{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T14:30:16Z","timestamp":1768314616813,"version":"3.49.0"},"publisher-location":"Singapore","reference-count":24,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819557394","type":"print"},{"value":"9789819557400","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-981-95-5740-0_28","type":"book-chapter","created":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T12:23:36Z","timestamp":1768220616000},"page":"402-415","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Contrastive Learning and\u00a0Multi-Granularity Feature Fusion for\u00a0Dynamic Video Summarization"],"prefix":"10.1007","author":[{"given":"Jing","family":"Han","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Keyang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xueqiang","family":"Lyu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zangtai","family":"Cai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,1,13]]},"reference":[{"key":"28_CR1","doi-asserted-by":"crossref","unstructured":"Afham, M., Shukla, S.N., Poursaeed, O., Zhang, P., Shah, A., Lim, S.: Revisiting kernel temporal segmentation as an adaptive tokenizer for long-form video understanding. In: IEEE\/CVF International Conference on Computer Vision Workshops, pp. 1181\u20131186 (2023)","DOI":"10.1109\/ICCVW60793.2023.00128"},{"issue":"11","key":"28_CR2","doi-asserted-by":"publisher","first-page":"1838","DOI":"10.1109\/JPROC.2021.3117472","volume":"109","author":"E Apostolidis","year":"2021","unstructured":"Apostolidis, E., Adamantidou, E., Metsai, A.I., Mezaris, V., Patras, I.: Video summarization using deep neural networks: a survey. Proc. IEEE 109(11), 1838\u20131863 (2021)","journal-title":"Proc. IEEE"},{"key":"28_CR3","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: Proceedings of the 37th International Conference on Machine Learning, pp. 149\u2013160. JMLR.org (2020)"},{"key":"28_CR4","doi-asserted-by":"publisher","first-page":"61451","DOI":"10.1007\/s11042-023-17985-0","volume":"83","author":"Z Chen","year":"2024","unstructured":"Chen, Z., Wang, X., Wang, J., Zhang, Y., Cao, X.: CSMB-VSS: video scene segmentation with cosine similarity matrix. Multim. Tools Appl. 83, 61451\u201361467 (2024)","journal-title":"Multim. Tools Appl."},{"key":"28_CR5","doi-asserted-by":"publisher","DOI":"10.1016\/j.margen.2019.100723","volume":"51","author":"MC Cieslak","year":"2020","unstructured":"Cieslak, M.C., Castelfranco, A.M., Roncalli, V., Lenz, P.H., Hartline, D.K.: t-distributed stochastic neighbor embedding (t-sne): a tool for eco-physiological transcriptomic analysis. Mar. Genomics 51, 100723 (2020)","journal-title":"Mar. Genomics"},{"key":"28_CR6","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: transformers for image recognition at scale. In: International Conference on Learning Representations, pp. 631\u2013653 (2021)"},{"key":"28_CR7","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. Springer International Publishing (2014)","DOI":"10.1007\/978-3-319-10584-0_33"},{"key":"28_CR8","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"28_CR9","doi-asserted-by":"crossref","unstructured":"Howard, A., et al.: Searching for mobilenetv3. In: IEEE\/CVF International Conference on Computer Vision, pp. 1314\u20131324 (2019)","DOI":"10.1109\/ICCV.2019.00140"},{"issue":"6","key":"28_CR10","doi-asserted-by":"publisher","first-page":"1709","DOI":"10.1109\/TCSVT.2019.2904996","volume":"30","author":"Z Ji","year":"2020","unstructured":"Ji, Z., Xiong, K., Pang, Y., Li, X.: Video summarization with attention-based encoder\u2013decoder networks. IEEE Trans. Circuits Syst. Video Technol. 30(6), 1709\u20131717 (2020)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"28_CR11","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.121288","volume":"237","author":"H Khan","year":"2024","unstructured":"Khan, H., Hussain, T., Ullah Khan, S., Ahmad Khan, Z., Baik, S.W.: Deep multi-scale pyramidal features network for supervised video summarization. Expert Syst. Appl. 237, 121288 (2024)","journal-title":"Expert Syst. Appl."},{"key":"28_CR12","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107677","volume":"111","author":"P Li","year":"2021","unstructured":"Li, P., Ye, Q., Zhang, L., Yuan, L., Xu, X., Shao, L.: Exploring global diverse attention via pairwise temporal relation for video summarization. Patt. Recogn. 111, 107677 (2021)","journal-title":"Patt. Recogn."},{"key":"28_CR13","doi-asserted-by":"crossref","unstructured":"Liang, G., Lv, Y., Li, S., Wang, X., Zhang, Y.: Video summarization with a dual-path attentive network. Neurocomput. 467(C), 1\u20139 (2022)","DOI":"10.1016\/j.neucom.2021.09.015"},{"key":"28_CR14","doi-asserted-by":"crossref","unstructured":"Otani, M., Nakashima, Y., Rahtu, E., Heikkil\u00e4, J.: Rethinking the evaluation of video summaries. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7588\u20137596 (2019)","DOI":"10.1109\/CVPR.2019.00778"},{"key":"28_CR15","doi-asserted-by":"crossref","unstructured":"Rochan, M., Ye, L., Wang, Y.: Video summarization using fully convolutional sequence networks. In: European Conference on Computer Vision, pp. 358\u2013374. Springer International Publishing (2018)","DOI":"10.1007\/978-3-030-01258-8_22"},{"key":"28_CR16","doi-asserted-by":"crossref","unstructured":"Rotman, D., Porat, D., Ashour, G.: Robust and efficient video scene detection using optimal sequential grouping. In: IEEE International Symposium on Multimedia, pp. 275\u2013280 (2016)","DOI":"10.1109\/ISM.2016.0061"},{"key":"28_CR17","doi-asserted-by":"crossref","unstructured":"Song, Y., Vallmitjana, J., Stent, A., Jaimes, A.: Tvsum: summarizing web videos using titles. In: IEEE Conference on Computer Vision and Pattern Recognition. pp. 5179\u20135187 (2015)","DOI":"10.1109\/CVPR.2015.7299154"},{"key":"28_CR18","unstructured":"Szegedy, C., et al.: Going deeper with convolutions. In: IEEE Conference on Computer Vision and Pattern Recognition, pp.\u00a01\u20139 (2015)"},{"key":"28_CR19","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, pp. 6000\u20136010 (2017)"},{"key":"28_CR20","doi-asserted-by":"crossref","unstructured":"Yun, S., Han, D., Chun, S., Oh, S.J., Yoo, Y., Choe, J.: Cutmix: regularization strategy to train strong classifiers with localizable features. In: IEEE\/CVF International Conference on Computer Vision, pp. 6022\u20136031 (2019)","DOI":"10.1109\/ICCV.2019.00612"},{"key":"28_CR21","unstructured":"Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: MIXUP: beyond empirical risk minimization. In: International Conference on Learning Representations. pp. 538\u2013551 (2018)"},{"key":"28_CR22","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. Springer International Publishing (2016)","DOI":"10.1007\/978-3-319-46478-7_47"},{"key":"28_CR23","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.123568","volume":"249","author":"Y Zhang","year":"2024","unstructured":"Zhang, Y., Liu, Y., Wu, C.: Attention-guided multi-granularity fusion model for video summarization. Expert Syst. Appl. 249, 123568 (2024)","journal-title":"Expert Syst. Appl."},{"key":"28_CR24","doi-asserted-by":"publisher","first-page":"948","DOI":"10.1109\/TIP.2020.3039886","volume":"30","author":"W Zhu","year":"2021","unstructured":"Zhu, W., Lu, J., Li, J., Zhou, J.: Dsnet: a flexible detect-to-summarize network for video summarization. IEEE Trans. Image Process. 30, 948\u2013962 (2021)","journal-title":"IEEE Trans. Image Process."}],"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\/978-981-95-5740-0_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T12:23:54Z","timestamp":1768220634000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-5740-0_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819557394","9789819557400"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-5740-0_28","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"13 January 2026","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":"Shanghai","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":"15 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2025.prcv.cn\/index.asp","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}