{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T19:26:52Z","timestamp":1757618812177,"version":"3.44.0"},"publisher-location":"Singapore","reference-count":17,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819697939"},{"type":"electronic","value":"9789819697946"}],"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\/978-981-96-9794-6_15","type":"book-chapter","created":{"date-parts":[[2025,7,14]],"date-time":"2025-07-14T06:12:31Z","timestamp":1752473551000},"page":"170-182","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Scene Knowledge Enhanced Multimodal Retrieval Model for Dense Video Captioning"],"prefix":"10.1007","author":[{"given":"Mingru","family":"Huang","sequence":"first","affiliation":[]},{"given":"Pengfei","family":"Duan","sequence":"additional","affiliation":[]},{"given":"Yifang","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Huimin","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Jiawang","family":"Peng","sequence":"additional","affiliation":[]},{"given":"Shengwu","family":"Xiong","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,7,15]]},"reference":[{"key":"15_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":"15_CR2","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. ICLR (2021)"},{"key":"15_CR3","doi-asserted-by":"publisher","unstructured":"Fujita, S., Hirao, T., Kamigaito, H., Okumura, M., Nagata, M.: Soda: Story oriented dense video captioning evaluation framework. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, JM. (eds.) Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part VI 16, pp. 517\u2013531. Springer (2020). https:\/\/doi.org\/10.1007\/978-3-030-58539-6_31","DOI":"10.1007\/978-3-030-58539-6_31"},{"key":"15_CR4","doi-asserted-by":"crossref","unstructured":"Huang, G., Pang, B., Zhu, Z., Rivera, C., Soricut, R.: Multimodal pretraining for dense video captioning. In: Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing, pp. 470\u2013490 (2020)","DOI":"10.18653\/v1\/2020.aacl-main.48"},{"issue":"2","key":"15_CR5","first-page":"1","volume":"21","author":"N Khaled","year":"2021","unstructured":"Khaled, N., Aref, M., et al.: Bidirectional temporal context fusion with bi-modal semantic features using a gating mechanism for dense video captioning. Int. J. Intell. Comput. Inf. Sci. 21(2), 1\u201322 (2021)","journal-title":"Int. J. Intell. Comput. Inf. Sci."},{"key":"15_CR6","doi-asserted-by":"crossref","unstructured":"Kim, M., Kim, H.B., Moon, J., Choi, J., Kim, S.T.: Do you remember? Dense video captioning with cross-modal memory retrieval. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13894\u201313904 (2024)","DOI":"10.1109\/CVPR52733.2024.01318"},{"key":"15_CR7","doi-asserted-by":"crossref","unstructured":"Krishna, R., Hata, K., Ren, F., Fei-Fei, L., Carlos Niebles, J.: Dense-captioning events in videos. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 706\u2013 715 (2017)","DOI":"10.1109\/ICCV.2017.83"},{"key":"15_CR8","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"issue":"140","key":"15_CR9","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":"15_CR10","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Lawrence Zitnick, C., Parikh, D.: Cider: consensus-based image description evaluation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4566\u20134575 (2015)","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"15_CR11","doi-asserted-by":"crossref","unstructured":"Wang, T., Zhang, R., Lu, Z., Zheng, F., Cheng, R., Luo, P.: End-to-end dense video captioning with parallel decoding. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6847\u20136857 (2021)","DOI":"10.1109\/ICCV48922.2021.00677"},{"key":"15_CR12","doi-asserted-by":"crossref","unstructured":"Yang, A., et al.: Vid2Seq: large-scale pretraining of a visual language model for dense video captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10714\u201310726 (2023)","DOI":"10.1109\/CVPR52729.2023.01032"},{"key":"15_CR13","doi-asserted-by":"crossref","unstructured":"Zellers, R., et al.: Merlot reserve: neural script knowledge through vision and language and sound. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16375\u201316387 (2022)","DOI":"10.1109\/CVPR52688.2022.01589"},{"key":"15_CR14","doi-asserted-by":"crossref","unstructured":"Zhou, L., Xu, C., Corso, J.: Towards automatic learning of procedures from web instructional videos. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32 (2018)","DOI":"10.1609\/aaai.v32i1.12342"},{"key":"15_CR15","doi-asserted-by":"crossref","unstructured":"Zhou, L., Zhou, Y., Corso, J.J., Socher, R., Xiong, C.: End-to-end dense video captioning with masked transformer. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8739\u20138748 (2018)","DOI":"10.1109\/CVPR.2018.00911"},{"key":"15_CR16","unstructured":"Zhu, W., Pang, B., Thapliyal, A.V., Wang, W.Y., Soricut, R.: End-to-end dense video captioning as sequence generation. In: Proceedings of the 29th International Conference on Computational Linguistics, pp. 5651\u20135665 (2022)"},{"issue":"4","key":"15_CR17","doi-asserted-by":"publisher","first-page":"387","DOI":"10.1016\/S0028-3932(96)00094-2","volume":"35","author":"K Allan","year":"1997","unstructured":"Allan, K., Rugg, M.: An event-related potential study of explicit memory on tests of cued recall and recognition. Neuropsychologia 35(4), 387\u2013397 (1997)","journal-title":"Neuropsychologia"}],"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\/978-981-96-9794-6_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,7]],"date-time":"2025-09-07T08:31:51Z","timestamp":1757233911000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-9794-6_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819697939","9789819697946"],"references-count":17,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-9794-6_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"15 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"}}]}}