{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T04:27:43Z","timestamp":1767155263903,"version":"3.37.3"},"reference-count":47,"publisher":"Springer Science and Business Media LLC","issue":"28","license":[{"start":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T00:00:00Z","timestamp":1652140800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T00:00:00Z","timestamp":1652140800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2022,11]]},"DOI":"10.1007\/s11042-022-12901-4","type":"journal-article","created":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T19:02:36Z","timestamp":1652209356000},"page":"40489-40510","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Spatiotemporal two-stream LSTM network for unsupervised video summarization"],"prefix":"10.1007","volume":"81","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1151-152X","authenticated-orcid":false,"given":"Min","family":"Hu","sequence":"first","affiliation":[]},{"given":"Ruimin","family":"Hu","sequence":"additional","affiliation":[]},{"given":"Zhongyuan","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Zixiang","family":"Xiong","sequence":"additional","affiliation":[]},{"given":"Rui","family":"Zhong","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,5,10]]},"reference":[{"key":"12901_CR1","doi-asserted-by":"crossref","unstructured":"Avila SEFD, Lopes APB, da Luz Jr A, de Albuquerque Arajo A (2011) Vsumm: a mechanism designed to produce static video summaries and a novel evaluation method. Pattern Recogn Lett 32(1):56\u201368","DOI":"10.1016\/j.patrec.2010.08.004"},{"key":"12901_CR2","unstructured":"Brown FP, et al. (1992) Class-based n-gram models of natural language. Comput Linguist:467\u2013480"},{"key":"12901_CR3","doi-asserted-by":"crossref","unstructured":"DeSimone R, Duncan J (1995) Neural mechanisms of selective visual attention. Ann Rev Neurosci 18(1):193\u2013222","DOI":"10.1146\/annurev.ne.18.030195.001205"},{"key":"12901_CR4","doi-asserted-by":"crossref","unstructured":"El-Ghoroury HN, Gupta SC (1972) Additive Bernoulli noise linear sequential circuits. IEEE Trans Comput 100(10):1119\u20131124","DOI":"10.1109\/T-C.1972.223460"},{"key":"12901_CR5","doi-asserted-by":"crossref","unstructured":"Elhamifar E, Sapiro G, Vidal R (2012) See all by looking at a few: Sparse modeling for finding representative objects. In: CVPR, pp 1600\u20131607","DOI":"10.1109\/CVPR.2012.6247852"},{"key":"12901_CR6","doi-asserted-by":"crossref","unstructured":"Elhamifar E, Sapiro G, Vidal R (2012) Sparse modeling for finding representative objects. Preparation 4(6):8","DOI":"10.1109\/CVPR.2012.6247852"},{"key":"12901_CR7","doi-asserted-by":"crossref","unstructured":"Fan G, Guo Y, Zheng J, Hong W (2020) A generalized regression model based on hybrid empirical mode decomposition and support vector regression with back propagation neural network for mid-short term load forecasting. J Forecast 39(5):737\u2013756","DOI":"10.1002\/for.2655"},{"key":"12901_CR8","doi-asserted-by":"crossref","unstructured":"Fan G, Peng LL, Hong W, et al. (2016) Electric load forecasting by the SVR model with differential empirical mode decomposition and auto regression. Neurocomputing 173:958\u2013970","DOI":"10.1016\/j.neucom.2015.08.051"},{"issue":"2","key":"12901_CR9","first-page":"1","volume":"77","author":"M Fei","year":"2017","unstructured":"Fei M, Jiang W, Mao W (2017) A novel compact yet rich key frame creation method for compressed video summarization. Multimed Tools Appl 77 (2):1\u201321","journal-title":"Multimed Tools Appl"},{"key":"12901_CR10","unstructured":"Gong B, Chao W-L, Grauman K, Sha F (2014) Diverse sequential subset selection for supervised video summarization. In: Advances in Neural Information Processing Systems, pp 2069\u20132077"},{"key":"12901_CR11","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, pp pp 505\u2013520","DOI":"10.1007\/978-3-319-10584-0_33"},{"key":"12901_CR12","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"},{"key":"12901_CR13","doi-asserted-by":"crossref","unstructured":"Han J, Li KM, Shao L, Hu XT, He S, Guo L, et al. (2014) And Video abstraction based on fMRI-driven visual attention model. Inf Sci 281:781\u2013796","DOI":"10.1016\/j.ins.2013.12.039"},{"key":"12901_CR14","doi-asserted-by":"crossref","unstructured":"Itti L, Koch C (2001) Computational modelling of visual attention. In: Nature Rev Neurosci 2(3):194","DOI":"10.1038\/35058500"},{"key":"12901_CR15","doi-asserted-by":"crossref","unstructured":"Ji QG, Fang ZD, Xie ZH, Lu ZM (2013) Video abstraction based on the visual attention model and online clustering. Signal Process Image Commun 28(3):241\u2013253","DOI":"10.1016\/j.image.2012.11.008"},{"key":"12901_CR16","unstructured":"Ji Z, Xiong K, Pang Y, Li X (2019) Video summarization with attention-based encoder-decoder networks. IEEE Trans Circ Syst Video Technol 1(1):183\u2013298"},{"key":"12901_CR17","unstructured":"Ji Z, Zhao Y, Pang Y, Li X, Han J (2019) Deep attentive video summarization with distribution consistency learning. IEEE Trans Neural Netw Learn Syst 99:1\u201311"},{"key":"12901_CR18","unstructured":"Jin J, Fu K, Cui R, Sha F, Zhang C (2015) Aligning where to see and what to tell: Image caption with region-based attention and scene factorization, [Online]. Available: 1506.06272"},{"key":"12901_CR19","first-page":"8537","volume":"33","author":"Y Jung","year":"2019","unstructured":"Jung Y, Cho D, Kim D, Woo S, Kweon IS (2019) Discriminative feature learning for unsupervised video summarization. Thirty-third AAAI Conf Artif Intell 33:8537\u20138544","journal-title":"Thirty-third AAAI Conf Artif Intell"},{"key":"12901_CR20","doi-asserted-by":"crossref","unstructured":"Kannan R, Swaminathan S, Ghinea G, Andres F, Anbananthen KASM (2019) Movie video summarization- generating personalized summaries using spatiotemporal salient region detection. Int J Multimed Data Eng Manag 10(3):1\u201326","DOI":"10.4018\/IJMDEM.2019070101"},{"key":"12901_CR21","doi-asserted-by":"crossref","unstructured":"Khosla A, Hamid R, Lin C-J, Sundaresan N (2013) Large-scale video summarization using web-image priors. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 2698\u2013 2705","DOI":"10.1109\/CVPR.2013.348"},{"issue":"4","key":"12901_CR22","doi-asserted-by":"publisher","first-page":"2579","DOI":"10.1007\/s11071-019-05149-5","volume":"97","author":"MW Li","year":"2019","unstructured":"Li MW, Geng J, Hong W, Zhang LD (2019) Periodogram estimation based on LSSVR-CCPSO compensation for forecasting ship motion. Nonlinear Dyn 97(4):2579\u20132594","journal-title":"Nonlinear Dyn"},{"key":"12901_CR23","doi-asserted-by":"crossref","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","DOI":"10.1109\/TIP.2017.2695887"},{"issue":"8","key":"12901_CR24","first-page":"187","volume":"23","author":"TP Lillicrap","year":"2015","unstructured":"Lillicrap TP, Hunt JJ, Pritzel A, Heess N, Erez T, et al. (2015) Continuous control with deep reinforcement learning. Comput ence 23 (8):187","journal-title":"Comput ence"},{"key":"12901_CR25","unstructured":"Lipton ZC, Berkowitz J, Elkan C (2015) A critical review of recurrent neural networks for sequence learning, [Online]. Available: arXiv:https:\/\/arxiv.org\/abs\/1506.000191506.00019"},{"key":"12901_CR26","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"},{"key":"12901_CR27","doi-asserted-by":"crossref","unstructured":"Mehmood I, Sajjad M, Ejaz W, Baik SW (2015) Saliency-directed prioritization of visual data in wireless surveillance networks. Inform Fusion 24:16\u201330","DOI":"10.1016\/j.inffus.2014.07.002"},{"key":"12901_CR28","doi-asserted-by":"crossref","unstructured":"Qu S, Xi Y, Ding S (2017) Visual attention based on long-short term memory model for image caption generation. In: 2017 29Th chinese control and decision conference (CCDC). IEEE, pp 4789\u20134794","DOI":"10.1109\/CCDC.2017.7979342"},{"key":"12901_CR29","doi-asserted-by":"crossref","unstructured":"Salehin MM, Paul M (2016) Summarizing surveillance video by saliency transition and moving object information, International Conference on Digital Image Computing, Techniques & Applications. IEEE","DOI":"10.1109\/DICTA.2015.7371311"},{"key":"12901_CR30","doi-asserted-by":"crossref","unstructured":"Shih H (2013) Chia a novel attention-based key-frame determination method. IEEE TransBroadcast 59(3):556\u2013562","DOI":"10.1109\/TBC.2013.2265782"},{"key":"12901_CR31","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":"12901_CR32","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":"12901_CR33","doi-asserted-by":"crossref","unstructured":"Venugopalan S, Rohrbach M, Donahue J, Mooney R, Darrell T, Saenko K (2015) Sequence to sequence-video to text. In: Proceedings of the IEEE International Conference on Computer Vision, pp 4534\u2013 4542","DOI":"10.1109\/ICCV.2015.515"},{"key":"12901_CR34","doi-asserted-by":"crossref","unstructured":"Wang W, Shen J, Shao L (2017) Video salient object detection via fully convolutional networks. IEEE Trans Image Process 27(1):38\u201349","DOI":"10.1109\/TIP.2017.2754941"},{"key":"12901_CR35","doi-asserted-by":"crossref","unstructured":"Wu G, et al. (2019) Unsupervised deep video hashing via balanced code for Large-Scale video retrieval. IEEE Trans Image Process 28(4):1993\u20132007","DOI":"10.1109\/TIP.2018.2882155"},{"key":"12901_CR36","doi-asserted-by":"crossref","unstructured":"Yao L, Torabi A, Cho K, Ballas N, Pal C, Larochelle H, Courville A (2015) Describing videos by exploiting temporal structure. In: Proceedings of the IEEE International Conference on Computer Vision, pp 4507\u20134515","DOI":"10.1109\/ICCV.2015.512"},{"issue":"8","key":"12901_CR37","doi-asserted-by":"publisher","first-page":"2503","DOI":"10.1109\/TCSVT.2019.2925844","volume":"30","author":"P Yi","year":"2020","unstructured":"Yi P, Wang ZY, Jiang K, Shao ZF, Ma J. y. (2020) Multi-Temporal Ultra Dense Memory Network For Video Super-Resolution. IEEE Trans Circ Syst Video Technol 30(8):2503\u20132516","journal-title":"IEEE Trans Circ Syst Video Technol"},{"key":"12901_CR38","doi-asserted-by":"crossref","unstructured":"Yuan Y, Li H, Wang Q (2019) Spatiotemporal modelling for video summarization using convolutional recurrent neural network. IEEE Access 7:64676\u201364685","DOI":"10.1109\/ACCESS.2019.2916989"},{"key":"12901_CR39","doi-asserted-by":"crossref","unstructured":"Yuan Y, Li H, Wang Q, Qi (2019) Spatiotemporal Modeling for Video Summarization Using Convolutional Recurrent Neural Network. In: IEEE Access, pp 1-1","DOI":"10.1109\/ACCESS.2019.2916989"},{"issue":"10","key":"12901_CR40","doi-asserted-by":"publisher","first-page":"2711","DOI":"10.1109\/TMM.2019.2959451","volume":"22","author":"L Yuan","year":"2020","unstructured":"Yuan L, Tay FEH, Li P, Feng J (2020) Unsupervised video summarization with cycle-consistent adversarial LSTM networks. IEEE Trans Multimed 22(10):2711\u20132722","journal-title":"IEEE Trans Multimed"},{"key":"12901_CR41","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, pp 766\u2013782","DOI":"10.1007\/978-3-319-46478-7_47"},{"key":"12901_CR42","doi-asserted-by":"crossref","unstructured":"Zhang K, Chao W. -L., 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":"12901_CR43","doi-asserted-by":"crossref","unstructured":"Zhang Z, Ding S, Sun Y (2020) A support vector regression model hybridized with chaotic krill herd algorithm and empirical mode decomposition for regression task. Neurocomputing 410:185\u2013201","DOI":"10.1016\/j.neucom.2020.05.075"},{"key":"12901_CR44","doi-asserted-by":"crossref","unstructured":"Zhang Z, Hong W (2019) Electric load forecasting by complete ensemble empirical model decomposition adaptive noise and support vector regression with quantum-based dragonfly algorithm. Nonlinear Dyn 98:1107\u20131136","DOI":"10.1007\/s11071-019-05252-7"},{"key":"12901_CR45","doi-asserted-by":"crossref","unstructured":"Zhang Q, Huang N, Yao L, Zhang D, Shan C, Han J (2020) RGB-T salient object detection via fusing Multi-Level CNN features. IEEE Trans Image Process 29:3321\u20133335","DOI":"10.1109\/TIP.2019.2959253"},{"key":"12901_CR46","doi-asserted-by":"crossref","unstructured":"Zhao B, Xing EP (2014) Quasi real-time summarization for consumer videos. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 2513\u20132520","DOI":"10.1109\/CVPR.2014.322"},{"key":"12901_CR47","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, pp 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\/s11042-022-12901-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-022-12901-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-022-12901-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,25]],"date-time":"2022-10-25T09:48:20Z","timestamp":1666691300000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-022-12901-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,10]]},"references-count":47,"journal-issue":{"issue":"28","published-print":{"date-parts":[[2022,11]]}},"alternative-id":["12901"],"URL":"https:\/\/doi.org\/10.1007\/s11042-022-12901-4","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"type":"print","value":"1380-7501"},{"type":"electronic","value":"1573-7721"}],"subject":[],"published":{"date-parts":[[2022,5,10]]},"assertion":[{"value":"14 November 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 February 2021","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 March 2022","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 May 2022","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}