{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T01:18:57Z","timestamp":1779326337075,"version":"3.51.4"},"publisher-location":"Cham","reference-count":42,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030210731","type":"print"},{"value":"9783030210748","type":"electronic"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-030-21074-8_4","type":"book-chapter","created":{"date-parts":[[2019,6,18]],"date-time":"2019-06-18T14:10:14Z","timestamp":1560867014000},"page":"39-54","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":135,"title":["Summarizing Videos with Attention"],"prefix":"10.1007","author":[{"given":"Jiri","family":"Fajtl","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hajar Sadeghi","family":"Sokeh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vasileios","family":"Argyriou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dorothy","family":"Monekosso","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Paolo","family":"Remagnino","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,6,19]]},"reference":[{"issue":"1","key":"4_CR1","doi-asserted-by":"publisher","first-page":"110","DOI":"10.1109\/TIP.2010.2057438","volume":"20","author":"V Argyriou","year":"2011","unstructured":"Argyriou, V.: Sub-hexagonal phase correlation for motion estimation. IEEE Trans. Image Process. 20(1), 110\u2013120 (2011)","journal-title":"IEEE Trans. Image Process."},{"key":"4_CR2","unstructured":"Athiwaratkun, B., Kang, K.: Feature representation in convolutional neural networks. arXiv preprint arXiv:1507.02313 (2015)"},{"key":"4_CR3","unstructured":"Ba, J.L., Kiros, J.R., Hinton, G.E.: Layer normalization. arXiv preprint arXiv:1607.06450 (2016)"},{"key":"4_CR4","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014)"},{"key":"4_CR5","doi-asserted-by":"crossref","unstructured":"Cheng, J., Dong, L., Lapata, M.: Long short-term memory-networks for machine reading. In: Proceedings of the EMNLP, pp. 551\u2013561 (2016)","DOI":"10.18653\/v1\/D16-1053"},{"key":"4_CR6","doi-asserted-by":"crossref","unstructured":"Cho, K., Merrienboer, B., Gulcehre, C., Bougares, F., Schwenk, H., Bengio, Y.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. In: Proceedings of the EMNLP (2014)","DOI":"10.3115\/v1\/D14-1179"},{"issue":"1","key":"4_CR7","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1016\/j.patrec.2010.08.004","volume":"32","author":"SEF De Avila","year":"2011","unstructured":"De Avila, S.E.F., Lopes, A.P.B., da Luz Jr., A., de Albuquerque Ara\u00fajo, A.: VSUMM: a mechanism designed to produce static video summaries and a novel evaluation. Pattern Recogn. Lett. 32(1), 56\u201368 (2011)","journal-title":"Pattern Recogn. Lett."},{"key":"4_CR8","doi-asserted-by":"crossref","unstructured":"Fajtl, J., Argyriou, V., Monekosso, D., Remagnino, P.: AMNet: memorability estimation with attention. In: Proceedings of the IEEE CVPR, pp. 6363\u20136372 (2018)","DOI":"10.1109\/CVPR.2018.00666"},{"issue":"C","key":"4_CR9","doi-asserted-by":"publisher","first-page":"207","DOI":"10.1016\/j.jvcir.2016.12.001","volume":"42","author":"M Fei","year":"2017","unstructured":"Fei, M., Jiang, W., Mao, W.: Memorable and rich video summarization. J. Vis. Commun. Image Represent. 42(C), 207\u2013217 (2017)","journal-title":"J. Vis. Commun. Image Represent."},{"key":"4_CR10","unstructured":"Gehring, J., et al.: Convolutional sequence to sequence learning. In: Proceedings of the ICML, pp. 1243\u20131252, 06\u201311 August 2017"},{"issue":"7626","key":"4_CR11","doi-asserted-by":"publisher","first-page":"471","DOI":"10.1038\/nature20101","volume":"538","author":"A Graves","year":"2016","unstructured":"Graves, A., et al.: Hybrid computing using a neural network with dynamic external memory. Nature 538(7626), 471 (2016)","journal-title":"Nature"},{"key":"4_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"505","DOI":"10.1007\/978-3-319-10584-0_33","volume-title":"Computer Vision \u2013 ECCV 2014","author":"M Gygli","year":"2014","unstructured":"Gygli, M., Grabner, H., Riemenschneider, H., Van Gool, L.: Creating summaries from user videos. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8695, pp. 505\u2013520. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10584-0_33"},{"key":"4_CR13","doi-asserted-by":"crossref","unstructured":"Gygli, M., et al.: Video summarization by learning submodular mixtures of objectives. In: Proceedings of the IEEE CVPR, pp. 3090\u20133098 (2015)","DOI":"10.1109\/CVPR.2015.7298928"},{"issue":"8","key":"4_CR14","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"4_CR15","unstructured":"Ji, Z., Xiong, K., Pang, Y., Li, X.: Video summarization with attention-based encoder-decoder networks. arXiv preprint arXiv:1708.09545 (2017)"},{"key":"4_CR16","doi-asserted-by":"crossref","unstructured":"Khosla, A., Raju, A.S., Torralba, A., Oliva, A.: Understanding and predicting image memorability at a large scale. In: Proceedings of the IEEE ICCV, pp. 2390\u20132398 (2015)","DOI":"10.1109\/ICCV.2015.275"},{"key":"4_CR17","unstructured":"Kingma, D., Ba, J.: Adam: a method for stochastic optimization. In: Proceedings of the ICLR, vol. 5 (2015)"},{"key":"4_CR18","unstructured":"Larkin, K.G.: Reflections on Shannon information: in search of a natural information-entropy for images. CoRR abs\/1609.01117 (2016)"},{"key":"4_CR19","unstructured":"Lin, C.Y.: ROUGE: a package for automatic evaluation of summaries. In: Text Summarization Branches Out: Proceedings of the ACL-2004 Workshop, pp. 74\u201381. Association for Computational Linguistics, Barcelona, July 2004"},{"key":"4_CR20","unstructured":"Lin, Z., et al.: A structured self-attentive sentence embedding. In: Proceedings of the ICLR (2017)"},{"key":"4_CR21","doi-asserted-by":"crossref","unstructured":"Luong, M.T., Pham, H., Manning, C.D.: Effective approaches to attention-based neural machine translation. arXiv preprint arXiv:1508.04025 (2015)","DOI":"10.18653\/v1\/D15-1166"},{"key":"4_CR22","doi-asserted-by":"crossref","unstructured":"Luong, T., Pham, H., Manning, C.D.: Effective approaches to attention-based neural machine translation. In: Proceedings of the EMNLP (2015)","DOI":"10.18653\/v1\/D15-1166"},{"key":"4_CR23","doi-asserted-by":"crossref","unstructured":"Mahasseni, B., Lam, M., Todorovic, S.: Unsupervised video summarization with adversarial LSTM networks. In: Proceedings of the IEEE CVPR, pp. 2982\u20132991 (2017)","DOI":"10.1109\/CVPR.2017.318"},{"key":"4_CR24","unstructured":"Mnih, V., Heess, N., Graves, A., et al.: Recurrent models of visual attention. In: Proceedings of the NIPS, pp. 2204\u20132212 (2014)"},{"key":"4_CR25","unstructured":"Novak, C.L., Shafer, S.A.: Anatomy of a color histogram. In: Proceedings of the IEEE CVPR, pp. 599\u2013605. IEEE (1992)"},{"key":"4_CR26","doi-asserted-by":"publisher","first-page":"361","DOI":"10.1007\/978-3-319-54193-8_23","volume-title":"Computer Vision \u2013 ACCV 2016","author":"Mayu Otani","year":"2017","unstructured":"Otani, M., et al.: Video summarization using deep semantic features. In: Proceedings of the ACCV, pp. 361\u2013377 (2016)"},{"key":"4_CR27","doi-asserted-by":"crossref","unstructured":"Parikh, A., et al.: A decomposable attention model for natural language inference. In: Proceedings of the EMNLP, pp. 2249\u20132255 (2016)","DOI":"10.18653\/v1\/D16-1244"},{"key":"4_CR28","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"540","DOI":"10.1007\/978-3-319-10599-4_35","volume-title":"Computer Vision \u2013 ECCV 2014","author":"D Potapov","year":"2014","unstructured":"Potapov, D., Douze, M., Harchaoui, Z., Schmid, C.: Category-specific video summarization. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8694, pp. 540\u2013555. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10599-4_35"},{"key":"4_CR29","doi-asserted-by":"crossref","unstructured":"Rochan, M., Wang, Y.: Learning video summarization using unpaired data. arXiv preprint arXiv:1805.12174 (2018)","DOI":"10.1109\/CVPR.2019.00809"},{"issue":"3","key":"4_CR30","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M.: Others: imagenet large scale visual recognition challenge. Int. J. Comput. Vision 115(3), 211\u2013252 (2015)","journal-title":"Int. J. Comput. Vision"},{"key":"4_CR31","doi-asserted-by":"publisher","first-page":"1001","DOI":"10.1016\/j.neucom.2015.08.057","volume":"173","author":"L dos Santos Belo","year":"2016","unstructured":"dos Santos Belo, L., Caetano Jr., C.A., do Patroc\u00ednio Jr., Z.K.G., Guimar\u00e3es, S.J.F.: Summarizing video sequence using a graph-based hierarchical approach. Neurocomputing 173, 1001\u20131016 (2016)","journal-title":"Neurocomputing"},{"key":"4_CR32","unstructured":"Song, Y., Vallmitjana, J., Stent, A., Jaimes, A.: TVSum: summarizing web videos using titles. In: Proceedings of the IEEE CVPR, pp. 5179\u20135187 (2015)"},{"key":"4_CR33","doi-asserted-by":"crossref","unstructured":"Szegedy, C., et al.: Going deeper with convolutions. In: Proceedings of the IEEE CVPR, pp. 1\u20139 (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"4_CR34","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Proceedings of the NIPS, pp. 5998\u20136008. Curran Associates, Inc. (2017)"},{"key":"4_CR35","doi-asserted-by":"crossref","unstructured":"Wei, H., Ni, B., Yan, Y., Yu, H., Yang, X., Yao, C.: Video summarization via semantic attended networks. In: Proceedings of the AAAI (2018)","DOI":"10.1609\/aaai.v32i1.11297"},{"key":"4_CR36","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1007\/978-1-4615-3618-5_2","volume-title":"Reinforcement Learning","author":"RJ Williams","year":"1992","unstructured":"Williams, R.J.: Simple statistical gradient-following algorithms for connectionist reinforcement learning. In: Sutton, R.S. (ed.) Reinforcement Learning, pp. 5\u201332. Springer, Boston (1992). https:\/\/doi.org\/10.1007\/978-1-4615-3618-5_2"},{"key":"4_CR37","unstructured":"Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention. In: Proceedings of the ICML, pp. 2048\u20132057 (2015)"},{"key":"4_CR38","doi-asserted-by":"crossref","unstructured":"Yao, L., et al.: Describing videos by exploiting temporal structure. In: Proceedings of the IEEE ICCV, pp. 4507\u20134515 (2015)","DOI":"10.1109\/ICCV.2015.512"},{"issue":"1","key":"4_CR39","doi-asserted-by":"publisher","first-page":"226","DOI":"10.1109\/TCSVT.2017.2771247","volume":"29","author":"Y Yuan","year":"2017","unstructured":"Yuan, Y., Mei, T., Cui, P., Zhu, W.: Video summarization by learning deep side semantic embedding. IEEE Trans. Circuits Syst. Video Technol. 29(1), 226\u2013237 (2017). https:\/\/doi.org\/10.1109\/TCSVT.2017.2771247","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"4_CR40","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"766","DOI":"10.1007\/978-3-319-46478-7_47","volume-title":"Computer Vision \u2013 ECCV 2016","author":"K Zhang","year":"2016","unstructured":"Zhang, K., Chao, W.-L., Sha, F., Grauman, K.: Video summarization with long short-term memory. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9911, pp. 766\u2013782. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46478-7_47"},{"key":"4_CR41","doi-asserted-by":"crossref","unstructured":"Zhao, B., Li, X., Lu, X.: Hierarchical recurrent neural network for video summarization. In: Proceedings of the ACM Multimedia Conference, pp. 863\u2013871 (2017)","DOI":"10.1145\/3123266.3123328"},{"key":"4_CR42","doi-asserted-by":"crossref","unstructured":"Zhou, K., Qiao, Y., Xiang, T.: Deep reinforcement learning for unsupervised video summarization with diversity-representativeness reward. In: Proceedings of the AAAI (2018)","DOI":"10.1609\/aaai.v32i1.12255"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2018 Workshops"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-21074-8_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,21]],"date-time":"2022-09-21T02:32:12Z","timestamp":1663727532000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-21074-8_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030210731","9783030210748"],"references-count":42,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-21074-8_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"19 June 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Perth, WA","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 December 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 December 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/accv2018.net\/","order":11,"name":"conference_url","label":"Conference URL","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":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"979","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":"274","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":"28% - 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","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":"2.7","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}