{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T06:16:10Z","timestamp":1767852970569,"version":"3.49.0"},"publisher-location":"Singapore","reference-count":28,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819786190","type":"print"},{"value":"9789819786206","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,20]],"date-time":"2024-10-20T00:00:00Z","timestamp":1729382400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,20]],"date-time":"2024-10-20T00:00:00Z","timestamp":1729382400000},"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\/978-981-97-8620-6_29","type":"book-chapter","created":{"date-parts":[[2024,10,19]],"date-time":"2024-10-19T21:02:10Z","timestamp":1729371730000},"page":"424-438","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Towards Making the Most of Knowledge Across Languages for Multimodal Cross-Lingual Summarization"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-6854-4465","authenticated-orcid":false,"given":"Xiaorui","family":"Shi","sequence":"first","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,10,20]]},"reference":[{"key":"29_CR1","doi-asserted-by":"crossref","unstructured":"Bai, Y., Gao, Y., Huang, H.: Cross-lingual abstractive summarization with limited parallel resources. In: ACL-IJCNLP, pp. 6910\u20136924 (2021)","DOI":"10.18653\/v1\/2021.acl-long.538"},{"key":"29_CR2","doi-asserted-by":"crossref","unstructured":"Bhattacharjee, A., Hasan, T., Ahmad, W.U., Li, Y.F., Kang, Y.B., Shahriyar, R.: Crosssum: Beyond English-centric cross-lingual abstractive text summarization for 1500+ language pairs (2022)","DOI":"10.18653\/v1\/2023.acl-long.143"},{"key":"29_CR3","doi-asserted-by":"crossref","unstructured":"Chen, J., Zhuge, H.: Abstractive text-image summarization using multi-modal attentional hierarchical RNN. In: EMNLP, pp. 4046\u20134056 (2018)","DOI":"10.18653\/v1\/D18-1438"},{"key":"29_CR4","unstructured":"Conneau, A., Lample, G.: Cross-lingual language model pretraining. In: NIPS (2019)"},{"key":"29_CR5","doi-asserted-by":"crossref","unstructured":"Fleiss, J.L., Cohen, J.: The equivalence of weighted kappa and the intraclass correlation coefficient as measures of reliability. Educ. Psychol. Meas. 613\u2013619 (1973)","DOI":"10.1177\/001316447303300309"},{"key":"29_CR6","doi-asserted-by":"crossref","unstructured":"Fu, X., Wang, J., Yang, Z.: MM-AVS: a full-scale dataset for multi-modal summarization. In: NAACL, pp. 5922\u20135926 (2021)","DOI":"10.18653\/v1\/2021.naacl-main.473"},{"key":"29_CR7","unstructured":"Koehn, P.: Statistical significance tests for machine translation evaluation. In: EMNLP, pp. 388\u2013395 (2004)"},{"key":"29_CR8","doi-asserted-by":"crossref","unstructured":"Li, H., Yuan, P., Xu, S., Wu, Y., He, X., Zhou, B.: Aspect-aware multimodal summarization for Chinese e-commerce products. In: AAAI, vol.\u00a034, pp. 8188\u20138195 (2020)","DOI":"10.1609\/aaai.v34i05.6332"},{"key":"29_CR9","doi-asserted-by":"crossref","unstructured":"Li, M., Chen, X., Gao, S., Chan, Z., Zhao, D., Yan, R.: VMSMO: learning to generate multimodal summary for video-based news articles. In: EMNLP, pp. 9360\u20139369 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.752"},{"key":"29_CR10","doi-asserted-by":"crossref","unstructured":"Liang, Y., Meng, F., Wang, J., Xu, J., Chen, Y., Zhou, J.: D2tv: dual knowledge distillation and target-oriented vision modeling for many-to-many multimodal summarization (2023). arXiv:2305.12767","DOI":"10.18653\/v1\/2023.findings-emnlp.994"},{"key":"29_CR11","doi-asserted-by":"crossref","unstructured":"Liang, Y., Meng, F., Xu, J., Wang, J., Chen, Y., Zhou, J.: Summary-oriented vision modeling for multimodal abstractive summarization (2022). arXiv:2212.07672","DOI":"10.18653\/v1\/2023.acl-long.165"},{"key":"29_CR12","unstructured":"Lin, C.Y.: ROUGE: a package for automatic evaluation of summaries. In: TSBO, pp. 74\u201381 (2004)"},{"key":"29_CR13","doi-asserted-by":"crossref","unstructured":"Liu, N., Wei, K., Sun, X., Yu, H., Yao, F., Jin, L., Zhi, G., Xu, G.: Assist non-native viewers: multimodal cross-lingual summarization for how2 videos. In: EMNLP, pp. 6959\u20136969 (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.468"},{"key":"29_CR14","unstructured":"Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., Krueger, G., Sutskever, I.: Learning transferable visual models from natural language supervision. In: ICML, vol.\u00a0139, pp. 8748\u20138763 (2021)"},{"key":"29_CR15","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster r-CNN: towards real-time object detection with region proposal networks. In: Cortes, C., Lawrence, N., Lee, D., Sugiyama, M., Garnett, R. (eds.) NIPS, vol.\u00a028 (2015)"},{"key":"29_CR16","unstructured":"Sanabria, R., Caglayan, O., Palaskar, S., Elliott, D., Barrault, L., Specia, L., Metze, F.: How2: a large-scale dataset for multimodal language understanding. In: ViGIL (2018)"},{"key":"29_CR17","unstructured":"Shazeer, N., Stern, M.: Adafactor: adaptive learning rates with sublinear memory cost. In: Dy, J., Krause, A. (eds.) ICML, vol.\u00a080, pp. 4596\u20134604 (2018)"},{"key":"29_CR18","doi-asserted-by":"crossref","unstructured":"Shi, X.: MCLS: a large-scale multimodal cross-lingual summarization dataset. In: CCL, pp. 273\u2013288. Springer (2023)","DOI":"10.1007\/978-981-99-6207-5_17"},{"key":"29_CR19","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L.u., Polosukhin, I.: Attention is all you need. In: NIPS, pp. 5998\u20136008 (2017)"},{"key":"29_CR20","unstructured":"Wan, X., Li, H., Xiao, J.: Cross-language document summarization based on machine translation quality prediction. In: ACL, pp. 917\u2013926. Uppsala, Sweden (2010)"},{"key":"29_CR21","doi-asserted-by":"crossref","unstructured":"Wang, J., Liang, Y., Meng, F., Li, Z., Qu, J., Zhou, J.: Cross-lingual summarization via chatgpt (2023). arXiv:2302.14229","DOI":"10.1162\/tacl_a_00520"},{"key":"29_CR22","doi-asserted-by":"crossref","unstructured":"Wang, J., Meng, F., Zheng, D., Liang, Y., Li, Z., Qu, J., Zhou, J.: Towards unifying multi-lingual and cross-lingual summarization (2023). arXiv:2305.09220","DOI":"10.18653\/v1\/2023.acl-long.843"},{"key":"29_CR23","doi-asserted-by":"crossref","unstructured":"Xiao, M., Zhu, J., Lin, H., Zhou, Y., Zong, C.: CFSum coarse-to-fine contribution network for multimodal summarization. In: ACL, pp. 8538\u20138553. Toronto, Canada (2023)","DOI":"10.18653\/v1\/2023.acl-long.476"},{"key":"29_CR24","doi-asserted-by":"crossref","unstructured":"Xiao, M., Zhu, J., Zhai, F., Zhou, Y., Zong, C.: Diusum: dynamic image utilization for multimodal summarization. In: AAAI, vol.\u00a038, pp. 19297\u201319305 (2024)","DOI":"10.1609\/aaai.v38i17.29899"},{"key":"29_CR25","doi-asserted-by":"crossref","unstructured":"Xue, L., Constant, N., Roberts, A., Kale, M., Al-Rfou, R., Siddhant, A., Barua, A., Raffel, C.: mT5: a massively multilingual pre-trained text-to-text transformer. In: NAACL, pp. 483\u2013498 (2021)","DOI":"10.18653\/v1\/2021.naacl-main.41"},{"key":"29_CR26","doi-asserted-by":"crossref","unstructured":"Yu, T., Dai, W., Liu, Z., Fung, P.: Vision guided generative pre-trained language models for multimodal abstractive summarization. In: EMNLP, pp. 3995\u20134007 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.326"},{"key":"29_CR27","doi-asserted-by":"crossref","unstructured":"Zhang, L., Zhang, X., Guo, Z., Liu, Z.: CISum: Learning cross-modality interaction to enhance multimodal semantic coverage for multimodal summarization (2023)","DOI":"10.1137\/1.9781611977653.ch42"},{"issue":"4","key":"29_CR28","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3445794","volume":"20","author":"J Zhu","year":"2021","unstructured":"Zhu, J., Xiang, L., Zhou, Y., Zhang, J., Zong, C.: Graph-based multimodal ranking models for multimodal summarization. TALLIP 20(4), 1\u201321 (2021)","journal-title":"TALLIP"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-8620-6_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,14]],"date-time":"2025-01-14T20:18:16Z","timestamp":1736885896000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-8620-6_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,20]]},"ISBN":["9789819786190","9789819786206"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-8620-6_29","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,20]]},"assertion":[{"value":"20 October 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","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":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2024.prcv.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}