{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T15:33:48Z","timestamp":1771515228253,"version":"3.50.1"},"reference-count":42,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2020,3,9]],"date-time":"2020-03-09T00:00:00Z","timestamp":1583712000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2020,3,9]],"date-time":"2020-03-09T00:00:00Z","timestamp":1583712000000},"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":["Sci. China Inf. Sci."],"published-print":{"date-parts":[[2020,4]]},"DOI":"10.1007\/s11432-019-2784-4","type":"journal-article","created":{"date-parts":[[2020,3,16]],"date-time":"2020-03-16T05:09:43Z","timestamp":1584335383000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":25,"title":["Deep feature extraction and motion representation for satellite video scene classification"],"prefix":"10.1007","volume":"63","author":[{"given":"Yanfeng","family":"Gu","sequence":"first","affiliation":[]},{"given":"Huan","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Tengfei","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Shengyang","family":"Li","sequence":"additional","affiliation":[]},{"given":"Guoming","family":"Gao","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,3,9]]},"reference":[{"key":"2784_CR1","doi-asserted-by":"publisher","first-page":"3389","DOI":"10.1109\/TMM.2018.2838320","volume":"20","author":"C Yan","year":"2018","unstructured":"Yan C, Xie H, Chen J, et al. A fast Uyghur text detector for complex background images. IEEE Trans Multimedia, 2018, 20: 3389\u20133398","journal-title":"IEEE Trans Multimedia"},{"key":"2784_CR2","doi-asserted-by":"publisher","first-page":"120103","DOI":"10.1007\/s11432-019-2713-1","volume":"63","author":"Q Q Wang","year":"2020","unstructured":"Wang Q Q, Huang Y, Jia W J, et al. FACLSTM: ConvLSTM with focused attention for scene text recognition. Sci China Inf Sci, 2020, 63: 120103","journal-title":"Sci China Inf Sci"},{"key":"2784_CR3","doi-asserted-by":"publisher","first-page":"042301","DOI":"10.1007\/s11432-017-9405-6","volume":"62","author":"J P Zhao","year":"2019","unstructured":"Zhao J P, Guo W W, Zhang Z H, et al. A coupled convolutional neural network for small and densely clustered ship detection in SAR images. Sci China Inf Sci, 2019, 62: 042301","journal-title":"Sci China Inf Sci"},{"key":"2784_CR4","doi-asserted-by":"crossref","unstructured":"Marszalek M, Laptev I, Schmid C. Actions in context. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Miami, 2009. 2929\u20132936","DOI":"10.1109\/CVPR.2009.5206557"},{"key":"2784_CR5","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1109\/TMM.2019.2924576","volume":"22","author":"C Yan","year":"2020","unstructured":"Yan C, Tu Y, Wang X, et al. STAT: spatial-temporal attention mechanism for video captioning. IEEE Trans Multimedia, 2020, 22: 229\u2013241","journal-title":"IEEE Trans Multimedia"},{"key":"2784_CR6","unstructured":"Lazebnik S, Schmid C, Ponce J. Beyond bags of features: spatial pyramid matching for recognizing natural scene categories. In: Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), New York, 2006. 2169\u20132178"},{"key":"2784_CR7","doi-asserted-by":"publisher","first-page":"222","DOI":"10.1007\/s11263-013-0636-x","volume":"105","author":"J S\u00e1nchez","year":"2013","unstructured":"S\u00e1nchez J, Perronnin F, Mensink T, et al. Image classification with the fisher vector: theory and practice. Int J Comput Vis, 2013, 105: 222\u2013245","journal-title":"Int J Comput Vis"},{"key":"2784_CR8","doi-asserted-by":"publisher","first-page":"439","DOI":"10.1109\/TGRS.2013.2241444","volume":"52","author":"A M Cheriyadat","year":"2014","unstructured":"Cheriyadat A M. Unsupervised feature learning for aerial scene classification. IEEE Trans Geosci Remote Sens, 2014, 52: 439\u2013451","journal-title":"IEEE Trans Geosci Remote Sens"},{"key":"2784_CR9","doi-asserted-by":"publisher","first-page":"2675","DOI":"10.1109\/TMM.2019.2903448","volume":"21","author":"C Yan","year":"2019","unstructured":"Yan C, Li L, Zhang C, et al. Cross-modality bridging and knowledge transferring for image understanding. IEEE Trans Multimedia, 2019, 21: 2675\u20132685","journal-title":"IEEE Trans Multimedia"},{"key":"2784_CR10","doi-asserted-by":"publisher","first-page":"2149","DOI":"10.1080\/01431161.2016.1171928","volume":"37","author":"E Othman","year":"2016","unstructured":"Othman E, Bazi Y, Alajlan N, et al. Using convolutional features and a sparse autoencoder for land-use scene classification. Int J Remote Sens, 2016, 37: 2149\u20132167","journal-title":"Int J Remote Sens"},{"key":"2784_CR11","unstructured":"Otavio A B P, Nogueira K, dos Santos J A. Do deep features generalize from everyday objects to remote sensing and aerial scenes domains? In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Boston, 2015. 44\u201351"},{"key":"2784_CR12","doi-asserted-by":"publisher","first-page":"14680","DOI":"10.3390\/rs71114680","volume":"7","author":"F Hu","year":"2015","unstructured":"Hu F, Xia G S, Hu J, et al. Transferring deep convolutional neural networks for the scene classification of high-resolution remote sensing imagery. Remote Sens, 2015, 7: 14680\u201314707","journal-title":"Remote Sens"},{"key":"2784_CR13","doi-asserted-by":"publisher","first-page":"4775","DOI":"10.1109\/TGRS.2017.2700322","volume":"55","author":"S Chaib","year":"2017","unstructured":"Chaib S, Liu H, Gu Y, et al. Deep feature fusion for VHR remote sensing scene classification. IEEE Trans Geosci Remote Sens, 2017, 55: 4775\u20134784","journal-title":"IEEE Trans Geosci Remote Sens"},{"key":"2784_CR14","doi-asserted-by":"publisher","first-page":"5653","DOI":"10.1109\/TGRS.2017.2711275","volume":"55","author":"E Li","year":"2017","unstructured":"Li E, Xia J, Du P, et al. Integrating multilayer features of convolutional neural networks for remote sensing scene classification. IEEE Trans Geosci Remote Sens, 2017, 55: 5653\u20135665","journal-title":"IEEE Trans Geosci Remote Sens"},{"key":"2784_CR15","doi-asserted-by":"publisher","first-page":"6899","DOI":"10.1109\/TGRS.2018.2845668","volume":"56","author":"N He","year":"2018","unstructured":"He N, Fang L, Li S, et al. Remote sensing scene classification using multilayer stacked covariance pooling. IEEE Trans Geosci Remote Sens, 2018, 56: 6899\u20136910","journal-title":"IEEE Trans Geosci Remote Sens"},{"key":"2784_CR16","doi-asserted-by":"crossref","unstructured":"Yi S, Pavlovic V. Spatio-temporal context modeling for BoW-based video classification. In: Proceedings of IEEE International Conference on Computer Vision Workshops (ICCVW), Sydney, 2013. 779\u2013786","DOI":"10.1109\/ICCVW.2013.107"},{"key":"2784_CR17","doi-asserted-by":"publisher","first-page":"1465","DOI":"10.1109\/TIP.2011.2175739","volume":"21","author":"G Y Zhao","year":"2012","unstructured":"Zhao G Y, Ahonen T, Matas J, et al. Rotation-invariant image and video description with local binary pattern features. IEEE Trans Image Process, 2012, 21: 1465\u20131477","journal-title":"IEEE Trans Image Process"},{"key":"2784_CR18","doi-asserted-by":"crossref","unstructured":"Scovanner P, Ali S, Shah M. A 3-dimensional sift descriptor and its application to action recognition. In: Proceedings of the 15th ACM International Conference on Multimedia (ACMMM), Augsburg, 2007. 357\u2013360","DOI":"10.1145\/1291233.1291311"},{"key":"2784_CR19","doi-asserted-by":"crossref","unstructured":"Derpanis K G, Lecce M, Daniilidis K, et al. Dynamic scene understanding: the role of orientation features in space and time in scene classification. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Providence, 2012. 1306\u20131313","DOI":"10.1109\/CVPR.2012.6247815"},{"key":"2784_CR20","doi-asserted-by":"crossref","unstructured":"Wang H, Ullah M M, Klaser A, et al. Evaluation of local spatio-temporal features for action recognition. In: Proceedings of British Machine Vision Conference (BMVC), London, 2009. 1\u201311","DOI":"10.5244\/C.23.124"},{"key":"2784_CR21","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1007\/s11263-012-0594-8","volume":"103","author":"H Wang","year":"2013","unstructured":"Wang H, Kl\u00e4ser A, Schmid C, et al. Dense trajectories and motion boundary descriptors for action recognition. Int J Comput Vis, 2013, 103: 60\u201379","journal-title":"Int J Comput Vis"},{"key":"2784_CR22","doi-asserted-by":"crossref","unstructured":"Wang H, Schmid C. Action recognition with improved trajectories. In: Proceedings of IEEE International Conference on Computer Vision (ICCV), Sydney, 2013. 3551\u20133558","DOI":"10.1109\/ICCV.2013.441"},{"key":"2784_CR23","doi-asserted-by":"crossref","unstructured":"Karpathy A, Toderici G, Shetty S, et al. Large scale video classification with convolutional neural networks. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Columbus, 2014. 1725\u20131732","DOI":"10.1109\/CVPR.2014.223"},{"key":"2784_CR24","doi-asserted-by":"crossref","unstructured":"Hara K, Kataoka H, Satoh Y. Can spatiotemporal 3D CNNs retrace the history of 2D CNNs and ImageNet? In: Proceedings of IEEE conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, 2018. 6546\u20136555","DOI":"10.1109\/CVPR.2018.00685"},{"key":"2784_CR25","doi-asserted-by":"crossref","unstructured":"Hara K, Kataoka H, Satoh Y. Learning spatio-temporal features with 3D residual networks for action recognition. In: Proceedings of IEEE International Conference on Computer Vision Workshop (ICCVW), Venice, 2017. 3154\u20133160","DOI":"10.1109\/ICCVW.2017.373"},{"key":"2784_CR26","doi-asserted-by":"crossref","unstructured":"Tran D, Bourdev L, Fergus R, et al. Learning spatiotemporal features with 3D convolutional networks. In: Proceedings of IEEE International Conference on Computer Vision (ICCV), Santiago, 2015. 4489\u20134497","DOI":"10.1109\/ICCV.2015.510"},{"key":"2784_CR27","unstructured":"Simonyan K, Zisserman A. Two-stream convolutional networks for action recognition in videos. In: Proceedings of International Conference on Neural Information Processing Systems (NeurIPS), Quebec, 2014. 568\u2013576"},{"key":"2784_CR28","doi-asserted-by":"publisher","first-page":"677","DOI":"10.1109\/TPAMI.2016.2599174","volume":"39","author":"J Donahue","year":"2017","unstructured":"Donahue J, Hendricks L A, Rohrbach M, et al. Long-term recurrent convolutional networks for visual recognition and description. IEEE Trans Pattern Anal Mach Intell, 2017, 39: 677\u2013691","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2784_CR29","unstructured":"Srivastava N, Mansimov E, Salakhutdinov R. Unsupervised learning of video representations using LSTMs. In: Proceedings of International Conference on Machine Learning (ICML), Lille, 2015. 843\u2013852"},{"key":"2784_CR30","unstructured":"Ng J Y, Hausknecht M, Vijayanarasimhan S, et al. Beyond short snippets: deep networks for video classification. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, 2015. 4694\u20134702"},{"key":"2784_CR31","doi-asserted-by":"crossref","unstructured":"Zhu L, Xu Z, Yang Y. Bidirectional multirate reconstruction for temporal modeling in videos. In: Proceedings of IEEE conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, 2017. 1339\u20131348","DOI":"10.1109\/CVPR.2017.147"},{"key":"2784_CR32","doi-asserted-by":"crossref","unstructured":"Feichtenhofer C, Pinz A, Wildes R P. Temporal residual networks for dynamic scene recognition. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, 2017. 7435\u20137444","DOI":"10.1109\/CVPR.2017.786"},{"key":"2784_CR33","unstructured":"Simonyan K, Zisserman A. Very deep convolutional networks for large scale image recognition. In: Proceedings of International Conference on Learning Representations (ICLR), San Diego, 2015. 1\u201314"},{"key":"2784_CR34","doi-asserted-by":"publisher","first-page":"1006","DOI":"10.1109\/TCSVT.2003.816521","volume":"13","author":"T M Liu","year":"2003","unstructured":"Liu T M, Zhang H J, Qi F H. A novel video key-frame-extraction algorithm based on perceived motion energy model. IEEE Trans Circ Syst Video Technol, 2003, 13: 1006\u20131013","journal-title":"IEEE Trans Circ Syst Video Technol"},{"key":"2784_CR35","doi-asserted-by":"publisher","first-page":"1148","DOI":"10.1109\/TCSVT.2005.852623","volume":"15","author":"K W Sze","year":"2005","unstructured":"Sze K W, Lam K M, Qiu G P. A new key frame representation for video segment retrieval. IEEE Trans Circ Syst Video Technol, 2005, 15: 1148\u20131155","journal-title":"IEEE Trans Circ Syst Video Technol"},{"key":"2784_CR36","unstructured":"Dufaux F. Key frame selection to represent a video. In: Proceedings of International Conference on Image Processing (ICIP), Vancouver, 2000. 275\u2013278"},{"key":"2784_CR37","doi-asserted-by":"crossref","unstructured":"Crete F, Dolmiere T, Ladret P, et al. The blur effect: perception and estimation with a new no-reference perceptual blur metric. In: Proceedings of SPIE, 2007. 64920I","DOI":"10.1117\/12.702790"},{"key":"2784_CR38","doi-asserted-by":"publisher","first-page":"1290","DOI":"10.1109\/76.809163","volume":"9","author":"E Sahouria","year":"1999","unstructured":"Sahouria E, Zakhor A. Content analysis of video using principal components. IEEE Trans Circ Syst Video Technol, 1999, 9: 1290\u20131298","journal-title":"IEEE Trans Circ Syst Video Technol"},{"key":"2784_CR39","doi-asserted-by":"publisher","first-page":"3965","DOI":"10.1109\/TGRS.2017.2685945","volume":"55","author":"G S Xia","year":"2017","unstructured":"Xia G S, Hu J, Hu F, et al. AID: a benchmark data set for performance evaluation of aerial scene classification. IEEE Trans Geosci Remote Sens, 2017, 55: 3965\u20133981","journal-title":"IEEE Trans Geosci Remote Sens"},{"key":"2784_CR40","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1109\/MGRS.2016.2515107","volume":"4","author":"D Tuia","year":"2016","unstructured":"Tuia D, Moser G, Le Saux B. 2016 IEEE GRSS data fusion contest: very high temporal resolution from space technical committees. IEEE Geosci Remote Sens Mag, 2016, 4: 46\u201348","journal-title":"IEEE Geosci Remote Sens Mag"},{"key":"2784_CR41","doi-asserted-by":"crossref","unstructured":"Farneback G. Two-frame motion estimation based on polynomial expansion. In: Proceedings of the 13th Scandinavian Conference on Image Analysis (SCIA), 2003. 363\u2013370","DOI":"10.1007\/3-540-45103-X_50"},{"key":"2784_CR42","doi-asserted-by":"crossref","unstructured":"KaewTraKulPong P, Bowden R. An improved adaptive background mixture model for real-time tracking with shadow detection. In: Proceedings of the 2nd European Workshop on Advanced Video Based Surveillance System, Boston, 2002. 135\u2013144","DOI":"10.1007\/978-1-4615-0913-4_11"}],"container-title":["Science China Information Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11432-019-2784-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11432-019-2784-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11432-019-2784-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,4,11]],"date-time":"2023-04-11T14:45:55Z","timestamp":1681224355000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11432-019-2784-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,3,9]]},"references-count":42,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2020,4]]}},"alternative-id":["2784"],"URL":"https:\/\/doi.org\/10.1007\/s11432-019-2784-4","relation":{},"ISSN":["1674-733X","1869-1919"],"issn-type":[{"value":"1674-733X","type":"print"},{"value":"1869-1919","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,3,9]]},"assertion":[{"value":"1 November 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 January 2020","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 February 2020","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 March 2020","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"140307"}}