{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,20]],"date-time":"2025-07-20T03:53:56Z","timestamp":1752983636216,"version":"3.37.3"},"reference-count":27,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2020,8,3]],"date-time":"2020-08-03T00:00:00Z","timestamp":1596412800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,8,3]],"date-time":"2020-08-03T00:00:00Z","timestamp":1596412800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61772352"],"award-info":[{"award-number":["61772352"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Science and Technology Planning Project of Sichuan Province","award":["2019YFG0400","2018GZDZX0031"],"award-info":[{"award-number":["2019YFG0400","2018GZDZX0031"]}]},{"name":"Science and Technology Planning Project of Sichuan Province","award":["2018GZDZX0004","2017GZDZX0003"],"award-info":[{"award-number":["2018GZDZX0004","2017GZDZX0003"]}]},{"name":"Science and Technology Planning Project of Sichuan Province","award":["2018JY0182","19ZDYF1286"],"award-info":[{"award-number":["2018JY0182","19ZDYF1286"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["SIViP"],"published-print":{"date-parts":[[2021,3]]},"DOI":"10.1007\/s11760-020-01758-5","type":"journal-article","created":{"date-parts":[[2020,8,3]],"date-time":"2020-08-03T17:05:52Z","timestamp":1596474352000},"page":"361-369","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Using efficient group pseudo-3D network to learn spatio-temporal features"],"prefix":"10.1007","volume":"15","author":[{"given":"Yaosen","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bing","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"Shen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinhua","family":"Suo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhen","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,8,3]]},"reference":[{"key":"1758_CR1","doi-asserted-by":"crossref","unstructured":"Wang, H., Kl\u00e4ser, A., Schmid, C., et al.: Action recognition by dense trajectories. In: 2011 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3169\u20133176 (2011)","DOI":"10.1109\/CVPR.2011.5995407"},{"key":"1758_CR2","doi-asserted-by":"crossref","unstructured":"Action Wang, H., Schmid, C.: Action recognition with improved trajectories. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3551\u20133558 (2013)","DOI":"10.1109\/ICCV.2013.441"},{"key":"1758_CR3","doi-asserted-by":"crossref","unstructured":"Donahue, J., et al.: Long-term recurrent convolutional networks for visual recognition and description. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2625\u20132634 (2015)","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"1758_CR4","unstructured":"Thung, G., Jiang, H.: A Torch Library for Action Recognition and Detection Using CNNs and LSTMs"},{"key":"1758_CR5","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":"1758_CR6","doi-asserted-by":"crossref","unstructured":"Qiu, Z., Yao, T., Mei, T.: Learning spatio-temporal representation with pseudo-3d residual networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5533\u20135541 (2017)","DOI":"10.1109\/ICCV.2017.590"},{"key":"1758_CR7","doi-asserted-by":"crossref","unstructured":"Tran, D., et al.: A closer look at spatiotemporal convolutions for action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6450\u20136459 (2018)","DOI":"10.1109\/CVPR.2018.00675"},{"key":"1758_CR8","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? A new model and the kinetics dataset. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6299\u20136308 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"1758_CR9","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: Advances in Neural Information Processing Systems, pp. 568\u2013576 (2014)"},{"key":"1758_CR10","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Pinz, A., Zisserman, A.: Convolutional two-stream network fusion for video action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1933\u20131941 (2016)","DOI":"10.1109\/CVPR.2016.213"},{"key":"1758_CR11","unstructured":"Ng, Y.-H.J., 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":"1758_CR12","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., et al.: Slowfast networks for video recognition. arXiv preprint arXiv:1812.03982 (2018)","DOI":"10.1109\/ICCV.2019.00630"},{"key":"1758_CR13","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"1758_CR14","unstructured":"Kim, K.-H., et al.: Pvanet: deep but lightweight neural networks for real-time object detection. arXiv preprint arXiv:1608.08021 (2016)"},{"key":"1758_CR15","unstructured":"Iandola, F.N., et al.: SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and $$<$$ 0.5 MB model size. arXiv preprint arXiv:1602.07360 (2016)"},{"key":"1758_CR16","unstructured":"Howard, A.G., et al.: Mobilenets: efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)"},{"key":"1758_CR17","doi-asserted-by":"crossref","unstructured":"Sandler, M., et al.: Mobilenetv2: inverted residuals and linear bottlenecks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4510\u20134520 (2018)","DOI":"10.1109\/CVPR.2018.00474"},{"key":"1758_CR18","unstructured":"Howard, A., et al.: Searching for mobilenetv3. arXiv preprint arXiv:1905.02244 (2019)"},{"key":"1758_CR19","unstructured":"Soomro, K., Zamir, A.R., Shah, M.: UCF101: a dataset of 101 human action classes from videos in the wild. CRCV-TR-12-01, 4, 6 (2012)"},{"key":"1758_CR20","doi-asserted-by":"crossref","unstructured":"Kuehne, H., et al.: HMDB: a large video database for human motion recognition. In: 2011 International Conference on Computer Vision. IEEE, pp. 2556\u20132563 (2011)","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"1758_CR21","doi-asserted-by":"crossref","unstructured":"Caba Heilbron, F., et al.: Activitynet: a large-scale video benchmark for human activity understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 961\u2013970 (2015)","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"1758_CR22","unstructured":"Kay, W., et al.: The kinetics human action video dataset. arXiv preprint arXiv:1705.06950 (2017)"},{"key":"1758_CR23","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7132\u20137141 (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"1758_CR24","unstructured":"Ghiasi, G., Lin, T.-Y., Le, Q.V.: Dropblock: a regularization method for convolutional networks. In: Advances in Neural Information Processing Systems, pp. 10727\u201310737 (2018)"},{"key":"1758_CR25","unstructured":"Tran, D., Ray, J., Shou, Z., Chang, S., Paluri, M.: Convnet architecture search for spatiotemporal feature learning. arXiv:1708.05038 (2017)"},{"key":"1758_CR26","unstructured":"https:\/\/pytorch.org\/"},{"key":"1758_CR27","unstructured":"https:\/\/docs.nvidia.com\/deeplearning\/sdk\/cudnn-install\/"}],"container-title":["Signal, Image and Video Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-020-01758-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11760-020-01758-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-020-01758-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,8,2]],"date-time":"2021-08-02T23:37:08Z","timestamp":1627947428000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11760-020-01758-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,8,3]]},"references-count":27,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2021,3]]}},"alternative-id":["1758"],"URL":"https:\/\/doi.org\/10.1007\/s11760-020-01758-5","relation":{},"ISSN":["1863-1703","1863-1711"],"issn-type":[{"type":"print","value":"1863-1703"},{"type":"electronic","value":"1863-1711"}],"subject":[],"published":{"date-parts":[[2020,8,3]]},"assertion":[{"value":"12 November 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 July 2020","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 July 2020","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 August 2020","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}