1\/P19-1659"},{"key":"23_CR17","doi-asserted-by":"crossref","unstructured":"Jiang, C., Xie, R., Ye, W., Sun, J., Zhang, S.: Exploiting pseudo image captions for multimodal summarization. In: ACL (2023)","DOI":"10.18653\/v1\/2023.findings-acl.12"},{"key":"23_CR18","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Wang, J., Sun, Z., Yang, Z.: LAMS: a location-aware approach for multi-modal summarization (Student Abstract). In AAAI (2021)","DOI":"10.1609\/aaai.v35i18.17971"},{"key":"23_CR19","unstructured":"Vinyals, O., Fortunato, M., Jaitly, N.: Pointer networks. In: Advances in Neural Information Processing Systems, In NIPS, vol. 28, pp. 2692\u20132700 (2015)"},{"key":"23_CR20","doi-asserted-by":"crossref","unstructured":"Narayan, S., et al.: Don\u2019t Give Me the Details, Just the Summary! Topic-aware convolutional neural networks for extreme summarization. In: EMNLP (2018)","DOI":"10.18653\/v1\/D18-1206"},{"key":"23_CR21","unstructured":"Lin, C.-Y.: ROUGE: a package for automatic evaluation of summaries. In: Text Summarization Branches Out, pp. 74\u201381 (2004)"},{"key":"23_CR22","unstructured":"Rohde, T., Wu, X., Liu, Y.: Hierarchical learning for generation with long source sequences. CoRR abs\/2104.07545 (2021)"},{"key":"23_CR23","doi-asserted-by":"crossref","unstructured":"Ravaut, M., Joty, S.R., Chen, N.F.: SummaReranker: a multi-task mixture-of-experts re-ranking framework for abstractive summarization. In: ACL (2022)","DOI":"10.18653\/v1\/2022.acl-long.309"},{"key":"23_CR24","doi-asserted-by":"crossref","unstructured":"Liu, Y., et al.: BRIO: bringing order to abstractive summarization. In: ACL (2022)","DOI":"10.18653\/v1\/2022.acl-long.207"},{"key":"23_CR25","doi-asserted-by":"crossref","unstructured":"He, K., et al.: Deep residual learning for image recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"23_CR26","unstructured":"Dosovitskiy, A., et al.: An image is worth 16\u00a0$$\\times $$\u00a016 words: transformers for image recognition at scale. In: ICLR (2021)"},{"key":"23_CR27","unstructured":"Li, J., et al.: Align before fuse: vision and language representation learning with momentum distillation. In: NIPS (2021)"},{"key":"23_CR28","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: ICML (2021)"},{"key":"23_CR29","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.C.H.: BLIP: boot-strapping language-image pre-training for unified vision-language understanding and generation. In: ICML (2022)"},{"key":"23_CR30","doi-asserted-by":"crossref","unstructured":"Ni, J., et al.: Sentence-T5: scalable sentence encoders from pre-trained text-to-text models. In: ACL (2022)","DOI":"10.18653\/v1\/2022.findings-acl.146"}],"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\/978-981-97-9440-9_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T17:11:49Z","timestamp":1730394709000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-9440-9_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,1]]},"ISBN":["9789819794393","9789819794409"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-9440-9_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,1]]},"assertion":[{"value":"1 November 2024","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":"Hangzhou","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":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 November 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 November 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"nlpcc2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/tcci.ccf.org.cn\/conference\/2024\/index.php","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}