{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T08:49:17Z","timestamp":1785919757026,"version":"3.56.0"},"publisher-location":"Cham","reference-count":25,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032314376","type":"print"},{"value":"9783032314383","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T00:00:00Z","timestamp":1785974400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T00:00:00Z","timestamp":1785974400000},"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":[[2027]]},"DOI":"10.1007\/978-3-032-31438-3_46","type":"book-chapter","created":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T08:16:10Z","timestamp":1785917770000},"page":"696-710","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Multimodal Abstractive Summarization of\u00a0Instructional Videos with\u00a0Vision-Language Models"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-1832-297X","authenticated-orcid":false,"given":"Maham","family":"Nazir","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-5095-605X","authenticated-orcid":false,"given":"Muhammad","family":"Aqeel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Richong","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0015-5534","authenticated-orcid":false,"given":"Francesco","family":"Setti","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,8,6]]},"reference":[{"key":"46_CR1","unstructured":"Banerjee, S., Lavie, A.: Meteor: an automatic metric for mt evaluation with improved correlation with human judgments. In: Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization, pp. 65\u201372 (2005)"},{"key":"46_CR2","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255 (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"46_CR3","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16$$\\times $$16 words: transformers for image recognition at scale. In: International Conference on Learning Representations (ICLR) (2021)"},{"key":"46_CR4","doi-asserted-by":"crossref","unstructured":"Gygli, M., Grabner, H., Riemenschneider, H., Van\u00a0Gool, L.: Creating summaries from user videos. In: European Conference on Computer Vision, pp. 505\u2013520 (2014)","DOI":"10.1007\/978-3-319-10584-0_33"},{"key":"46_CR5","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"46_CR6","doi-asserted-by":"crossref","unstructured":"Hori, C., et al.: Attention-based multimodal fusion for video description. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4193\u20134202 (2017)","DOI":"10.1109\/ICCV.2017.450"},{"key":"46_CR7","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: International Conference on Learning Representations (2015)"},{"key":"46_CR8","doi-asserted-by":"crossref","unstructured":"Lewis, M., et al.: BART: denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. In: Proceedings of the Annual Meeting of the Association for Computational Linguistics (2020)","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"46_CR9","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: BLIP: bootstrapping language-image pre-training for unified vision-language understanding and generation. In: International Conference on Machine Learning, pp. 12888\u201312900 (2022)"},{"key":"46_CR10","unstructured":"Li, J., Selvaraju, R., Gotmare, A., Joty, S., Xiong, C., Hoi, S.C.H.: Align before fuse: vision and language representation learning with momentum distillation. In: Advances in Neural Information Processing Systems, pp. 9694\u20139705 (2021)"},{"key":"46_CR11","doi-asserted-by":"crossref","unstructured":"Li, L., Gan, Z., Cheng, Y., Liu, J.: Multi-modal factorized bilinear pooling with co-attention learning for visual question answering. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1839\u20131848 (2017)","DOI":"10.1109\/ICCV.2017.202"},{"key":"46_CR12","doi-asserted-by":"crossref","unstructured":"Libovick\u00fd, J., Helcl, J.: Attention strategies for multi-source sequence-to-sequence learning. In: Proceedings of the Annual Meeting of the Association for Computational Linguistics, pp. 196\u2013202 (2017)","DOI":"10.18653\/v1\/P17-2031"},{"key":"46_CR13","unstructured":"Lin, C.Y.: ROUGE: a package for automatic evaluation of summaries. In: Text Summarization Branches Out, pp. 74\u201381 (2004)"},{"key":"46_CR14","doi-asserted-by":"crossref","unstructured":"Liu, N., Sun, X., Yu, H., Zhang, W., Xu, G.: Multistage fusion with forget gate for multimodal summarization in open-domain videos. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1834\u20131845. Association for Computational Linguistics (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.144"},{"key":"46_CR15","doi-asserted-by":"crossref","unstructured":"Palaskar, S., Libovick\u00fd, J., Gella, S., Metze, F.: Multimodal abstractive summarization for how2 videos. arXiv preprint arXiv:1906.07901 (2019)","DOI":"10.18653\/v1\/P19-1659"},{"key":"46_CR16","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: BLEU: a method for automatic evaluation of machine translation. In: Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, pp. 311\u2013318 (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"46_CR17","unstructured":"Paszke, A., et\u00a0al.: PyTorch: an imperative style, high-performance deep learning library. In: Advances in Neural Information Processing Systems, pp. 8026\u20138037 (2019)"},{"key":"46_CR18","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763 (2021)"},{"issue":"140","key":"46_CR19","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(140), 1\u201367 (2020)","journal-title":"J. Mach. Learn. Res."},{"key":"46_CR20","doi-asserted-by":"crossref","unstructured":"Song, Y., Vallmitjana, J., Stent, A., Jaimes, A.: TVSum: summarizing web videos using titles. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5179\u20135187 (2015)","DOI":"10.1109\/CVPR.2015.7299154"},{"key":"46_CR21","unstructured":"Song, Y., et\u00a0al.: Video summarization using deep semantic features. In: Asian Conference on Computer Vision, pp. 361\u2013376 (2020)"},{"key":"46_CR22","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: Proceedings of the Conference on Empirical Methods in Natural Language Processing (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.326"},{"key":"46_CR23","doi-asserted-by":"crossref","unstructured":"Zhang, K., Chao, W.L., Sha, F., Grauman, K.: Video summarization with long short-term memory. In: European Conference on Computer Vision, pp. 766\u2013782 (2016)","DOI":"10.1007\/978-3-319-46478-7_47"},{"key":"46_CR24","doi-asserted-by":"crossref","unstructured":"Zhou, L., Xu, C., Corso, J.J.: Towards automatic learning of procedures from web instructional videos. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a032 (2018)","DOI":"10.1609\/aaai.v32i1.12342"},{"key":"46_CR25","doi-asserted-by":"crossref","unstructured":"Zhu, J., Zhou, Y., Zhang, J., Li, H., Zong, C., Li, C.: Multimodal summarization with guidance of multimodal reference. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a034, pp. 9749\u20139756 (2020)","DOI":"10.1609\/aaai.v34i05.6525"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-31438-3_46","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T08:16:25Z","timestamp":1785917785000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-31438-3_46"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,6]]},"ISBN":["9783032314376","9783032314383"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-31438-3_46","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,6]]},"assertion":[{"value":"6 August 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lyon","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"France","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 August 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 August 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpr2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2026.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}