{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T14:57:53Z","timestamp":1775228273610,"version":"3.50.1"},"reference-count":47,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2021,4,27]],"date-time":"2021-04-27T00:00:00Z","timestamp":1619481600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,4,27]],"date-time":"2021-04-27T00:00:00Z","timestamp":1619481600000},"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":["Multimedia Systems"],"published-print":{"date-parts":[[2022,4]]},"DOI":"10.1007\/s00530-021-00793-7","type":"journal-article","created":{"date-parts":[[2021,4,27]],"date-time":"2021-04-27T04:07:32Z","timestamp":1619496452000},"page":"433-444","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Structure injected weight normalization for training deep networks"],"prefix":"10.1007","volume":"28","author":[{"given":"Xu","family":"Yuan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangjun","family":"Shen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sumet","family":"Mehta","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Teng","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shiming","family":"Ge","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhengjun","family":"Zha","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,4,27]]},"reference":[{"key":"793_CR1","doi-asserted-by":"crossref","unstructured":"Liu, M., Nie, L., Wang, X., Tian, Q., Chen, B.: Online data organizer: micro-video categorization by structure-guided multimodal dictionary learning. IEEE Transactions on Image Processing, pp. 1235\u20131247 (2018)","DOI":"10.1109\/TIP.2018.2875363"},{"key":"793_CR2","doi-asserted-by":"crossref","unstructured":"Liu, M., Qu, L., Nie, L., Liu, M., Duan, L., Chen, B.: Iterative local-global collaboration learning towards one-shot video person re-identification. IEEE Transactions on Image Processing, pp. 9360\u20139372 (2020)","DOI":"10.1109\/TIP.2020.3026625"},{"key":"793_CR3","doi-asserted-by":"crossref","unstructured":"Qu, L., Liu, M., Cao, D., Nie, L., Tian, Q.: Context-aware multi-view summarization network for image-text matching. Proceedings of the 28th ACM International Conference on Multimedia, pp. 1047\u20131055 (2020)","DOI":"10.1145\/3394171.3413961"},{"key":"793_CR4","doi-asserted-by":"crossref","unstructured":"Liu, Y., Gao, Q., Yang, Z., Wang, S.: Learning with adaptive neighbors for image clustering. In: International Joint Conference on Artificial Intelligence (IJCAI), pp. 2483\u20132489 (2018)","DOI":"10.24963\/ijcai.2018\/344"},{"key":"793_CR5","doi-asserted-by":"crossref","unstructured":"Hong, Z., Yuming, C., Su, S., Shann, T., Chang, Y., Yang, H., Ho, B.H., Tu, C., Chang, Y., Hsiao, T., et\u00a0al.: Virtual-to-real: learning to control in visual semantic segmentation. Preprint at arXiv:1802.00285 (2018)","DOI":"10.24963\/ijcai.2018\/682"},{"key":"793_CR6","doi-asserted-by":"crossref","unstructured":"Liang, B., Li, H., Su, M., Bian, P., Li, X., Shi, W.: Deep text classification can be fooled. Preprint at arXiv:1704.08006 (2018)","DOI":"10.24963\/ijcai.2018\/585"},{"key":"793_CR7","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: International Conference on Machine Learning (ICML), pp. 448\u2013456 (2015)"},{"key":"793_CR8","doi-asserted-by":"crossref","unstructured":"Wu, Y., He, K.: Group normalization. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 3\u201319 (2018)","DOI":"10.1007\/978-3-030-01261-8_1"},{"key":"793_CR9","unstructured":"Salimans, T., Kingma, D.P.: Weight normalization: a simple reparameterization to accelerate training of deep neural networks. Preprint at arXiv:1602.07868 (2016)"},{"key":"793_CR10","doi-asserted-by":"crossref","unstructured":"Huang, L., Liu, X., Lang, B., Yu, A.W., Wang, Y., Bo, L.: Orthogonal weight normalization: solution to optimization over multiple dependent stiefel manifolds in deep neural networks. In: Proceedings of the AAAI Conference on Artificial Intelligence (2018)","DOI":"10.1609\/aaai.v32i1.11768"},{"key":"793_CR11","unstructured":"Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 1929\u20131958 (2014)"},{"key":"793_CR12","unstructured":"Han, S., Pool, J., Tran, J., Dally, W.J.: Learning both weights and connections for efficient neural networks. Preprint at arXiv:1506.02626 (2015)"},{"key":"793_CR13","unstructured":"Collins, M.D., Kohli, P.: Memory bounded deep convolutional networks. Preprint at arXiv:1412.1442 (2014)"},{"key":"793_CR14","doi-asserted-by":"crossref","unstructured":"Zhu, X., Zhou, W., Li, H.: Improving deep neural network sparsity through decorrelation regularization. In: International Joint Conference on Artificial Intelligence (IJCAI), pp. 3264\u20133270 (2018)","DOI":"10.24963\/ijcai.2018\/453"},{"key":"793_CR15","unstructured":"Wen, W., Wu, C., Wang, Y., Chen, Y., Li, H.: Learning structured sparsity in deep neural networks. Preprint arXiv:1608.03665 (2016)"},{"key":"793_CR16","unstructured":"Liu, B., Wang, M., Foroosh, H., Tappen, M.F., Penksy, M.: Sparse convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 806\u2013814 (2015)"},{"key":"793_CR17","unstructured":"Friedman, J., Hastie, T., Tibshirani, R.: A note on the group lasso and a sparse group lasso. Preprint arXiv:1001.0736 (2010)"},{"key":"793_CR18","unstructured":"Zhou, Y., Jin, R., Hoi, S.C.H.: Exclusive lasso for multi-task feature selection. In: Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics (AIS-TATS), pp. 988\u2013995 (2010)"},{"key":"793_CR19","doi-asserted-by":"crossref","unstructured":"Liang, Z., Liu, N.: Efficient feature scaling for support vector machines with a quadratic kernel. Neural Process. Lett. 235\u2013246 (2014)","DOI":"10.1007\/s11063-013-9301-1"},{"key":"793_CR20","unstructured":"Cun, Y.L., Denker, J.S., Solla, S.A.: Optimal brain damage. In Advances in Neural Information Processing Systems (NeurIPS) (2000)"},{"key":"793_CR21","unstructured":"Hu, H., Peng, R., Tai, Y., Tang, C.: Network trimming: a data-driven neuron pruning approach towards efficient deep architectures. Preprint at arXiv:1607.03250 (2016)"},{"key":"793_CR22","unstructured":"Han, S., Mao, H., Dally, W.J.: Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding. Preprint at arXiv:1510.00149 (2016)"},{"key":"793_CR23","unstructured":"Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. J. Mach. Learn. Res. 249\u2013256 (2010)"},{"key":"793_CR24","unstructured":"Ba, J.L., Kiros, J.R., Hinton, G.E.: Layer normalization. Preprint at arXiv:1607.06450 (2016)"},{"key":"793_CR25","unstructured":"Ulyanov, D., Vedaldi, A., Lempitsky, V.S.: Instance normalization: the missing ingredient for fast stylization. Preprint at arXiv:1607.08022 (2016)"},{"key":"793_CR26","doi-asserted-by":"crossref","unstructured":"Pan, X., Luo, P., Shi, J., Tang, X.: Two at once: enhancing learning and generalization capacities via ibn-net: 15th European conference, Munich, Germany, September 8\u201314, 2018, proceedings, part iv. In: Proceedings of the European Conference on Computer Vision (ECCV) (2018)","DOI":"10.1007\/978-3-030-01225-0_29"},{"key":"793_CR27","doi-asserted-by":"crossref","unstructured":"Dalmau, C., Oscar, S., Oviedo, L., Harry, F.: Projected nonmonotone search methods for optimization with orthogonality constraints. Comput. Appl. Math. pp. 3118\u20133144 (2018)","DOI":"10.1007\/s40314-017-0501-6"},{"key":"793_CR28","doi-asserted-by":"crossref","unstructured":"Absil, P.-A., Mahony, R., Sepulchre, R.: Optimization algorithms on matrix manifolds (2008)","DOI":"10.1515\/9781400830244"},{"key":"793_CR29","unstructured":"Vorontsov, E., Trabelsi, C., Kadoury, S., Pal, C.: On orthogonality and learning recurrent networks with long term dependencies. In: International Conference on Machine Learning (ICML) (2017)"},{"key":"793_CR30","unstructured":"Harandi, M.T., Fernando, B.: Generalized backpropagation, ??tude de cas: Orthogonality. Preprint at arXiv:1611.05927 (2016)"},{"key":"793_CR31","unstructured":"Ozay,M., Okatani, T.: Optimization on submanifolds of convolution kernels in CNNS. Preprint at arXiv:1610.07008 (2016)"},{"key":"793_CR32","doi-asserted-by":"crossref","unstructured":"Meng, F., Cheng, H., Li, K., Xu, Z., Ji, R., Sun, X., Lu, G.: Filter grafting for deep neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6599\u20136607 (2020)","DOI":"10.1109\/CVPR42600.2020.00663"},{"key":"793_CR33","doi-asserted-by":"crossref","unstructured":"Yang, Y., Wu, J., Li, H., Li, X., Shen, T., Lin, Z.: Dynamical system inspired adaptive time stepping controller for residual network families. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 6648\u20136655 (2020)","DOI":"10.1609\/aaai.v34i04.6141"},{"key":"793_CR34","unstructured":"Xie, X., Kong, H., Wu, J., Zhang, W., Liu, G., Lin, Z.: International Conference on Machine Learning (ICML), pp. 10\u00a0483\u201310\u00a0494 (2020)"},{"key":"793_CR35","doi-asserted-by":"crossref","unstructured":"Wu, H., Gu, X.: Towards dropout training for convolutional neural networks. Neural Netw. 1\u201310 (2015)","DOI":"10.1016\/j.neunet.2015.07.007"},{"key":"793_CR36","unstructured":"Li, W., Zeiler, M.D., Zhang, S., Lecun, Y., Fergus, R.: Regularization of neural networks using dropconnect. In: International Conference on Machine Learning (ICML) (2013)"},{"key":"793_CR37","doi-asserted-by":"crossref","unstructured":"Huang, G., Sun, Y., Liu, Z., Sedra, D., Weinberger, K.: Deep networks with stochastic depth. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 646\u2013661 (2016)","DOI":"10.1007\/978-3-319-46493-0_39"},{"key":"793_CR38","unstructured":"Hwang, S.J., Grauman, K., Sha, F.: Learning a tree of metrics with disjoint visual features. In Advances in Neural Information Processing Systems (NeurIPS) (2011)"},{"key":"793_CR39","unstructured":"Kong, D., Fujimaki, R., Liu, J., Nie, F., Ding, C.: Exclusive feature learning on arbitrary structures via l1,2-norm. In: Advances in Neural Information Processing Systems (NeurIPS), pp. 1655\u20131663 (2014)"},{"key":"793_CR40","unstructured":"Molchanov, P., Tyree, S., Karras, T., Aila, T., Kautz, J.: Pruning convolutional neural networks for resource efficient transfer learning. Preprint at arXiv:1611.06440 (2016)"},{"key":"793_CR41","unstructured":"Guyon, I., Elisseeff, A.: An introduction to variable and feature selection. J. Mach. Learn. Res. 1157\u20131182 (2003)"},{"key":"793_CR42","doi-asserted-by":"crossref","unstructured":"Qu, L., Liu, M., Cao, D., Nie, L., Tian, Q.: Context-aware multi-view summarization network for image-text matching. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 1047\u20131055 (2020)","DOI":"10.1145\/3394171.3413961"},{"key":"793_CR43","doi-asserted-by":"crossref","unstructured":"Ionescu, C., Vantzos, O., Sminchisescu, C.: Matrix backpropagation for deep networks with structured layers. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 2965\u20132973 (2015)","DOI":"10.1109\/ICCV.2015.339"},{"key":"793_CR44","unstructured":"Kingma, D.P., Ba, J.: Adam: Aa method for stochastic optimization. Preprint at arXiv:1412.6980 (2014)"},{"key":"793_CR45","unstructured":"Yoon, J., Hwang, S.J.: Combined group and exclusive sparsity for deep neural networks. In: International Conference on Machine Learning (ICML), pp. 3958\u20133966 (2017)"},{"key":"793_CR46","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. Preprint at arXiv:1409.1556 (2014)"},{"key":"793_CR47","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S.E., Anguelov, D., Erhan, D., Vanhoucke, V., Rabinovich, A.: Going deeper with convolutions. In: Proceedings of the IEEE conference on Computer Vision and Pattern Recognition (CVPR), pp. 1\u20139 (2015)","DOI":"10.1109\/CVPR.2015.7298594"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-021-00793-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-021-00793-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-021-00793-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,25]],"date-time":"2022-12-25T14:17:52Z","timestamp":1671977872000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-021-00793-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,4,27]]},"references-count":47,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2022,4]]}},"alternative-id":["793"],"URL":"https:\/\/doi.org\/10.1007\/s00530-021-00793-7","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,4,27]]},"assertion":[{"value":"16 September 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 April 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 April 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}