{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,22]],"date-time":"2025-04-22T01:32:18Z","timestamp":1745285538857},"reference-count":29,"publisher":"Springer Science and Business Media LLC","issue":"S1","license":[{"start":{"date-parts":[[2017,11,7]],"date-time":"2017-11-07T00:00:00Z","timestamp":1510012800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Cluster Comput"],"published-print":{"date-parts":[[2019,1]]},"DOI":"10.1007\/s10586-017-1309-2","type":"journal-article","created":{"date-parts":[[2017,11,7]],"date-time":"2017-11-07T12:53:24Z","timestamp":1510059204000},"page":"819-826","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["More efficient and effective tricks for deep action recognition"],"prefix":"10.1007","volume":"22","author":[{"given":"Zheyuan","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoteng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Song","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhengyan","family":"Ding","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huixian","family":"Duan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,11,7]]},"reference":[{"key":"1309_CR1","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: NIPS, pp. 1106\u20131114 (2012)"},{"key":"1309_CR2","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: ICLR, pp. 1\u201314 (2015)"},{"key":"1309_CR3","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: CVPR, pp. 1\u20139 (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"1309_CR4","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., Fei-Fei, L.: Large-scale video classification with convolutional neural networks. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.223"},{"key":"1309_CR5","doi-asserted-by":"crossref","unstructured":"Tran, D., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3d convolutional networks. In: ICCV, pp. 4489\u20134497 (2015)","DOI":"10.1109\/ICCV.2015.510"},{"key":"1309_CR6","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In NIPS (2014)"},{"key":"1309_CR7","doi-asserted-by":"crossref","unstructured":"Wang, L., Qiao, Y., Tang, X.: Action recognition with trajectory-pooled deep-convolutional descriptors. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7299059"},{"key":"1309_CR8","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Pinz, A., Zisserman, A.: Convolutional two-stream network fusion for video action recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.213"},{"key":"1309_CR9","doi-asserted-by":"crossref","unstructured":"Wang, L., Xiong, Y., Wang, Z., Qiao, Y., Lin, D., Tang, X., Gool, L.V.: Temporal segment networks: towards good practices for deep action recognition. In: ECCV (2016)","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"1309_CR10","unstructured":"Soomro, K., Zamir, A.R., Shah, M.: UCF101: A dataset of 101 human actions classes from videos in the wild. In: CoRR (2012)"},{"key":"1309_CR11","doi-asserted-by":"crossref","unstructured":"Kuehne, H., Jhuang, H., Garrote, E., Poggio, T., Serre, T.: Hmdb: a large video database for human motion recognition. In: ICCV (2011)","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"1309_CR12","unstructured":"Ioe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: ICML, pp. 448\u2013456 (2015)"},{"key":"1309_CR13","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"1309_CR14","unstructured":"Yue-Hei, J., Jonghyun, C., Jan, N., Larry, D.: ActionFlowNet: learning motion representation for action recognition. In: CoRR (2016). \n                    arXiv:1612.03052"},{"key":"1309_CR15","doi-asserted-by":"crossref","unstructured":"Brox, T., Bruhn, A., Papenberg, N., Weickert, J.: High accuracy optical flow estimation based on a theory for warping. In: ECCV (2004)","DOI":"10.1007\/978-3-540-24673-2_3"},{"key":"1309_CR16","unstructured":"Jean-Yves, B.: Pyramidal Implementation of the Affine Lucas Kanade Feature Tracker Description of the Algorithm, vol. 5, no. 1\u201310, p. 4. Intel Corporation (2001)"},{"key":"1309_CR17","doi-asserted-by":"crossref","unstructured":"Zach, C., Pock, T., Bischof, H.: A duality based approach for realtime tv-L1 optical flow. In: Proceedings of the 29th DAGM symposium on pattern recognition, pp. 214\u2013223 (2007)","DOI":"10.1007\/978-3-540-74936-3_22"},{"key":"1309_CR18","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: CVPR (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"1309_CR19","unstructured":"Zhou, B., Lapedriza, A., Xiao, J., Torralba, A., Oliva, A.: Learning deep features for scene recognition using places database 27. In: NIPS (2014)"},{"key":"1309_CR20","unstructured":"Jiang, Y., Wu, Z., Wang, J., Xue, X., Chang, S.: Exploiting feature and class relationships in video categorization with regularized deep neural networks. In: CoRR (2015). \n                    arXiv:1502.07209"},{"key":"1309_CR21","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Jonathon, S.: Rethinking the inception architecture for computer vision. In: CoRR (2015). \n                    arXiv:1512.00567"},{"key":"1309_CR22","unstructured":"Szegedy, C., Ioffe, S., Vanhoucke, V.: Inception-v4, inception-resnet and the impact of residual connections on learning. In: CoRR (2016). \n                    arXiv:1602.07261"},{"key":"1309_CR23","unstructured":"Xie, S., Girshick, R., Doll\u2019ar, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. In: CoRR (2016). \n                    arXiv:1611.05431"},{"key":"1309_CR24","unstructured":"Lan, Z., Lin, M., Li, X., Hauptmann, A.G., Raj, B.: Beyond Gaussian pyramid: multi-skip feature stacking for action recognition. In: CVPR (2015)"},{"key":"1309_CR25","doi-asserted-by":"crossref","unstructured":"Zhu, W., Hu, J., Sun, G., Cao, X., Qiao, Y.: A key volume mining deep framework for action recognition. In: CVPR, pp. 1991\u20131999 (2016)","DOI":"10.1109\/CVPR.2016.219"},{"key":"1309_CR26","unstructured":"Diba, A., Sharma, V., Van Gool, L.: Deep temporal linear encoding networks (2016). arXiv Preprint \n                    arXiv:1611.06678"},{"key":"1309_CR27","unstructured":"Zhenzhong, L., Yi, Z., Alexander, G.: Deep local video feature for action recognition. In: CoRR (2017). \n                    arXiv:1701.07368"},{"key":"1309_CR28","unstructured":"Jiang, Y.G., Liu, J., Roshan Zamir, A., Laptev, I., Piccardi, M., Shah, M., Suk-thankar, R.: THUMOS challenge: action recognition with a large number of classes (2013)"},{"key":"1309_CR29","unstructured":"Lucas, B., Kanade, T.: An iterative image registration technique with an application to stereo vision. In: Proceedings of the 7th international joint conference on artificial intelligence (IJCAI), pp. 674\u2013679 (1981)"}],"container-title":["Cluster Computing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10586-017-1309-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10586-017-1309-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10586-017-1309-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,8,12]],"date-time":"2019-08-12T14:18:33Z","timestamp":1565619513000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10586-017-1309-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,11,7]]},"references-count":29,"journal-issue":{"issue":"S1","published-print":{"date-parts":[[2019,1]]}},"alternative-id":["1309"],"URL":"https:\/\/doi.org\/10.1007\/s10586-017-1309-2","relation":{},"ISSN":["1386-7857","1573-7543"],"issn-type":[{"value":"1386-7857","type":"print"},{"value":"1573-7543","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,11,7]]},"assertion":[{"value":"31 July 2017","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 September 2017","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 October 2017","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 November 2017","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}