{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T23:41:43Z","timestamp":1780357303836,"version":"3.54.1"},"reference-count":53,"publisher":"Springer Science and Business Media LLC","issue":"12","license":[{"start":{"date-parts":[[2021,2,12]],"date-time":"2021-02-12T00:00:00Z","timestamp":1613088000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,2,12]],"date-time":"2021-02-12T00:00:00Z","timestamp":1613088000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"name":"TUBITAK","award":["116E685"],"award-info":[{"award-number":["116E685"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2021,5]]},"DOI":"10.1007\/s11042-020-10293-x","type":"journal-article","created":{"date-parts":[[2021,2,12]],"date-time":"2021-02-12T18:22:34Z","timestamp":1613154154000},"page":"17827-17847","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":24,"title":["Using independently recurrent networks for reinforcement learning based unsupervised video summarization"],"prefix":"10.1007","volume":"80","author":[{"given":"Gokhan","family":"Yaliniz","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8644-2875","authenticated-orcid":false,"given":"Nazli","family":"Ikizler-Cinbis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,2,12]]},"reference":[{"key":"10293_CR1","doi-asserted-by":"crossref","unstructured":"Cai S, Zuo W, Davis LS, Zhang L (2018) Weakly-supervised video summarization using variational encoder-decoder and web prior. In: Proceedings of the European conference on computer vision (ECCV), pp 184\u2013200","DOI":"10.1007\/978-3-030-01264-9_12"},{"key":"10293_CR2","doi-asserted-by":"crossref","unstructured":"Casas LL, Koblents E (2019) Video summarization with lstm and deep attention models. In: International conference on multimedia modeling. Springer, pp 67\u201379","DOI":"10.1007\/978-3-030-05716-9_6"},{"key":"10293_CR3","doi-asserted-by":"crossref","unstructured":"Chakraborty S, Tickoo O, Iyer R (2015) Adaptive keyframe selection for video summarization. In: 2015 IEEE winter conference on applications of computer vision. IEEE, pp 702\u2013709","DOI":"10.1109\/WACV.2015.99"},{"key":"10293_CR4","unstructured":"Chung J, Gulcehre C, Cho K, Bengio Y (2014) Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv:1412.3555"},{"issue":"1","key":"10293_CR5","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 SEF, Lopes APB, da Luz A Jr, de Albuquerque Ara\u00fajo A (2011) Vsumm: a mechanism designed to produce static video summaries and a novel evaluation method. Pattern Recognit Lett 32(1):56\u201368","journal-title":"Pattern Recognit Lett"},{"key":"10293_CR6","doi-asserted-by":"crossref","unstructured":"Deng J, Dong W, Socher R, Li LJ, Li K, Fei-Fei L (2009) Imagenet: a large-scale hierarchical image database. In: 2009 IEEE conference on computer vision and pattern recognition. IEEE, pp 248\u2013255","DOI":"10.1109\/CVPR.2009.5206848"},{"issue":"7","key":"10293_CR7","doi-asserted-by":"publisher","first-page":"1031","DOI":"10.1016\/j.jvcir.2012.06.013","volume":"23","author":"N Ejaz","year":"2012","unstructured":"Ejaz N, Tariq TB, Baik SW (2012) Adaptive key frame extraction for video summarization using an aggregation mechanism. J Vis Commun Image Represent 23(7):1031\u20131040","journal-title":"J Vis Commun Image Represent"},{"key":"10293_CR8","doi-asserted-by":"crossref","unstructured":"Elfeki M, Borji A (2019) Video summarization via actionness ranking. In: 2019 IEEE Winter conference on applications of computer vision (WACV). IEEE, pp 754\u2013763","DOI":"10.1109\/WACV.2019.00085"},{"key":"10293_CR9","doi-asserted-by":"crossref","unstructured":"Fu TJ, Tai SH, Chen HT (2019) Attentive and adversarial learning for video summarization. In: 2019 IEEE Winter conference on applications of computer vision (WACV). IEEE, pp 1579\u20131587","DOI":"10.1109\/WACV.2019.00173"},{"key":"10293_CR10","doi-asserted-by":"crossref","unstructured":"Garcia del Molino A, Gygli M (2018) Phd-gifs: personalized highlight detection for automatic gif creation. In: Proceedings of the 26th ACM international conference on multimedia, pp 600\u2013608","DOI":"10.1145\/3240508.3240599"},{"issue":"3","key":"10293_CR11","doi-asserted-by":"publisher","first-page":"347","DOI":"10.1023\/A:1009630817712","volume":"11","author":"A Girgensohn","year":"2000","unstructured":"Girgensohn A, Boreczky J (2000) Time-constrained keyframe selection technique. Multimed Tools Appl 11(3):347\u2013358","journal-title":"Multimed Tools Appl"},{"key":"10293_CR12","unstructured":"Gong B, Chao WL, Grauman K, Sha F (2014) Diverse sequential subset selection for supervised video summarization. In: Advances in neural information processing systems, pp 2069\u20132077"},{"key":"10293_CR13","doi-asserted-by":"crossref","unstructured":"Gygli M, Grabner H, Riemenschneider H, Van Gool L (2014) Creating summaries from user videos. In: European conference on computer vision. Springer, pp 505\u2013520","DOI":"10.1007\/978-3-319-10584-0_33"},{"key":"10293_CR14","doi-asserted-by":"crossref","unstructured":"Gygli M, Grabner H, Van Gool L (2015) Video summarization by learning submodular mixtures of objectives. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3090\u20133098","DOI":"10.1109\/CVPR.2015.7298928"},{"issue":"8","key":"10293_CR15","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 (1997) Long short-term memory. Neural Comput 9(8):1735\u20131780","journal-title":"Neural Comput"},{"key":"10293_CR16","unstructured":"Hochreiter S, Schmidhuber J (1997) Lstm can solve hard long time lag problems. In: Advances in neural information processing systems, pp 473\u2013479"},{"issue":"2","key":"10293_CR17","doi-asserted-by":"publisher","first-page":"577","DOI":"10.1109\/TCSVT.2019.2890899","volume":"30","author":"C Huang","year":"2019","unstructured":"Huang C, Wang H (2019) Novel key-frames selection framework for comprehensive video summarization. IEEE Trans Circuits Syst Video Technol 30 (2):577\u2013589","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"issue":"6","key":"10293_CR18","doi-asserted-by":"publisher","first-page":"2654","DOI":"10.1109\/TIP.2018.2889265","volume":"28","author":"S Huang","year":"2019","unstructured":"Huang S, Li X, Zhang Z, Wu F, Han J (2019) User-ranking video summarization with multi-stage spatio\u2013temporal representation. IEEE Trans Image Process 28(6):2654\u20132664","journal-title":"IEEE Trans Image Process"},{"key":"10293_CR19","doi-asserted-by":"publisher","first-page":"152","DOI":"10.1016\/j.ins.2018.09.050","volume":"478","author":"Z Ji","year":"2019","unstructured":"Ji Z, Ma Y, Pang Y, Li X (2019) Query-aware sparse coding for web multi-video summarization. Inf Sci 478:152\u2013166","journal-title":"Inf Sci"},{"key":"10293_CR20","unstructured":"Ju Z, Lin W, Yang MY, Zhang B, Luo C, Lin CW, Mei T (2016) A representative-based framework for parsing and summarizing events in surveillance videos. In: 2016 IEEE International conference on multimedia & expo workshops (ICMEW). IEEE, pp 1\u20136"},{"key":"10293_CR21","doi-asserted-by":"crossref","unstructured":"Jung Y, Cho D, Kim D, Woo S, Kweon IS (2018) Discriminative feature learning for unsupervised video summarization. arXiv:1811.09791","DOI":"10.1609\/aaai.v33i01.33018537"},{"key":"10293_CR22","unstructured":"Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. arXiv:1412.6980"},{"key":"10293_CR23","doi-asserted-by":"crossref","unstructured":"Lal S, Duggal S, Sreedevi I (2019) Online video summarization: predicting future to better summarize present. In: 2019 IEEE Winter conference on applications of computer vision (WACV). IEEE, pp 471\u2013480","DOI":"10.1109\/WACV.2019.00056"},{"issue":"1","key":"10293_CR24","first-page":"1","volume":"18","author":"HC Lee","year":"2003","unstructured":"Lee HC, Kim SD (2003) Iterative key frame selection in the rate-constraint environment. Signal Process: Image Commun 18(1):1\u201315","journal-title":"Signal Process: Image Commun"},{"issue":"7","key":"10293_CR25","doi-asserted-by":"crossref","first-page":"2126","DOI":"10.1109\/TCSVT.2018.2860797","volume":"29","author":"J Lei","year":"2018","unstructured":"Lei J, Luan Q, Song X, Liu X, Tao D, Song M (2018) Action parsing driven video summarization based on reinforcement learning. IEEE Trans Circuits Syst Video Technol 29(7):2126\u20132137","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"issue":"8","key":"10293_CR26","doi-asserted-by":"publisher","first-page":"3652","DOI":"10.1109\/TIP.2017.2695887","volume":"26","author":"X Li","year":"2017","unstructured":"Li X, Zhao B, Lu X (2017) A general framework for edited video and raw video summarization. IEEE Trans Image Process 26(8):3652\u20133664","journal-title":"IEEE Trans Image Process"},{"key":"10293_CR27","doi-asserted-by":"crossref","unstructured":"Li S, Li W, Cook C, Zhu C, Gao Y (2018) Independently recurrent neural network (indrnn): building a longer and deeper rnn. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5457\u20135466","DOI":"10.1109\/CVPR.2018.00572"},{"key":"10293_CR28","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1016\/j.neucom.2014.12.044","volume":"155","author":"W Lin","year":"2015","unstructured":"Lin W, Zhang Y, Lu J, Zhou B, Wang J, Zhou Y (2015) Summarizing surveillance videos with local-patch-learning-based abnormality detection, blob sequence optimization, and type-based synopsis. Neurocomputing 155:84\u201398","journal-title":"Neurocomputing"},{"key":"10293_CR29","doi-asserted-by":"crossref","unstructured":"Mahasseni B, Lam M, Todorovic S (2017) Unsupervised video summarization with adversarial lstm networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 202\u2013211","DOI":"10.1109\/CVPR.2017.318"},{"issue":"3","key":"10293_CR30","doi-asserted-by":"publisher","first-page":"447","DOI":"10.1109\/TCSVT.2009.2013517","volume":"19","author":"C Panagiotakis","year":"2009","unstructured":"Panagiotakis C, Doulamis A, Tziritas G (2009) Equivalent key frames selection based on iso-content principles. IEEE Trans Circuits Syst Video Technol 19(3):447\u2013451","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"10293_CR31","doi-asserted-by":"crossref","unstructured":"Panagiotakis C, Papadakis H, Fragopoulou P (2020) Personalized video summarization based exclusively on user preferences. In: European conference on information retrieval. Springer, pp 305\u2013311","DOI":"10.1007\/978-3-030-45442-5_38"},{"issue":"87","key":"10293_CR32","first-page":"464","volume":"18","author":"B Parlett","year":"1964","unstructured":"Parlett B (1964) Laguerre\u2019s method applied to the matrix eigenvalue problem. Math Comput 18(87):464\u2013485","journal-title":"Math Comput"},{"key":"10293_CR33","doi-asserted-by":"crossref","unstructured":"Potapov D, Douze M, Harchaoui Z, Schmid C (2014) Category-specific video summarization. In: European conference on computer vision. Springer, pp 540\u2013555","DOI":"10.1007\/978-3-319-10599-4_35"},{"key":"10293_CR34","doi-asserted-by":"crossref","unstructured":"Rochan M, Ye L, Wang Y (2018) Video summarization using fully convolutional sequence networks. In: Proceedings of the European conference on computer vision (ECCV), pp 347\u2013363","DOI":"10.1007\/978-3-030-01258-8_22"},{"key":"10293_CR35","doi-asserted-by":"crossref","unstructured":"Sharghi A, Gong B, Shah M (2016) Query-focused extractive video summarization. In: European conference on computer vision. Springer, pp 3\u201319","DOI":"10.1007\/978-3-319-46484-8_1"},{"key":"10293_CR36","doi-asserted-by":"crossref","unstructured":"Sharghi A, Laurel JS, Gong B (2017) Query-focused video summarization: dataset, evaluation, and a memory network based approach. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4788\u20134797","DOI":"10.1109\/CVPR.2017.229"},{"key":"10293_CR37","unstructured":"Song Y, Vallmitjana J, Stent A, Jaimes A (2015) Tvsum: summarizing web videos using titles. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5179\u20135187"},{"key":"10293_CR38","doi-asserted-by":"crossref","unstructured":"Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2015) Going deeper with convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1\u20139","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"10293_CR39","doi-asserted-by":"crossref","unstructured":"Wang L, Zhu Y, Pan H (2019) Unsupervised reinforcement learning for video summarization reward function. In: Proceedings of the 2019 international conference on image, video and signal processing. ACM, pp 40\u201344","DOI":"10.1145\/3317640.3317658"},{"issue":"3\u20134","key":"10293_CR40","first-page":"229","volume":"8","author":"RJ Williams","year":"1992","unstructured":"Williams RJ (1992) Simple statistical gradient-following algorithms for connectionist reinforcement learning. Mach Learn 8(3\u20134):229\u2013256","journal-title":"Mach Learn"},{"key":"10293_CR41","doi-asserted-by":"publisher","first-page":"29245","DOI":"10.1007\/s11042-018-5953-1","volume":"77","author":"J Wu","year":"2018","unstructured":"Wu J, Zhong SH, Ma Z, Heinen SJ, Jiang J (2018) Foveated convolutional neural networks for video summarization. Multimed Tools Appl 77:29245\u201329267","journal-title":"Multimed Tools Appl"},{"key":"10293_CR42","doi-asserted-by":"crossref","unstructured":"Xu J, Mukherjee L, Li Y, Warner J, Rehg JM, Singh V (2015) Gaze-enabled egocentric video summarization via constrained submodular maximization. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2235\u20132244","DOI":"10.1109\/CVPR.2015.7298836"},{"key":"10293_CR43","doi-asserted-by":"crossref","unstructured":"Yao T, Mei T, Rui Y (2016) Highlight detection with pairwise deep ranking for first-person video summarization. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 982\u2013990","DOI":"10.1109\/CVPR.2016.112"},{"key":"10293_CR44","doi-asserted-by":"crossref","unstructured":"Yuan L, Tay FE, Li P, Zhou L, Feng J (2019) Cycle-sum: cycle-consistent adversarial lstm networks for unsupervised video summarization. arXiv:1904.08265","DOI":"10.1609\/aaai.v33i01.33019143"},{"key":"10293_CR45","doi-asserted-by":"crossref","unstructured":"Zhang K, Chao WL, Sha F, Grauman K (2016) Summary transfer: exemplar-based subset selection for video summarization. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1059\u20131067","DOI":"10.1109\/CVPR.2016.120"},{"key":"10293_CR46","doi-asserted-by":"crossref","unstructured":"Zhang K, Chao WL, Sha F, Grauman K (2016) Video summarization with long short-term memory. In: European conference on computer vision. Springer, pp 766\u2013782","DOI":"10.1007\/978-3-319-46478-7_47"},{"key":"10293_CR47","doi-asserted-by":"crossref","unstructured":"Zhang K, Grauman K, Sha F (2018) Retrospective encoders for video summarization. In: Proceedings of the European conference on computer vision (ECCV), pp 383\u2013399","DOI":"10.1007\/978-3-030-01237-3_24"},{"key":"10293_CR48","unstructured":"Zhang Y, Kampffmeyer M, Liang X, Tan M, Xing EP (2018) Query-conditioned three-player adversarial network for video summarization. arXiv:1807.06677"},{"issue":"24","key":"10293_CR49","doi-asserted-by":"publisher","first-page":"35237","DOI":"10.1007\/s11042-019-08175-y","volume":"78","author":"Y Zhang","year":"2019","unstructured":"Zhang Y, Kampffmeyer M, Liang X, Zhang D, Tan M, Xing EP (2019) Dilated temporal relational adversarial network for generic video summarization. Multimed Tools Appl 78(24):35237\u201335261","journal-title":"Multimed Tools Appl"},{"issue":"4","key":"10293_CR50","doi-asserted-by":"publisher","first-page":"750","DOI":"10.3390\/app9040750","volume":"9","author":"Y Zhang","year":"2019","unstructured":"Zhang Y, Kampffmeyer M, Zhao X, Tan M (2019) Deep reinforcement learning for query-conditioned video summarization. Appl Sci 9(4):750","journal-title":"Appl Sci"},{"key":"10293_CR51","doi-asserted-by":"crossref","unstructured":"Zhao B, Li X, Lu X (2018) Hsa-rnn: hierarchical structure-adaptive rnn for video summarization. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7405\u20137414","DOI":"10.1109\/CVPR.2018.00773"},{"key":"10293_CR52","doi-asserted-by":"publisher","first-page":"224","DOI":"10.1016\/j.neucom.2018.12.040","volume":"332","author":"SH Zhong","year":"2019","unstructured":"Zhong SH, Wu J, Jiang J (2019) Video summarization via spatio-temporal deep architecture. Neurocomputing 332:224\u2013235","journal-title":"Neurocomputing"},{"key":"10293_CR53","doi-asserted-by":"crossref","unstructured":"Zhou K, Qiao Y, Xiang T (2018) Deep reinforcement learning for unsupervised video summarization with diversity-representativeness reward. In: Thirty-second AAAI conference on artificial intelligence","DOI":"10.1609\/aaai.v32i1.12255"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-020-10293-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-020-10293-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-020-10293-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,17]],"date-time":"2022-12-17T02:05:04Z","timestamp":1671242704000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-020-10293-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,2,12]]},"references-count":53,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2021,5]]}},"alternative-id":["10293"],"URL":"https:\/\/doi.org\/10.1007\/s11042-020-10293-x","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,2,12]]},"assertion":[{"value":"31 December 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 September 2020","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 December 2020","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 February 2021","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}