{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:05:35Z","timestamp":1777655135942,"version":"3.51.4"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783031160134","type":"print"},{"value":"9783031160141","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-16014-1_59","type":"book-chapter","created":{"date-parts":[[2022,9,20]],"date-time":"2022-09-20T23:03:09Z","timestamp":1663714989000},"page":"755-767","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["TT-ViT: Vision Transformer Compression Using Tensor-Train Decomposition"],"prefix":"10.1007","author":[{"given":"Hoang","family":"Pham Minh","sequence":"first","affiliation":[]},{"given":"Nguyen","family":"Nguyen Xuan","sequence":"additional","affiliation":[]},{"given":"Son","family":"Tran Thai","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,9,21]]},"reference":[{"issue":"4\u20135","key":"59_CR1","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1561\/2200000059","volume":"9","author":"A Cichocki","year":"2016","unstructured":"Cichocki, A., Lee, N., Oseledets, I., Phan, A.H., Zhao, Q., Mandic, D.P.: Tensor networks for dimensionality reduction and large-scale optimization: part 1 low-rank tensor decompositions. Found. Trends Mach. Learn. 9(4\u20135), 249\u2013429 (2016)","journal-title":"Found. Trends Mach. Learn."},{"key":"59_CR2","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: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255 (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"59_CR3","unstructured":"Devlin, J., Chang, M., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American NAACL-HLT 2019, Minneapolis, MN, USA, 2\u20137 June 2019, vol. 1 (Long and Short Papers), pp. 4171\u20134186. Association for Computational Linguistics (2019)"},{"key":"59_CR4","unstructured":"Dosovitskiy, A., et al.: An image is worth 16 $$\\times $$ 16 words: transformers for image recognition at scale. In: International Conference on Learning Representations (2021)"},{"key":"59_CR5","unstructured":"Garipov, T., Podoprikhin, D., Novikov, A., Vetrov, D.P.: Ultimate tensorization: compressing convolutional and FC layers alike. CoRR abs\/1611.03214 (2016)"},{"issue":"12","key":"59_CR6","doi-asserted-by":"publisher","first-page":"2213","DOI":"10.1109\/TASLP.2019.2944078","volume":"27","author":"Q Guo","year":"2019","unstructured":"Guo, Q., Qiu, X., Xue, X., Zhang, Z.: Low-rank and locality constrained self-attention for sequence modeling. IEEE\/ACM Trans. Audio Speech Lang. Process. 27(12), 2213\u20132222 (2019)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"issue":"3","key":"59_CR7","doi-asserted-by":"publisher","first-page":"688","DOI":"10.1109\/JSTSP.2020.3042063","volume":"15","author":"PM Hoang","year":"2021","unstructured":"Hoang, P.M., Tuan, H.D., Son, T.T., Poor, H.V.: Qualitative HD image and video recovery via high-order tensor augmentation and completion. IEEE J. Sel. Topics Signal Process. 15(3), 688\u2013701 (2021)","journal-title":"IEEE J. Sel. Topics Signal Process."},{"key":"59_CR8","doi-asserted-by":"crossref","unstructured":"Jaderberg, M., Vedaldi, A., Zisserman, A.: Speeding up convolutional neural networks with low rank expansions. In: Valstar, M.F., French, A.P., Pridmore, T.P. (eds.) British Machine Vision Conference, BMVC 2014, Nottingham, UK, 1\u20135 September 2014. BMVA Press (2014)","DOI":"10.5244\/C.28.88"},{"key":"59_CR9","unstructured":"Kim, Y., Park, E., Yoo, S., Choi, T., Yang, L., Shin, D.: Compression of deep convolutional neural networks for fast and low power mobile applications. In: Bengio, Y., LeCun, Y. (eds.) 4th International Conference on Learning Representations, ICLR 2016, San Juan, Puerto Rico, 2\u20134 May 2016, Conference Track Proceedings (2016)"},{"key":"59_CR10","unstructured":"Krizhevsky, A., Hinton, G.: Learning multiple layers of features from tiny images. Technical Report 0, University of Toronto, Toronto, Ontario (2009)"},{"key":"59_CR11","unstructured":"Lebedev, V., Ganin, Y., Rakhuba, M., Oseledets, I.V., Lempitsky, V.S.: Speeding-up convolutional neural networks using fine-tuned CP-decomposition. In: 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, 7\u20139 May 2015, Conference Track Proceedings (2015)"},{"issue":"11","key":"59_CR12","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y Lecun","year":"1998","unstructured":"Lecun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278\u20132324 (1998)","journal-title":"Proc. IEEE"},{"key":"59_CR13","doi-asserted-by":"crossref","unstructured":"Lee, N., Cichocki, A.: Fundamental tensor operations for large-scale data analysis in tensor train formats (2016)","DOI":"10.1007\/s11045-017-0481-0"},{"key":"59_CR14","unstructured":"Liu, Y., et al.: Roberta: a robustly optimized BERT pretraining approach. CoRR abs\/1907.11692 (2019)"},{"issue":"4","key":"59_CR15","doi-asserted-by":"publisher","first-page":"944","DOI":"10.1109\/TCSVT.2019.2901311","volume":"30","author":"Y Liu","year":"2020","unstructured":"Liu, Y., Long, Z., Huang, H., Zhu, C.: Low CP rank and Tucker rank tensor completion for estimating missing components in image data. IEEE Trans. Circ. Syst. Video Techn. 30(4), 944\u2013954 (2020)","journal-title":"IEEE Trans. Circ. Syst. Video Techn."},{"key":"59_CR16","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 10012\u201310022, October 2021","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"59_CR17","unstructured":"Ma, X., et al.: A tensorized transformer for language modeling. In: Wallach, H., Larochelle, H., Beygelzimer, A., d\u2019 Alch\u00e9-Buc, F., Fox, E., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 32. Curran Associates, Inc. (2019)"},{"key":"59_CR18","unstructured":"Novikov, A., Podoprikhin, D., Osokin, A., Vetrov, D.P.: Tensorizing neural networks. In: Advances in Neural Information Processing Systems, vol. 28. Curran Associates, Inc. (2015)"},{"issue":"4","key":"59_CR19","doi-asserted-by":"publisher","first-page":"2130","DOI":"10.1137\/090757861","volume":"31","author":"IV Oseledets","year":"2010","unstructured":"Oseledets, I.V.: Approximation of $$2^d \\times 2^d$$ matrices using tensor decomposition. SIAM J. Matrix Anal. Appl. 31(4), 2130\u20132145 (2010)","journal-title":"SIAM J. Matrix Anal. Appl."},{"issue":"5","key":"59_CR20","doi-asserted-by":"publisher","first-page":"2295","DOI":"10.1137\/090752286","volume":"33","author":"IV Oseledets","year":"2011","unstructured":"Oseledets, I.V.: Tensor-train decomposition. SIAM J. Sci. Comput. 33(5), 2295\u20132317 (2011)","journal-title":"SIAM J. Sci. Comput."},{"key":"59_CR21","unstructured":"Radford, A., Narasimhan, K.: Improving language understanding by generative pre-training (2018)"},{"key":"59_CR22","doi-asserted-by":"publisher","DOI":"10.1016\/j.physd.2019.132306","volume":"404","author":"A Sherstinsky","year":"2020","unstructured":"Sherstinsky, A.: Fundamentals of recurrent neural network (RNN) and long short-term memory (LSTM) network. Physica D 404, 132306 (2020)","journal-title":"Physica D"},{"key":"59_CR23","doi-asserted-by":"crossref","unstructured":"Song, D., Zhang, P., Li, F.: Speeding up deep convolutional neural networks based on tucker-CP decomposition. In: Proceedings of the 2020 5th International Conference on Machine Learning Technologies, pp. 56\u201361. Association for Computing Machinery, New York, NY, USA (2020)","DOI":"10.1145\/3409073.3409094"},{"key":"59_CR24","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., Jegou, H.: Training data-efficient image transformers & distillation through attention. In: International Conference on Machine Learning, vol. 139, pp. 10347\u201310357, July 2021"},{"key":"59_CR25","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30. Curran Associates, Inc. (2017)"},{"key":"59_CR26","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: Pyramid vision transformer: a versatile backbone for dense prediction without convolutions. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 568\u2013578, October 2021","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"59_CR27","unstructured":"Xiao, H., Rasul, K., Vollgraf, R.: Fashion-MNIST: a novel image dataset for benchmarking machine learning algorithms (2017)"},{"key":"59_CR28","doi-asserted-by":"crossref","unstructured":"Xing, Y., Yang, S., Jiao, L.: Hyperspectral image super-resolution based on tensor spatial-spectral joint correlation regularization. IEEE Access IEEE, vol. 8, pp. 63654\u201363665, 2020 8, 63654\u201363665 (2020)","DOI":"10.1109\/ACCESS.2020.2982494"},{"key":"59_CR29","unstructured":"Yang, Y., Krompass, D., Tresp, V.: Tensor-train recurrent neural networks for video classification. In: Proceedings of the 34th International Conference on Machine Learning, vol. 70, pp. 3891\u20133900. ICML 2017, JMLR.org (2017)"}],"container-title":["Lecture Notes in Computer Science","Computational Collective Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-16014-1_59","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,9]],"date-time":"2023-03-09T12:13:33Z","timestamp":1678364013000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-16014-1_59"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031160134","9783031160141"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-16014-1_59","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"21 September 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}