{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T06:30:24Z","timestamp":1770964224022,"version":"3.50.1"},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2020,8,20]],"date-time":"2020-08-20T00:00:00Z","timestamp":1597881600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,8,20]],"date-time":"2020-08-20T00:00:00Z","timestamp":1597881600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"name":"the project of Jilin Provincial Science and Technology Department","award":["20180201003GX"],"award-info":[{"award-number":["20180201003GX"]}]},{"name":"the project of Jilin province development and reform commission","award":["2019C053-4."],"award-info":[{"award-number":["2019C053-4."]}]},{"name":"Jilin Provincial Science and Technology Department","award":["20180201003GX"],"award-info":[{"award-number":["20180201003GX"]}]},{"DOI":"10.13039\/100015800","name":"Jilin province development and reform commission","doi-asserted-by":"crossref","award":["2019C053-4"],"award-info":[{"award-number":["2019C053-4"]}],"id":[{"id":"10.13039\/100015800","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2020,12]]},"DOI":"10.1007\/s00530-020-00683-4","type":"journal-article","created":{"date-parts":[[2020,8,20]],"date-time":"2020-08-20T12:02:32Z","timestamp":1597924952000},"page":"715-725","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Integrating Gaussian mixture model and dilated residual network for action recognition in videos"],"prefix":"10.1007","volume":"26","author":[{"given":"Ming","family":"Fang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoying","family":"Bai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianwei","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fengqin","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chih-Cheng","family":"Hung","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuhua","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,8,20]]},"reference":[{"key":"683_CR1","unstructured":"Chenyang, S.I., et al.: An attention enhanced graph convolutional LSTM network for skeleton-based action recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp. 1227\u20131236 2019."},{"key":"683_CR2","doi-asserted-by":"crossref","unstructured":"Tran, D., et al.: Learning spatiotemporal features with 3d convolutional networks. In: Proceedings of the IEEE international conference on computer vision, pp. 4489\u20134497 (2015).","DOI":"10.1109\/ICCV.2015.510"},{"key":"683_CR3","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: NIPS, pp. 568\u2013576 (2014)"},{"key":"683_CR4","unstructured":"Ng, J.Y.-H., Hausknecht, M., Vijayanarasimhan, S., Vinyals, O., Monga, R., Toderici, G.: Beyond short snippets: deep networks for video classification. In: IEEE conference on computer vision and pattern recognition (CVPR), pp. 4694\u20134702 (2015)"},{"issue":"1","key":"683_CR5","doi-asserted-by":"publisher","first-page":"507","DOI":"10.1007\/s11042-017-5251-3","volume":"78","author":"LU Xiusheng","year":"2019","unstructured":"Xiusheng, L.U., et al.: Action recognition with multi-scale trajectory-pooled 3D convolutional descriptors. Multimedia Tools Appl 78(1), 507\u2013523 (2019)","journal-title":"Multimedia Tools Appl"},{"issue":"5","key":"683_CR6","doi-asserted-by":"publisher","first-page":"2326","DOI":"10.1109\/TIP.2018.2791180","volume":"27","author":"B Zhang","year":"2018","unstructured":"Zhang, B., Wang, L., Wang, Z., et al.: Real-time action recognition with deeply-transferred motion vector CNNs. IEEE Trans. Image Process.vol. 27(5), 2326\u20132339 (2018)","journal-title":"IEEE Trans. Image Process.vol."},{"key":"683_CR7","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE conference on computer vision and pattern recognition (CVPR), pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"683_CR8","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Weinberger, K.Q., van der Maaten, L.: Densely connected convolutional networks. https:\/\/arxiv.org\/abs\/1608.06993 (2016)","DOI":"10.1109\/CVPR.2017.243"},{"key":"683_CR9","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Neural information processing systems (NIPS), pp. 1097\u20131105 (2012)"},{"key":"683_CR10","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: International conference on learning representations (ICLR) 2015."},{"key":"683_CR11","doi-asserted-by":"publisher","first-page":"299","DOI":"10.1007\/s11263-007-0122-4","volume":"79","author":"JC Niebles","year":"2008","unstructured":"Niebles, J.C., Wang, H., Fei-Fei, L.: Unsupervised learning of human action categories using spatial-temporal words. Int. J. Comput. Vis. 79(3), pp. 299\u2013318 (2008).","journal-title":"Int. J. Comput. Vis."},{"issue":"1","key":"683_CR12","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1007\/s11263-012-0594-8","volume":"103","author":"H Wang","year":"2013","unstructured":"Wang, H., Klser, A., Schmid, C., et al.: Dense trajectories and motion boundary descriptors for action recognition. Int. J. Comput. Vis. 103(1), 60\u201379 (2013)","journal-title":"Int. J. Comput. Vis."},{"key":"683_CR13","doi-asserted-by":"crossref","unstructured":"Wang, H., Schmid, C.: Action recognition with improved trajectories. In: IEEE international conference on computer vision, pp. 3551\u20133558 (2014)","DOI":"10.1109\/ICCV.2013.441"},{"key":"683_CR14","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Toderici, G., Shetty, S., et al.: Large-scale video classification with convolutional neural networks. In: IEEE conference on computer vision and pattern recognition (CVPR), pp. 1725\u20131732 (2014)","DOI":"10.1109\/CVPR.2014.223"},{"key":"683_CR15","unstructured":"Srivastava, N., Mansimov, E., Salakhudinov, R.: Unsupervised learning of video representations using LSTMs. In: International conference on machine learning, pp. 843\u2013852 2015"},{"issue":"12","key":"683_CR16","doi-asserted-by":"publisher","first-page":"2799","DOI":"10.1109\/TPAMI.2017.2769085","volume":"40","author":"H Bilen","year":"2017","unstructured":"Bilen, H., Fernando, B., Gavves, E., et al.: Action recognition with dynamic image networks. IEEE Trans. Pattern Anal. Mach. Intell. 40(12), 2799\u20132813 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"683_CR17","doi-asserted-by":"crossref","unstructured":"Xie, S., Sun, C., Huang, J., et al.: Rethinking spatiotemporal feature learning: speed-accuracy trade-offs in video classification. In: Proceedings of the European conference on computer vision (ECCV), pp. 305\u2013321 (2018)","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"683_CR18","unstructured":"Nair, V., Hinton, G.E.: Rectified linear units improve restricted boltzmann machines. In: ICML, pp. 807\u2013814 (2010)"},{"key":"683_CR19","doi-asserted-by":"crossref","unstructured":"Zivkovic, Z.: Improved adaptive Gaussian mixture model for background subtraction. In: ICPR (2), pp. 28\u201331 (2004)","DOI":"10.1109\/ICPR.2004.1333992"},{"issue":"7","key":"683_CR20","doi-asserted-by":"publisher","first-page":"773","DOI":"10.1016\/j.patrec.2005.11.005","volume":"27","author":"Z Zivkovic","year":"2006","unstructured":"Zivkovic, Z., Van Der Heijden, F.: Efficient adaptive density estimation per image pixel for the task of background subtraction. Pattern Recogn. Lett. 27(7), 773\u2013780 (2006)","journal-title":"Pattern Recogn. Lett."},{"key":"683_CR21","unstructured":"Yu, F., Koltun, V.: Multi-scale context aggregation by dilated convolutions. In: ICLR 2016."},{"key":"683_CR22","unstructured":"Soomro, K., Zamir A.R., Shah M.: UCF101: a dataset of 101 human actions classes from videos in the wild. arXiv preprint. https:\/\/arxiv.org\/abs\/1212.0402 (2012)."},{"key":"683_CR23","unstructured":"Jhuang, H., Garrote, H., Poggio, E., et al.: A large video database for human motion recognition. In: Proceedings of of IEEE international conference on computer vision,\u00a0pp. 2556\u20132563 (2011)"},{"key":"683_CR24","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Li, F.F.: Imagenet: a large-scale hierarchical image database. In: IEEE conference on computer vision and pattern recognition, CVPR 2009, pp. 248\u2013255 2009.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"683_CR25","doi-asserted-by":"crossref","unstructured":"Zach, C., Pock, T., Bischof, H.: A duality based approach for real-time tv-l 1 optical flow. In: Joint pattern recognition symposium, vol. 5, Springer, pp. 214\u2013223 2007","DOI":"10.1007\/978-3-540-74936-3_22"},{"key":"683_CR26","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Pinz, A., Zisserman, A.: Convolutional two-stream network fusion for video action recognition. arXiv preprint. https:\/\/arxiv.org\/abs\/1604.06573 (2016)","DOI":"10.1109\/CVPR.2016.213"},{"key":"683_CR27","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., Rabinovich, A.: Going deeper with convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 1\u20139 (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"683_CR28","unstructured":"Wang, L., Xiong, Y., Wang, Z., Qiao, Y.: Towards good practices for very deep two-stream convnets. arXiv preprint. https:\/\/arxiv.org\/abs\/1507.02159 (2015)."},{"key":"683_CR29","unstructured":"Peng, X., Wang, L., Wang, X., Qiao, Y.: Bag of visual words and fusion methods for action recognition: comprehensive study and good practice. CoRR. https:\/\/arxiv.org\/abs\/1405.4506 (2014)."},{"key":"683_CR30","doi-asserted-by":"publisher","first-page":"677","DOI":"10.1109\/TPAMI.2016.2599174","volume":"39","author":"J Donahue","year":"2015","unstructured":"Donahue, J., Hendricks, J., Rohrbach, M., Venugopalan, S., Guadarrama, S., Saenko, K., Darrell, T.: Long-term recurrent convolutional networks for visual recognition and description. IEEE Trans. Pattern Anal. Mach. Intell. 39,  677\u2013691 (2015)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"683_CR31","unstructured":"Ng, J.Y.-H., Hausknecht, M., Vijayanarasimhan, S., et al.: Beyond short snippets: Deep networks for video classification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 4694\u20134702 (2015)"},{"key":"683_CR32","unstructured":"Tran, D., Ray, J., Shou, Z., Changm, S.F, Paluri, M. ConvNet architecture search for spatiotemporal feature learning. arXiv. https:\/\/arxiv.org\/abs\/1708.05038 (2017)."},{"key":"683_CR33","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3D convolutional networks. In: Proceedings of the IEEE international conference on computer vision, Venice, Italy, 22\u201329 October, pp. 4489\u20134497 (2017)"},{"key":"683_CR34","unstructured":"Ng, J., Hausknecht, M., Vijayanarasimhan, S., Vinyals, O., Monga, R., Toderici, G.: Beyond short snippets: deep networks for video classification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, Boston, MA, USA, 7\u201312 June, pp. 4694\u20134702 (2015)"},{"key":"683_CR35","doi-asserted-by":"crossref","unstructured":"Li, Y., Li, W., Mahadevan, V., Vasconcelos, N.: VLAD3: Encoding dynamics of deep features for action recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, Las Vegas, NV, USA, 26 June\u20131 July, pp. 1951\u20131960 (2016)","DOI":"10.1109\/CVPR.2016.215"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-020-00683-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-020-00683-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-020-00683-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,8,20]],"date-time":"2021-08-20T00:05:04Z","timestamp":1629417904000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-020-00683-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,8,20]]},"references-count":35,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2020,12]]}},"alternative-id":["683"],"URL":"https:\/\/doi.org\/10.1007\/s00530-020-00683-4","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,8,20]]},"assertion":[{"value":"4 May 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 August 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 August 2020","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Compliance with ethical standards"}},{"value":"Authors declare no conflicts of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}