{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T14:05:57Z","timestamp":1774533957796,"version":"3.50.1"},"reference-count":53,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2020,10,12]],"date-time":"2020-10-12T00:00:00Z","timestamp":1602460800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,10,12]],"date-time":"2020-10-12T00:00:00Z","timestamp":1602460800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"name":"National High Technology Re-search and Development Program of China","award":["ZZKT2018A09"],"award-info":[{"award-number":["ZZKT2018A09"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61321491"],"award-info":[{"award-number":["61321491"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61272219"],"award-info":[{"award-number":["61272219"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004602","name":"Program for New Century Excellent Talents in University","doi-asserted-by":"publisher","award":["NCET-04-04605"],"award-info":[{"award-number":["NCET-04-04605"]}],"id":[{"id":"10.13039\/501100004602","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100011246","name":"State Key Laboratory of Novel Software Technology","doi-asserted-by":"publisher","award":["ZZKT2018A09"],"award-info":[{"award-number":["ZZKT2018A09"]}],"id":[{"id":"10.13039\/501100011246","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2021,2]]},"DOI":"10.1007\/s11042-020-09888-1","type":"journal-article","created":{"date-parts":[[2020,10,12]],"date-time":"2020-10-12T09:02:58Z","timestamp":1602493378000},"page":"6121-6141","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Crowd aware summarization of surveillance videos by deep reinforcement learning"],"prefix":"10.1007","volume":"80","author":[{"given":"Junfeng","family":"Xu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7137-6169","authenticated-orcid":false,"given":"Zhengxing","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chen","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,10,12]]},"reference":[{"issue":"2","key":"9888_CR1","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1109\/72.279181","volume":"5","author":"Y Bengio","year":"1994","unstructured":"Bengio Y, Simard PY, Frasconi P (1994) Learning long-term dependencies with gradient descent is difficult. IEEE Trans Neural Netw 5(2):157\u2013166","journal-title":"IEEE Trans Neural Netw"},{"key":"9888_CR2","volume-title":"Selection bias and covariate imbalances in randomized clinical trials","author":"V Berger","year":"2007","unstructured":"Berger V (2007) Selection bias and covariate imbalances in randomized clinical trials, vol 66. Sons, John Wiley & Sons"},{"key":"9888_CR3","unstructured":"Chao W-L, Gong B, Grauman K, Sha F (2015) Large-margin Determinantal point processes. UAI:191\u2013200"},{"key":"9888_CR4","doi-asserted-by":"crossref","unstructured":"Deng J, Dong W, Socher R, Li L-J, Li K, Li F-F (2009) Imagenet: a large-scale hierarchical image database. CVPR:248\u2013255","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"9888_CR5","doi-asserted-by":"publisher","first-page":"8247","DOI":"10.1609\/aaai.v33i01.33018247","volume":"33","author":"W Dong","year":"2019","unstructured":"Dong W, Zhang Z, Tan T (2019) Attention-aware sampling via deep reinforcement learning for action recognition. AAAI 33:8247\u20138254","journal-title":"AAAI"},{"key":"9888_CR6","doi-asserted-by":"crossref","unstructured":"Feng L, Li Z, Kuang Z, Zhang W (2018) Extractive video summarizer with memory augmented neural networks. ACM Multiedia:976\u2013983","DOI":"10.1145\/3240508.3240651"},{"key":"9888_CR7","doi-asserted-by":"crossref","unstructured":"Ferryman JM, Pets AE (2010) Dataset and challenge. AVSS 2010:143\u2013150","DOI":"10.1109\/AVSS.2010.90"},{"key":"9888_CR8","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/j.inffus.2014.09.005","volume":"24","author":"H Fradi","year":"2015","unstructured":"Fradi H, Dugelay J-L (2015) Towards crowd density-aware video surveillance applications. Information Fusion 24:3\u201315","journal-title":"Information Fusion"},{"issue":"7","key":"9888_CR9","doi-asserted-by":"publisher","first-page":"1101","DOI":"10.1007\/s00138-018-0954-7","volume":"29","author":"Z Gao","year":"2018","unstructured":"Gao Z, Lu G, Lyu C, Yan P (2018) Key-frame selection for automatic summarization of surveillance videos: a method of multiple change-point detection. Mach Vis Appl 29(7):1101\u20131117","journal-title":"Mach Vis Appl"},{"key":"9888_CR10","unstructured":"Gong B, Chao W-L, Grauman K, Sha F (2014) Diverse sequential subset selection for supervised video summarization. NIPS:2069\u20132077"},{"key":"9888_CR11","doi-asserted-by":"crossref","unstructured":"Gygli M, Grabner H, Riemenschneider H, Van Gool L (2014) Creating summaries from user videos. ECCV:505\u2013520","DOI":"10.1007\/978-3-319-10584-0_33"},{"key":"9888_CR12","doi-asserted-by":"crossref","unstructured":"Gygli M, Grabner H, Van Gool L (2015) Video summarization by learning submodular mixtures of objectives. CVPR:3090\u20133098","DOI":"10.1109\/CVPR.2015.7298928"},{"issue":"8","key":"9888_CR13","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"},{"issue":"4","key":"9888_CR14","doi-asserted-by":"publisher","first-page":"35:1","DOI":"10.1145\/2043612.2043613","volume":"7","author":"R Hong","year":"2011","unstructured":"Hong R, Tang J, Tan H-K, Ngo C-W, Yan S, Chua T-S (2011) Event driven summarization for web videos. TOMCCAP 7(4):35:1\u201335:18","journal-title":"TOMCCAP"},{"key":"9888_CR15","doi-asserted-by":"crossref","unstructured":"Idress H, Tayyab M, Athrey K, Dong Z, AI-Maadeed S, Rajpoot NM, Shah M (2018) Composition loss for counting, density map estimation and localization in dense crowds. ECCV:544\u2013559","DOI":"10.1007\/978-3-030-01216-8_33"},{"key":"9888_CR16","doi-asserted-by":"publisher","first-page":"3959","DOI":"10.1609\/aaai.v33i01.33013959","volume":"33","author":"J Janisch","year":"2019","unstructured":"Janisch J, Pevny T, Lisy V (2019) Classification with costly features using deep reinforcement learning. AAAI 33:3959\u20133966","journal-title":"AAAI"},{"key":"9888_CR17","unstructured":"Jay N, Rotman NH, Godfrey B, Schapira M, Tamar A (2019) A deep reinforcement learning perspective on internet congestion control. ICML:3050\u20133059"},{"key":"9888_CR18","unstructured":"Kang H-W, Matsushita Y, Tang X, Chen X-Q (2006) Space-time video montage. CVPR:1331\u20131338"},{"key":"9888_CR19","doi-asserted-by":"crossref","unstructured":"Khosla A, Hamid R, Lin C-J, Sundaresan N (2013) Large-scale video summarization using web-image priors. CVPR:2698\u20132705","DOI":"10.1109\/CVPR.2013.348"},{"key":"9888_CR20","unstructured":"Kingma DP, Ba J (2015) Adam: a method for stochastic optimization. In: ICLR"},{"key":"9888_CR21","unstructured":"Lee YJ, Ghosh J, Grauman K (2012) Discovering important people and objects for egocentric video summarization. CVPR:1346\u20131353"},{"key":"9888_CR22","doi-asserted-by":"crossref","unstructured":"Lei Z, Zhang C, Zhang Q, Qiu G (2019) FrameRank: a text processing approach to video summarization. ICME:368\u2013373","DOI":"10.1109\/ICME.2019.00071"},{"key":"9888_CR23","doi-asserted-by":"crossref","unstructured":"Li Y, Merialdo B (2011) Multi-video summarization based on OB-MMR. CBMI:163\u2013168","DOI":"10.1109\/CBMI.2011.5972539"},{"issue":"24","key":"9888_CR24","doi-asserted-by":"publisher","first-page":"17393","DOI":"10.1007\/s11042-015-3003-9","volume":"75","author":"Q Li","year":"2016","unstructured":"Li Q, Sun Z, Chen S, S-m X (2016) Dynamic node selection in camera networks based on approximate reinforcement learning. Multimed Tools Appl 75(24):17393\u201317419","journal-title":"Multimed Tools Appl"},{"key":"9888_CR25","unstructured":"Li JZN, Kong W, Liu S, Li TH, Li G (2019) Graph convolutional label noise cleaner: train a plug-and-play action classifier for anomaly detection. CVPR:1237\u20131246"},{"key":"9888_CR26","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, Yu Z (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":"9888_CR27","doi-asserted-by":"crossref","unstructured":"Liu T, Kender JR (2002) Optimization algorithms for the selection of key frame sequences of variable length. ECCV:403\u2013417","DOI":"10.1007\/3-540-47979-1_27"},{"key":"9888_CR28","doi-asserted-by":"crossref","unstructured":"Lu Z, Grauman K (2013) Story-driven summarization for egocentric video. CVPR:2714\u20132721","DOI":"10.1109\/CVPR.2013.350"},{"issue":"5","key":"9888_CR29","doi-asserted-by":"publisher","first-page":"6309","DOI":"10.1007\/s11042-016-3263-z","volume":"76","author":"G Lu","year":"2017","unstructured":"Lu G, Zhou Y, Li X, Yan P (2017) Unsupervised, efficient and scalable key-frame selection for automatic summarization of surveillance videos. Multimed Tools Appl 76(5):6309\u20136331","journal-title":"Multimed Tools Appl"},{"key":"9888_CR30","doi-asserted-by":"crossref","unstructured":"Lu X, Wang W, Ma C, Shen J, Shao L, Porkli F (2019) See more, know more: unsupervised video object segmentation with co-attention siamese networks. CVPR:3623\u20133632","DOI":"10.1109\/CVPR.2019.00374"},{"key":"9888_CR31","unstructured":"Lv P, Liu S, Mingliang X, Zhou B (2018) Abnormal Event Detection and Location for Dense Crowds using Repulsive Forces and Sparse Reconstruction. CoRR abs\/1808.:06749"},{"key":"9888_CR32","doi-asserted-by":"crossref","unstructured":"Ma Y-F, Lie L, Zhang HJ, Li M (2002) A user attention model for video summarization. ACM Multimedia:533\u2013542","DOI":"10.1145\/641007.641116"},{"key":"9888_CR33","doi-asserted-by":"crossref","unstructured":"Mahasseni B, Lam M, Todorovi S (2017) Unsupervised video summarization with adversarial LSTM networks. CVPR:2982\u20132991","DOI":"10.1109\/CVPR.2017.318"},{"issue":"2","key":"9888_CR34","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1007\/s00799-005-0129-9","volume":"6","author":"P Mundur","year":"2006","unstructured":"Mundur P, Rao Y, Yesha Y (2006) Keyframe-based video summarization using delaunay clustering. Int J Digit Libr 6(2):219\u2013232","journal-title":"Int J Digit Libr"},{"key":"9888_CR35","unstructured":"Ng JY-H, Hausknecht MJ, Vijayanarasimhan S, Vinyals O, Monga R, Toderici G (2015) Beyond short snippets: deep networks for video classification. CVPR:4694\u20134702"},{"key":"9888_CR36","unstructured":"Ngo C-W, Ma Y-F, Zhang HJ (2003) Automatic video summarization by graph modeling. ICCV:104\u2013109"},{"key":"9888_CR37","doi-asserted-by":"crossref","unstructured":"Potapov D, Douze M, Harchaoui Z, Schmid C (2014) Category-specific video summarization. ECCV:540\u2013555","DOI":"10.1007\/978-3-319-10599-4_35"},{"key":"9888_CR38","doi-asserted-by":"crossref","unstructured":"Pritch Y, Rav-Acha A, Gutman A, Peleg S (2007) Webcam synopsis: peeking around the world. ICCV:1\u20138","DOI":"10.1109\/ICCV.2007.4408934"},{"key":"9888_CR39","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1016\/j.engappai.2015.01.007","volume":"41","author":"SAM Saleh","year":"2015","unstructured":"Saleh SAM, Suandi SA, Lbrahim H (2015) Recent survey on crowd density estimation and counting for visual surveillance. Eng Appl Artif Intell 41:103\u2013114","journal-title":"Eng Appl Artif Intell"},{"key":"9888_CR40","doi-asserted-by":"crossref","unstructured":"Sharghi A, Lurel JS, Gong B (2017) Query-focused video summarization: dataset, evaluation, and a memory network based approach. CVPR:2127\u20132136","DOI":"10.1109\/CVPR.2017.229"},{"key":"9888_CR41","doi-asserted-by":"crossref","unstructured":"Sindagi VA, Patel VM (2017) CNN-based cascaded multi-task learning of high-level Priorand density estimation for crowd counting. AVSS:1\u20136","DOI":"10.1109\/AVSS.2017.8078491"},{"key":"9888_CR42","unstructured":"Song Y, Vallmitjana J, Stent A, Jaimes A (2015) Tvsum: summarizing web videos using titles. CVPR:5179\u20135187"},{"key":"9888_CR43","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1016\/j.neucom.2015.07.131","volume":"187","author":"X Song","year":"2016","unstructured":"Song X, Sun L, Lei J, Tao D, Yuan G, Song M (2016) Event-based large scale surveillance video summarization. Neurocomputing 187:66\u201374","journal-title":"Neurocomputing"},{"key":"9888_CR44","doi-asserted-by":"crossref","unstructured":"Szegedy C, Liu W, Jia Y, Sermanet P, Reed SE, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2015) Going deeper with convolutions. CVPR:1\u20139","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"9888_CR45","unstructured":"van Seijen H, Fatemi M, Laroche R, Romoff J, Barnes T, Tsang J (2017) Hybrid reward architecture for reinforcement learning. NIPS:5392\u20135402"},{"key":"9888_CR46","doi-asserted-by":"crossref","unstructured":"Vasudevan AB, Gygli M, Volokitin A, Van Gool L (2017) Query-adaptive video summarization via quality-aware relevance estimation. ACM Multimedia:582\u2013590","DOI":"10.1145\/3123266.3123297"},{"key":"9888_CR47","doi-asserted-by":"crossref","unstructured":"Zhang C, Li H, Wang X, Yang X (2015) Cross-scene crowd counting via deep convolutional neural networks. CVPR:833\u2013841","DOI":"10.1109\/CVPR.2015.7298684"},{"key":"9888_CR48","doi-asserted-by":"crossref","unstructured":"Zhang K, Chao W-L, Sha F, Grauman K (2016) Video summarization with long short-term memory. ECCV:766\u2013782","DOI":"10.1007\/978-3-319-46478-7_47"},{"key":"9888_CR49","doi-asserted-by":"crossref","unstructured":"Zhang K, Chao W-L, Sha F, Grauman K (2016) Summary transfer: exemplar-based subset selection for video summarization. CVPR:1059\u20131067","DOI":"10.1109\/CVPR.2016.120"},{"key":"9888_CR50","doi-asserted-by":"crossref","unstructured":"Zhang K, Grauman K, Sha F (2018) Retrospective encoders for video summarization. ECCV:391\u2013408","DOI":"10.1007\/978-3-030-01237-3_24"},{"key":"9888_CR51","doi-asserted-by":"crossref","unstructured":"Zhao B, Li X, Xiaoqiang L (2017) Hierarchical recurrent neural network for video summarization. ACM Multimedia:863\u2013871","DOI":"10.1145\/3123266.3123328"},{"key":"9888_CR52","unstructured":"Zhou K, Xiang T, Cavallaro A (2018) Video summarisation by classification with deep reinforcement learning. BMVC 298"},{"key":"9888_CR53","doi-asserted-by":"crossref","unstructured":"Zhou K, Qiao Y, Xiang T (2018) Deep reinforcement learning for unsupervised video summarization with diversity-representativeness reward. AAAI:7582\u20137589","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\/s11042-020-09888-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-020-09888-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-020-09888-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,22]],"date-time":"2022-11-22T23:47:33Z","timestamp":1669160853000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-020-09888-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,12]]},"references-count":53,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2021,2]]}},"alternative-id":["9888"],"URL":"https:\/\/doi.org\/10.1007\/s11042-020-09888-1","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,10,12]]},"assertion":[{"value":"23 December 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 August 2020","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 September 2020","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 October 2020","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}