{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,15]],"date-time":"2025-10-15T10:36:21Z","timestamp":1760524581664,"version":"3.40.3"},"publisher-location":"Cham","reference-count":45,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031533075"},{"type":"electronic","value":"9783031533082"}],"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\/978-3-031-53308-2_15","type":"book-chapter","created":{"date-parts":[[2024,1,27]],"date-time":"2024-01-27T21:37:36Z","timestamp":1706391456000},"page":"199-212","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Find the\u00a0Cliffhanger: Multi-modal Trailerness in\u00a0Soap Operas"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4489-5454","authenticated-orcid":false,"given":"Carlo","family":"Bretti","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9275-5942","authenticated-orcid":false,"given":"Pascal","family":"Mettes","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6980-7027","authenticated-orcid":false,"given":"Hendrik Vincent","family":"Koops","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0369-8857","authenticated-orcid":false,"given":"Daan","family":"Odijk","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5145-3603","authenticated-orcid":false,"given":"Nanne","family":"van Noord","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,1,28]]},"reference":[{"key":"15_CR1","unstructured":"Ba, J.L., Kiros, J.R., Hinton, G.E.: Layer Normalization (2016)"},{"key":"15_CR2","unstructured":"Bordwell, D., Thompson, K., Smith, J.: Film Art: an introduction (2020)"},{"key":"15_CR3","unstructured":"Buchner, J.: ImageHash: a Python perceptual image Hashing module. https:\/\/github.com\/JohannesBuchner\/imagehash (2021)"},{"key":"15_CR4","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo Vadis, Action Recognition? A new model and the kinetics dataset. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"15_CR5","doi-asserted-by":"crossref","unstructured":"Evangelopoulos, G., et al.: Multimodal saliency and fusion for movie summarization based on aural, visual, and textual attention. IEEE Transactions on Multimedia (2013)","DOI":"10.1109\/TMM.2013.2267205"},{"key":"15_CR6","doi-asserted-by":"crossref","unstructured":"Everingham, M., Sivic, J., Zisserman, A.: Hello! My name is... Buffy\u201d - Automatic Naming of Characters in TV Video. In: BMVC (2006)","DOI":"10.5244\/C.20.92"},{"key":"15_CR7","doi-asserted-by":"crossref","unstructured":"Fajtl, J., Sokeh, H.S., Argyriou, V., Monekosso, D., Remagnino, P.: Summarizing Videos with Attention. In: ACCVW (2019)","DOI":"10.1007\/978-3-030-21074-8_4"},{"key":"15_CR8","doi-asserted-by":"crossref","unstructured":"Gygli, M., Grabner, H., Riemenschneider, H., Van Gool, L.: Creating summaries from user videos. In: ECCV (2014)","DOI":"10.1007\/978-3-319-10584-0_33"},{"key":"15_CR9","doi-asserted-by":"crossref","unstructured":"Hanjalic, A., Lagendijk, R.L., Biemond, J.: Automated high-level movie segmentation for advanced video-retrieval systems. IEEE Trans. Circuits Syst. Video Technol. (1999)","DOI":"10.1109\/76.767124"},{"key":"15_CR10","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"15_CR11","doi-asserted-by":"crossref","unstructured":"Huang, J.H., Murn, L., Mrak, M., Worring, M.: GPT2MVS: generative pre-trained transformer-2 for multi-modal video summarization. In: ACM ICMR (2021)","DOI":"10.1145\/3460426.3463662"},{"key":"15_CR12","doi-asserted-by":"crossref","unstructured":"Huang, J.H., Worring, M.: Query-controllable video summarization. In: ACM ICMR (2020)","DOI":"10.1145\/3372278.3390695"},{"key":"15_CR13","doi-asserted-by":"crossref","unstructured":"Huang, Q., Xiong, Y., Rao, A., Wang, J., Lin, D.: MovieNet: a holistic dataset for movie understanding. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58548-8_41"},{"key":"15_CR14","unstructured":"Huang, Q., Xiong, Y., Xiong, Y., Zhang, Y., Lin, D.: From trailers to storylines: an efficient way to learn from movies (2018)"},{"key":"15_CR15","unstructured":"Iashin, V.: Video Features. https:\/\/github.com\/v-iashin\/video_features (2023)"},{"key":"15_CR16","doi-asserted-by":"crossref","unstructured":"Irie, G., Satou, T., Kojima, A., Yamasaki, T., Aizawa, K.: Automatic trailer generation. In: ACM MM (2010)","DOI":"10.1145\/1873951.1874092"},{"key":"15_CR17","doi-asserted-by":"crossref","unstructured":"Ji, Z., Jiao, F., Pang, Y., Shao, L.: Deep attentive and semantic preserving video summarization. Neurocomputing (2020)","DOI":"10.1016\/j.neucom.2020.04.132"},{"key":"15_CR18","doi-asserted-by":"crossref","unstructured":"Ji, Z., Xiong, K., Pang, Y., Li, X.: Video summarization with attention-based encoder\u2013decoder networks. IEEE Trans. Circuits Syst. Video Technol. (2020)","DOI":"10.1109\/TCSVT.2019.2904996"},{"key":"15_CR19","doi-asserted-by":"crossref","unstructured":"Johnson, J., Douze, M., J\u00e9gou, H.: Billion-scale similarity search with GPUs. IEEE Trans. Big Data (2021)","DOI":"10.1109\/TBDATA.2019.2921572"},{"key":"15_CR20","doi-asserted-by":"crossref","unstructured":"Kaushal, V., Kothawade, S., Iyer, R., Ramakrishnan, G.: Realistic video summarization through VISIOCITY: a new benchmark and evaluation framework. In: ACM MMW (2020)","DOI":"10.1145\/3422839.3423064"},{"key":"15_CR21","doi-asserted-by":"crossref","unstructured":"Li, P., Ye, Q., Zhang, L., Yuan, L., Xu, X., Shao, L.: Exploring global diverse attention via pairwise temporal relation for video summarization. Pattern Recogn. (2021)","DOI":"10.1016\/j.patcog.2020.107677"},{"key":"15_CR22","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Dollar, P.: Focal loss for dense object detection. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"15_CR23","doi-asserted-by":"crossref","unstructured":"Liu, Y.T., Li, Y.J., Yang, F.E., Chen, S.F., Wang, Y.C.F.: Learning hierarchical self-attention for video summarization. In: ICIP (2019)","DOI":"10.1109\/ICIP.2019.8803639"},{"key":"15_CR24","doi-asserted-by":"crossref","unstructured":"Mahasseni, B., Lam, M., Todorovic, S.: Unsupervised video summarization with adversarial LSTM networks. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.318"},{"key":"15_CR25","unstructured":"Papalampidi, P., Keller, F., Lapata, M.: Film trailer generation via task decomposition (2021)"},{"key":"15_CR26","doi-asserted-by":"crossref","unstructured":"Reimers, N., Gurevych, I.: Sentence-BERT: sentence embeddings using Siamese BERT-networks. In: EMNLP (2019)","DOI":"10.18653\/v1\/D19-1410"},{"key":"15_CR27","doi-asserted-by":"crossref","unstructured":"Reimers, N., Gurevych, I.: Making monolingual sentence embeddings multilingual using knowledge distillation. In: EMNLP (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.365"},{"key":"15_CR28","doi-asserted-by":"crossref","unstructured":"Smeaton, A.F., Lehane, B., O\u2019Connor, N.E., Brady, C., Craig, G.: Automatically selecting shots for action movie trailers. In: ACM ICMR (2006)","DOI":"10.1145\/1178677.1178709"},{"key":"15_CR29","doi-asserted-by":"crossref","unstructured":"Smith, J.R., Joshi, D., Huet, B., Hsu, W., Cota, J.: Harnessing A.I. for augmenting creativity: application to movie trailer creation. In: ACM MM (2017)","DOI":"10.1145\/3123266.3127906"},{"key":"15_CR30","doi-asserted-by":"crossref","unstructured":"Snoek, C.G.M., Worring, M., Smeulders, A.W.M.: Early versus late fusion in semantic video analysis. In: ACM MM (2005)","DOI":"10.1145\/1101149.1101236"},{"key":"15_CR31","unstructured":"Song, Y., Vallmitjana, J., Stent, A., Jaimes, A.: TVSum: summarizing web videos using titles. In: CVPR (2015)"},{"key":"15_CR32","unstructured":"Sou\u010dek, T., Loko\u010d, J.: TransNet V2: an effective deep network architecture for fast shot transition detection (2020)"},{"key":"15_CR33","doi-asserted-by":"crossref","unstructured":"Tapaswi, M., Zhu, Y., Stiefelhagen, R., Torralba, A., Urtasun, R., Fidler, S.: MovieQA: understanding stories in movies through question-answering. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.501"},{"key":"15_CR34","doi-asserted-by":"crossref","unstructured":"Turner, G.: Cultural Identity, Soap Narrative, and Reality TV. Television & New Media (2005)","DOI":"10.1177\/1527476405279864"},{"key":"15_CR35","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NeurIPS (2017)"},{"key":"15_CR36","doi-asserted-by":"crossref","unstructured":"von Wenzlawowicz, T., Herzog, O.: Semantic video abstracting: automatic generation of movie trailers based on video patterns. In: SETN (2012)","DOI":"10.1007\/978-3-642-30448-4_44"},{"key":"15_CR37","doi-asserted-by":"crossref","unstructured":"Wang, L., Liu, D., Puri, R., Metaxas, D.N.: Learning trailer moments in full-length movies with co-contrastive attention. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58523-5_18"},{"key":"15_CR38","doi-asserted-by":"crossref","unstructured":"Wang, W., Wei, F., Dong, L., Bao, H., Yang, N., Zhou, M.: MiniLM: Deep self-attention distillation for task-agnostic compression of pre-trained transformers. In: NeurIPS (2020)","DOI":"10.18653\/v1\/2021.findings-acl.188"},{"key":"15_CR39","doi-asserted-by":"crossref","unstructured":"Wu, C.Y., Krahenbuhl, P.: Towards long-form video understanding. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00192"},{"key":"15_CR40","unstructured":"Xu, H., Zhen, Y., Zha, H.: Trailer generation via a point process-based visual attractiveness model. In: IJCAI (2015)"},{"key":"15_CR41","doi-asserted-by":"crossref","unstructured":"Zhang, K., Chao, W.L., Sha, F., Grauman, K.: Video summarization with long short-term memory. In: ECCV (2016)","DOI":"10.1007\/978-3-319-46478-7_47"},{"key":"15_CR42","doi-asserted-by":"crossref","unstructured":"Zhao, B., Gong, M., Li, X.: Hierarchical multimodal transformer to summarize videos. Neurocomputing (2022)","DOI":"10.1016\/j.neucom.2021.10.039"},{"key":"15_CR43","doi-asserted-by":"crossref","unstructured":"Zhao, B., Li, X., Lu, X.: Hierarchical recurrent neural network for video summarization. In: ACM MM (2017)","DOI":"10.1145\/3123266.3123328"},{"key":"15_CR44","doi-asserted-by":"crossref","unstructured":"Zhao, B., Li, X., Lu, X.: HSA-RNN: hierarchical structure-adaptive RNN for video summarization. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00773"},{"key":"15_CR45","doi-asserted-by":"crossref","unstructured":"Zhao, B., Li, X., Lu, X.: TTH-RNN: tensor-train hierarchical recurrent neural network for video summarization. IEEE Trans. Ind. Electron. (2021)","DOI":"10.1109\/TIE.2020.2979573"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-53308-2_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T11:09:35Z","timestamp":1710241775000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-53308-2_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031533075","9783031533082"],"references-count":45,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-53308-2_15","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)"}}]}}