{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T17:17:31Z","timestamp":1742923051568,"version":"3.40.3"},"publisher-location":"Cham","reference-count":41,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031533105"},{"type":"electronic","value":"9783031533112"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-53311-2_2","type":"book-chapter","created":{"date-parts":[[2024,1,27]],"date-time":"2024-01-27T21:37:36Z","timestamp":1706391456000},"page":"14-27","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Semantic Transition Detection for\u00a0Self-supervised Video Scene Segmentation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-7297-2071","authenticated-orcid":false,"given":"Lu","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3299-0785","authenticated-orcid":false,"given":"Jiawei","family":"Tan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9797-3241","authenticated-orcid":false,"given":"Pingan","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7799-1023","authenticated-orcid":false,"given":"Hongxing","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,1,28]]},"reference":[{"key":"2_CR1","doi-asserted-by":"crossref","unstructured":"Baraldi, L., Grana, C., Cucchiara, R.: A deep siamese network for scene detection in broadcast videos. In: ACM Multimedia, pp. 1199\u20131202 (2015)","DOI":"10.1145\/2733373.2806316"},{"key":"2_CR2","doi-asserted-by":"crossref","unstructured":"Benaim, S., et al.: SpeedNet: learning the speediness in videos. In: CVPR, pp. 9919\u20139928 (2020)","DOI":"10.1109\/CVPR42600.2020.00994"},{"key":"2_CR3","unstructured":"Berndt, D.J., Clifford, J.: Using dynamic time warping to find patterns in time series. In: KDD Workshop, pp. 359\u2013370 (1994)"},{"key":"2_CR4","unstructured":"Castellano, B.: Pyscenedetect: intelligent scene cut detection and video splitting tool. https:\/\/pyscenedetect.readthedocs.io\/en\/latest\/ (2018)"},{"issue":"1","key":"2_CR5","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1109\/TMM.2008.2008924","volume":"11","author":"V Chasanis","year":"2009","unstructured":"Chasanis, V., Likas, A., Galatsanos, N.P.: Scene detection in videos using shot clustering and sequence alignment. IEEE Trans. Multim. 11(1), 89\u2013100 (2009)","journal-title":"IEEE Trans. Multim."},{"key":"2_CR6","doi-asserted-by":"crossref","unstructured":"Chen, S., Nie, X., Fan, D., et al.: Shot contrastive self-supervised learning for scene boundary detection. In: CVPR, pp. 9796\u20139805 (2021)","DOI":"10.1109\/CVPR46437.2021.00967"},{"key":"2_CR7","doi-asserted-by":"crossref","unstructured":"Chen, S., Liu, C.H., Hao, X., Nie, X., Arap, M., Hamid, R.: Movies2Scenes: using movie metadata to learn scene representation. In: CVPR, pp. 6535\u20136544 (2023)","DOI":"10.1109\/CVPR52729.2023.00632"},{"key":"2_CR8","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., et al.: ImageNet: a large-scale hierarchical image database. In: CVPR, pp. 248\u2013255 (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"2_CR9","doi-asserted-by":"crossref","unstructured":"Gaikwad, B., Sontakke, A., Patwardhan, M.S., et al.: Plots to previews: towards automatic movie preview retrieval using publicly available meta-data. In: ICCV Workshop, pp. 3198\u20133207 (2021)","DOI":"10.1109\/ICCVW54120.2021.00359"},{"key":"2_CR10","unstructured":"Gehring, J., Auli, M., Grangier, D., et al.: Convolutional sequence to sequence learning. In: ICML, vol. 70, pp. 1243\u20131252 (2017)"},{"key":"2_CR11","doi-asserted-by":"crossref","unstructured":"Han, B., Wu, W.: Video scene segmentation using a novel boundary evaluation criterion and dynamic programming. In: ICME, pp. 1\u20136 (2011)","DOI":"10.1109\/ICME.2011.6012001"},{"key":"2_CR12","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1016\/j.inffus.2021.04.016","volume":"76","author":"IU Haq","year":"2021","unstructured":"Haq, I.U., Muhammad, K., Hussain, T., et al.: Quicklook: movie summarization using scene-based leading characters with psychological cues fusion. Inf. Fusion 76, 24\u201335 (2021)","journal-title":"Inf. Fusion"},{"key":"2_CR13","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., et al.: Deep residual learning for image recognition. In: CVPR, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"2_CR14","doi-asserted-by":"crossref","unstructured":"Huang, Q., Xiong, Y., Rao, A., et al.: MovieNet: a holistic dataset for movie understanding. In: ECCV, vol. 12349, pp. 709\u2013727 (2020)","DOI":"10.1007\/978-3-030-58548-8_41"},{"key":"2_CR15","doi-asserted-by":"crossref","unstructured":"Kim, D., Cho, D., Kweon, I.S.: Self-supervised video representation learning with space-time cubic puzzles. In: AAAI, pp. 8545\u20138552 (2019)","DOI":"10.1609\/aaai.v33i01.33018545"},{"key":"2_CR16","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (2015)"},{"key":"2_CR17","doi-asserted-by":"crossref","unstructured":"Liang, C., Zhang, Y., Cheng, J., et al.: A novel role-based movie scene segmentation method. In: PCM, vol. 5879, pp. 917\u2013922 (2009)","DOI":"10.1007\/978-3-642-10467-1_82"},{"issue":"9","key":"2_CR18","doi-asserted-by":"publisher","first-page":"3559","DOI":"10.1109\/TCSVT.2020.3042476","volume":"31","author":"D Liu","year":"2021","unstructured":"Liu, D., Kamath, N., Bhattacharya, S., et al.: Adaptive context reading network for movie scene detection. IEEE Trans. Circuits Syst. Video Technol. 31(9), 3559\u20133574 (2021)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"2_CR19","unstructured":"Van der Maaten, L., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9(11), 2579\u20132605 (2008)"},{"key":"2_CR20","doi-asserted-by":"crossref","unstructured":"Mun, J., Shin, M., Han, G., et al.: BaSSL: boundary-aware self-supervised learning for video scene segmentation. In: ACCV, pp. 4027\u20134043 (2022)","DOI":"10.1007\/978-3-031-26316-3_29"},{"key":"2_CR21","doi-asserted-by":"crossref","unstructured":"Na, S., Lee, S., Kim, J., et al.: A read-write memory network for movie story understanding. In: ICCV, pp. 677\u2013685 (2017)","DOI":"10.1109\/ICCV.2017.80"},{"key":"2_CR22","doi-asserted-by":"crossref","unstructured":"Nicolas, H., Manoury, A., Benois-Pineau, J., et al.: Grouping video shots into scenes based on 1d mosaic descriptors. In: ICIP, pp. 637\u2013640 (2004)","DOI":"10.1109\/ICIP.2004.1418835"},{"issue":"5","key":"2_CR23","doi-asserted-by":"publisher","first-page":"991","DOI":"10.1007\/s11760-018-1244-6","volume":"12","author":"S Protasov","year":"2018","unstructured":"Protasov, S., Khan, A.M., Sozykin, K., et al.: Using deep features for video scene detection and annotation. Sig. Image Video Process. 12(5), 991\u2013999 (2018)","journal-title":"Sig. Image Video Process."},{"key":"2_CR24","doi-asserted-by":"crossref","unstructured":"Qian, R., et al.: Spatiotemporal contrastive video representation learning. In: CVPR, pp. 6964\u20136974 (2021)","DOI":"10.1109\/CVPR46437.2021.00689"},{"key":"2_CR25","doi-asserted-by":"crossref","unstructured":"Rao, A., Xu, L., Xiong, Y., et al.: A local-to-global approach to multi-modal movie scene segmentation. In: CVPR, pp. 10143\u201310152 (2020)","DOI":"10.1109\/CVPR42600.2020.01016"},{"key":"2_CR26","doi-asserted-by":"crossref","unstructured":"Rasheed, Z., Shah, M.: Scene detection in hollywood movies and TV shows. In: CVPR, pp. 343\u2013350 (2003)","DOI":"10.1109\/CVPR.2003.1211489"},{"issue":"6","key":"2_CR27","doi-asserted-by":"publisher","first-page":"1097","DOI":"10.1109\/TMM.2005.858392","volume":"7","author":"Z Rasheed","year":"2005","unstructured":"Rasheed, Z., Shah, M.: Detection and representation of scenes in videos. IEEE Trans. Multim. 7(6), 1097\u20131105 (2005)","journal-title":"IEEE Trans. Multim."},{"issue":"2","key":"2_CR28","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1142\/S1793351X17400086","volume":"11","author":"D Rotman","year":"2017","unstructured":"Rotman, D., Porat, D., Ashour, G.: Optimal sequential grouping for robust video scene detection using multiple modalities. Int. J. Semantic Comput. 11(2), 193\u2013208 (2017)","journal-title":"Int. J. Semantic Comput."},{"key":"2_CR29","unstructured":"Rui, Y., Huang, T.S., Mehrotra, S.: Exploring video structure beyond the shots. In: ICMCS, pp. 237\u2013240 (1998)"},{"issue":"5","key":"2_CR30","doi-asserted-by":"publisher","first-page":"359","DOI":"10.1007\/s005300050138","volume":"7","author":"Y Rui","year":"1999","unstructured":"Rui, Y., Huang, T.S., Mehrotra, S.: Constructing table-of-content for videos. Multim. Syst. 7(5), 359\u2013368 (1999)","journal-title":"Multim. Syst."},{"issue":"8","key":"2_CR31","doi-asserted-by":"publisher","first-page":"1163","DOI":"10.1109\/TCSVT.2011.2138830","volume":"21","author":"P Sidiropoulos","year":"2011","unstructured":"Sidiropoulos, P., Mezaris, V., Kompatsiaris, I., et al.: Temporal video segmentation to scenes using high-level audiovisual features. IEEE Trans. Circuits Syst. Video Technol. 21(8), 1163\u20131177 (2011)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"1","key":"2_CR32","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava, N., Hinton, G.E., Krizhevsky, A., et al.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929\u20131958 (2014)","journal-title":"J. Mach. Learn. Res."},{"key":"2_CR33","doi-asserted-by":"crossref","first-page":"12506","DOI":"10.1109\/TPAMI.2023.3283067","volume":"45","author":"J Tan","year":"2023","unstructured":"Tan, J., Wang, Y., Wu, G., et al.: Temporal perceiver: a general architecture for arbitrary boundary detection. IEEE Trans. Pattern Anal. Mach. Intell. 45, 12506\u201312520 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2_CR34","doi-asserted-by":"crossref","unstructured":"Tan, J., Wang, H., Yuan, J.: Characters link shots: character attention network for movie scene segmentation. ACM Trans. Multim. Comput. Commun, Appl. 20(4), 1\u201323 (2023)","DOI":"10.1145\/3630257"},{"key":"2_CR35","doi-asserted-by":"crossref","unstructured":"Tapaswi, M., B\u00e4uml, M., Stiefelhagen, R.: StoryGraphs: visualizing character interactions as a timeline. In: CVPR, pp. 827\u2013834 (2014)","DOI":"10.1109\/CVPR.2014.111"},{"key":"2_CR36","unstructured":"Tavenard, R., Faouzi, J., Vandewiele, G., et al.: Tslearn, a machine learning toolkit for time series data. J. Mach. Learn. Res. 21, 118:1\u2013118:6 (2020)"},{"key":"2_CR37","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., et al.: Attention is all you need. In: NIPS, pp. 5998\u20136008 (2017)"},{"key":"2_CR38","doi-asserted-by":"crossref","unstructured":"Wu, H., Chen, K., Luo, Y., Qiao, R., Ren, B., Liu, H., Xie, W., Shen, L.: Scene consistency representation learning for video scene segmentation. In: CVPR, pp. 14001\u201314010 (2022)","DOI":"10.1109\/CVPR52688.2022.01363"},{"key":"2_CR39","doi-asserted-by":"crossref","unstructured":"Xu, M., P\u00e9rez-R\u00faa, J.M., Escorcia, V., et al.: Boundary-sensitive pre-training for temporal localization in videos. In: ICCV, pp. 7200\u20137210 (2021)","DOI":"10.1109\/ICCV48922.2021.00713"},{"key":"2_CR40","unstructured":"Yang, H., et al.: Self-supervised video representation learning with motion-aware masked autoencoders. CoRR abs\/2210.04154 (2022)"},{"issue":"1","key":"2_CR41","doi-asserted-by":"publisher","first-page":"94","DOI":"10.1006\/cviu.1997.0628","volume":"71","author":"MM Yeung","year":"1998","unstructured":"Yeung, M.M., Yeo, B., Liu, B.: Segmentation of video by clustering and graph analysis. Comput. Vis. Image Underst. 71(1), 94\u2013109 (1998)","journal-title":"Comput. Vis. Image Underst."}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-53311-2_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,9]],"date-time":"2024-11-09T09:54:27Z","timestamp":1731146067000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-53311-2_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031533105","9783031533112"],"references-count":41,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-53311-2_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"28 January 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MMM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multimedia Modeling","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Amsterdam","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"The Netherlands","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":"29 January 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 February 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"ConfTool Pro","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"297","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"112","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"38% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.2","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.2","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}