{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T15:54:38Z","timestamp":1780674878823,"version":"3.54.1"},"reference-count":203,"publisher":"Association for Computing Machinery (ACM)","issue":"5","license":[{"start":{"date-parts":[[2025,1,24]],"date-time":"2025-01-24T00:00:00Z","timestamp":1737676800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62272170"],"award-info":[{"award-number":["62272170"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"General Program of Shanghai Natural Science Foundation","award":["24ZR1419800, 23ZR1419300"],"award-info":[{"award-number":["24ZR1419800, 23ZR1419300"]}]},{"DOI":"10.13039\/501100003399","name":"Science and Technology Commission of Shanghai Municipality","doi-asserted-by":"crossref","award":["22DZ2229004"],"award-info":[{"award-number":["22DZ2229004"]}],"id":[{"id":"10.13039\/501100003399","id-type":"DOI","asserted-by":"crossref"}]},{"name":"\u201cDigital Silk Road\u201d Shanghai International Joint Lab of Trustworthy Intelligent Software","award":["22510750100"],"award-info":[{"award-number":["22510750100"]}]},{"name":"Shanghai Trusted Industry Internet Software Collaborative Innovation Center"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Comput. Surv."],"published-print":{"date-parts":[[2025,5,31]]},"abstract":"<jats:p>\n            Deep Learning (DL) has achieved remarkable success in tackling complex Artificial Intelligence tasks. The standard training of neural networks employs backpropagation to compute gradients and utilizes various optimization algorithms in the Euclidean space \u211b\n            <jats:italic>\n              <jats:sup>n<\/jats:sup>\n            <\/jats:italic>\n            . However, this optimization process faces challenges, such as the local optimal issues and the problem of gradient vanishing and exploding. To address these problems, Riemannian optimization offers a powerful extension to solve optimization problems in deep learning. By incorporating the prior constraint structure and the metric information of the underlying geometric information, Riemannian optimization-based DL offers a more stable and reliable optimization process, as well as enhanced adaptability to complex data structures. This article presents a comprehensive survey of applying geometric optimization in DL, including the basic procedure of geometric optimization, various geometric optimizers, and some concepts of the Riemannian manifold. In addition, it investigates various applications of geometric optimization in different DL networks for diverse tasks and discusses typical public toolboxes that implement optimization on the manifold. This article also includes a performance comparison among different deep geometric optimization methods in image recognition scenarios. Finally, this article elaborates on future opportunities and challenges in this field.\n          <\/jats:p>","DOI":"10.1145\/3708498","type":"journal-article","created":{"date-parts":[[2024,12,26]],"date-time":"2024-12-26T09:31:57Z","timestamp":1735205517000},"page":"1-37","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":23,"title":["A Survey of Geometric Optimization for Deep Learning: From Euclidean Space to Riemannian Manifold"],"prefix":"10.1145","volume":"57","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2503-6929","authenticated-orcid":false,"given":"Yanhong","family":"Fei","sequence":"first","affiliation":[{"name":"East China Normal University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-4872-2404","authenticated-orcid":false,"given":"Yingjie","family":"Liu","sequence":"additional","affiliation":[{"name":"East China Normal University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-8480-999X","authenticated-orcid":false,"given":"Chentao","family":"Jia","sequence":"additional","affiliation":[{"name":"East China Normal University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2836-276X","authenticated-orcid":false,"given":"Zhengyu","family":"Li","sequence":"additional","affiliation":[{"name":"East China Normal University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9566-7814","authenticated-orcid":false,"given":"Xian","family":"Wei","sequence":"additional","affiliation":[{"name":"East China Normal University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3922-0989","authenticated-orcid":false,"given":"Mingsong","family":"Chen","sequence":"additional","affiliation":[{"name":"East China Normal University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,1,24]]},"reference":[{"key":"e_1_3_3_2_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10710-017-9314-z"},{"key":"e_1_3_3_3_2","doi-asserted-by":"publisher","DOI":"10.1126\/science.abe5650"},{"key":"e_1_3_3_4_2","first-page":"6105","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Tan Mingxing","year":"2019","unstructured":"Mingxing Tan and Quoc Le. 2019. EfficientNet: Rethinking model scaling for convolutional neural networks. In Proceedings of the International Conference on Machine Learning. 6105\u20136114."},{"key":"e_1_3_3_5_2","first-page":"1","volume-title":"Proceedings of the Conference on Advances in Neural Information Processing Systems","author":"He Zhen","year":"2017","unstructured":"Zhen He, Shaobing Gao, Liang Xiao, Daxue Liu, Hangen He, and David Barber. 2017. Wider and deeper, cheaper and faster: Tensorized LSTMs for sequence learning. In Proceedings of the Conference on Advances in Neural Information Processing Systems. 1\u201311."},{"key":"e_1_3_3_6_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Rolnick David","year":"2018","unstructured":"David Rolnick and Max Tegmark. 2018. The power of deeper networks for expressing natural functions. In Proceedings of the International Conference on Learning Representations."},{"key":"e_1_3_3_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01152"},{"key":"e_1_3_3_8_2","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014).","journal-title":"arXiv preprint arXiv:1409.1556"},{"key":"e_1_3_3_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_3_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01548"},{"key":"e_1_3_3_11_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i12.29276"},{"key":"e_1_3_3_12_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i14.29512"},{"key":"e_1_3_3_13_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Dosovitskiy Alexey","year":"2021","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gellyet al.2021. An image is worth 16x16 words: Transformers for image recognition at scale. In Proceedings of the International Conference on Learning Representations. Retrieved from https:\/\/openreview.net\/forum?id=YicbFdNTTy"},{"key":"e_1_3_3_14_2","article-title":"Attention is all you need","volume":"30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Proc. Advan. Neural Inf. Process. Syst. 30 (2017).","journal-title":"Proc. Advan. Neural Inf. Process. Syst."},{"key":"e_1_3_3_15_2","article-title":"Riemannian self-attention mechanism for SPD networks","author":"Wang Rui","year":"2023","unstructured":"Rui Wang, Xiao-Jun Wu, Hui Li, and Josef Kittler. 2023. Riemannian self-attention mechanism for SPD networks. arXiv preprint arXiv:2311.16738 (2023).","journal-title":"arXiv preprint arXiv:2311.16738"},{"key":"e_1_3_3_16_2","doi-asserted-by":"publisher","DOI":"10.1515\/9781400830244"},{"key":"e_1_3_3_17_2","doi-asserted-by":"publisher","DOI":"10.1017\/9781009166164"},{"key":"e_1_3_3_18_2","doi-asserted-by":"publisher","DOI":"10.1007\/s40305-020-00295-9"},{"key":"e_1_3_3_19_2","doi-asserted-by":"publisher","DOI":"10.5555\/3161468"},{"key":"e_1_3_3_20_2","first-page":"4266","volume-title":"Proceedings of the International Conference on Neural Information Processing Systems","author":"Bansal Nitin","year":"2018","unstructured":"Nitin Bansal, Xiaohan Chen, and Zhangyang Wang. 2018. Can we gain more from orthogonality regularizations in training deep CNNs. In Proceedings of the International Conference on Neural Information Processing Systems. 4266\u20134276."},{"key":"e_1_3_3_21_2","first-page":"3794","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Lezcano-Casado Mario","year":"2019","unstructured":"Mario Lezcano-Casado and David Mart\u0131nez-Rubio. 2019. Cheap orthogonal constraints in neural networks: A simple parametrization of the orthogonal and unitary group. In Proceedings of the International Conference on Machine Learning. 3794\u20133803."},{"key":"e_1_3_3_22_2","first-page":"1120","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Arjovsky Martin","year":"2016","unstructured":"Martin Arjovsky, Amar Shah, and Yoshua Bengio. 2016. Unitary evolution recurrent neural networks. In Proceedings of the International Conference on Machine Learning. 1120\u20131128."},{"key":"e_1_3_3_23_2","article-title":"O-ViT: Orthogonal vision transformer","author":"Fei Yanhong","year":"2022","unstructured":"Yanhong Fei, Yingjie Liu, Xian Wei, and Mingsong Chen. 2022. O-ViT: Orthogonal vision transformer. arXiv preprint arXiv:2201.12133 (2022).","journal-title":"arXiv preprint arXiv:2201.12133"},{"key":"e_1_3_3_24_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-12598-0_12"},{"key":"e_1_3_3_25_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2011.08.002"},{"issue":"3","key":"e_1_3_3_26_2","first-page":"113","article-title":"Optimization techniques on Riemannian manifolds","volume":"3","author":"Smith Steven T.","year":"1994","unstructured":"Steven T. Smith. 1994. Optimization techniques on Riemannian manifolds. Fields Inst. Commun. 3, 3 (1994), 113\u2013135.","journal-title":"Fields Inst. Commun."},{"key":"e_1_3_3_27_2","volume-title":"Deep Grassmann Manifold Optimization for Computer Vision","author":"Minnehan Breton Lawrence","year":"2019","unstructured":"Breton Lawrence Minnehan. 2019. Deep Grassmann Manifold Optimization for Computer Vision. Rochester Institute of Technology."},{"key":"e_1_3_3_28_2","unstructured":"Mario Lezcano-Casado. 2022. Geometric optimisation on manifolds with applications to deep learning. arXiv preprint arXiv:2203.04794 (2022)."},{"key":"e_1_3_3_29_2","doi-asserted-by":"publisher","DOI":"10.5555\/2686068.2686333"},{"key":"e_1_3_3_30_2","doi-asserted-by":"publisher","DOI":"10.1093\/imanum\/23.3.395"},{"key":"e_1_3_3_31_2","doi-asserted-by":"publisher","DOI":"10.1023\/A:1012930416777"},{"key":"e_1_3_3_32_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10589-009-9251-8"},{"key":"e_1_3_3_33_2","article-title":"Gradient descent ascent for minimax problems on Riemannian manifolds","author":"Huang Feihu","year":"2023","unstructured":"Feihu Huang and Shangqian Gao. 2023. Gradient descent ascent for minimax problems on Riemannian manifolds. IEEE Trans. Pattern Anal. Mach. Intell. 45, 7 (2023), 8466\u20138476.","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"e_1_3_3_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2013.2254619"},{"key":"e_1_3_3_35_2","doi-asserted-by":"publisher","DOI":"10.1007\/b98874"},{"key":"e_1_3_3_36_2","volume-title":"Linear and Nonlinear Programming","author":"Luenberger David G.","year":"1984","unstructured":"David G. Luenberger and Yinyu Ye. 1984. Linear and Nonlinear Programming. Vol. 2. Springer."},{"key":"e_1_3_3_37_2","doi-asserted-by":"publisher","DOI":"10.1007\/BF00934767"},{"key":"e_1_3_3_38_2","doi-asserted-by":"publisher","DOI":"10.1090\/pspum\/054.1\/1216576"},{"key":"e_1_3_3_39_2","doi-asserted-by":"publisher","DOI":"10.1137\/S0895479895290954"},{"key":"e_1_3_3_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.63"},{"key":"e_1_3_3_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.569"},{"key":"e_1_3_3_42_2","doi-asserted-by":"publisher","DOI":"10.5555\/3115489.3115871"},{"key":"e_1_3_3_43_2","doi-asserted-by":"publisher","DOI":"10.1145\/3218822"},{"key":"e_1_3_3_44_2","volume-title":"Learning Sparse Data Models via Geometric Optimization with Applications to Image Processing","author":"Hawe Simon Alois","year":"2013","unstructured":"Simon Alois Hawe. 2013. Learning Sparse Data Models via Geometric Optimization with Applications to Image Processing. Ph.D. Dissertation. Technische Universit\u00e4t M\u00fcnchen."},{"key":"e_1_3_3_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2691549"},{"key":"e_1_3_3_46_2","doi-asserted-by":"publisher","DOI":"10.1137\/100802529"},{"key":"e_1_3_3_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00469"},{"key":"e_1_3_3_48_2","doi-asserted-by":"publisher","DOI":"10.1162\/neco_a_01174"},{"key":"e_1_3_3_49_2","first-page":"3570","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Vorontsov Eugene","year":"2017","unstructured":"Eugene Vorontsov, Chiheb Trabelsi, Samuel Kadoury, and Chris Pal. 2017. On orthogonality and learning recurrent networks with long term dependencies. In Proceedings of the International Conference on Machine Learning. 3570\u20133578."},{"key":"e_1_3_3_50_2","volume-title":"Proceedings of the Conference on Advances in Neural Information Processing Systems","volume":"29","author":"Wisdom Scott","year":"2016","unstructured":"Scott Wisdom, Thomas Powers, John Hershey, Jonathan Le Roux, and Les Atlas. 2016. Full-capacity unitary recurrent neural networks. In Proceedings of the Conference on Advances in Neural Information Processing Systems, Vol. 29."},{"key":"e_1_3_3_51_2","first-page":"2401","volume-title":"Proceedings of the International Conference on Machine Learning","volume":"70","author":"Mhammedi Zakaria","year":"2017","unstructured":"Zakaria Mhammedi, Andrew Hellicar, Ashfaqur Rahman, and James Bailey. 2017. Efficient orthogonal parametrisation of recurrent neural networks using householder reflections. In Proceedings of the International Conference on Machine Learning, Vol. 70. 2401\u20132409."},{"key":"e_1_3_3_52_2","first-page":"2401","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Mhammedi Zakaria","year":"2017","unstructured":"Zakaria Mhammedi, Andrew Hellicar, Ashfaqur Rahman, and James Bailey. 2017. Efficient orthogonal parametrisation of recurrent neural networks using householder reflections. In Proceedings of the International Conference on Machine Learning. 2401\u20132409."},{"key":"e_1_3_3_53_2","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390204"},{"key":"e_1_3_3_54_2","article-title":"Grassmannian learning: Embedding geometry awareness in shallow and deep learning","author":"Zhang Jiayao","year":"2018","unstructured":"Jiayao Zhang, Guangxu Zhu, Robert W. Heath Jr, and Kaibin Huang. 2018. Grassmannian learning: Embedding geometry awareness in shallow and deep learning. arXiv preprint arXiv:1808.02229 (2018).","journal-title":"arXiv preprint arXiv:1808.02229"},{"key":"e_1_3_3_55_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11725"},{"key":"e_1_3_3_56_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4419-9982-5_1"},{"key":"e_1_3_3_57_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-022-06258-w"},{"key":"e_1_3_3_58_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2729660"},{"key":"e_1_3_3_59_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10866"},{"key":"e_1_3_3_60_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00772"},{"key":"e_1_3_3_61_2","first-page":"8940","article-title":"On Riemannian optimization over positive definite matrices with the Bures-Wasserstein geometry","volume":"34","author":"Han Andi","year":"2021","unstructured":"Andi Han, Bamdev Mishra, Pratik Kumar Jawanpuria, and Junbin Gao. 2021. On Riemannian optimization over positive definite matrices with the Bures-Wasserstein geometry. Proc. Advan. Neural Inf. Process. Syst. 34 (2021), 8940\u20138953.","journal-title":"Proc. Advan. Neural Inf. Process. Syst."},{"key":"e_1_3_3_62_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-38271-0_40"},{"key":"e_1_3_3_63_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15552-9_28"},{"key":"e_1_3_3_64_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10605-2_2"},{"key":"e_1_3_3_65_2","first-page":"720","volume-title":"Proceedings of the International Conference on Machine Learning","volume":"37","author":"Huang Zhiwu","year":"2015","unstructured":"Zhiwu Huang, Ruiping Wang, Shiguang Shan, Xianqiu Li, and Xilin Chen. 2015. Log-Euclidean metric learning on symmetric positive definite manifold with application to image set classification. In Proceedings of the International Conference on Machine Learning, Vol. 37. 720\u2013729."},{"issue":"59","key":"e_1_3_3_66_2","first-page":"2","article-title":"Hyperbolic geometry","volume":"31","author":"Cannon James W.","year":"1997","unstructured":"James W. Cannon, William J. Floyd, Richard Kenyon, and Walter R. Parry. 1997. Hyperbolic geometry. Flav Geom. 31, 59-115 (1997), 2.","journal-title":"Flav Geom."},{"key":"e_1_3_3_67_2","article-title":"An introduction to geometric topology","author":"Martelli Bruno","year":"2016","unstructured":"Bruno Martelli. 2016. An introduction to geometric topology. arXiv preprint arXiv:1610.02592 (2016).","journal-title":"arXiv preprint arXiv:1610.02592"},{"key":"e_1_3_3_68_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587407"},{"key":"e_1_3_3_69_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-28649-3_32"},{"key":"e_1_3_3_70_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.387"},{"key":"e_1_3_3_71_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206806"},{"key":"e_1_3_3_72_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10928"},{"key":"e_1_3_3_73_2","doi-asserted-by":"publisher","DOI":"10.1109\/78.984753"},{"issue":"1012","key":"e_1_3_3_74_2","first-page":"317","article-title":"Random walk on a sphere and on a Riemannian manifold","volume":"252","author":"Roberts Paul Harry","year":"1960","unstructured":"Paul Harry Roberts and Harold Douglas Ursell. 1960. Random walk on a sphere and on a Riemannian manifold. Philos. Trans. R. Societ. Lond. Series A, Math. Phys. Sci. 252, 1012 (1960), 317\u2013356.","journal-title":"Philos. Trans. R. Societ. Lond. Series A, Math. Phys. Sci."},{"key":"e_1_3_3_75_2","volume-title":"Proceedings of the International Symposium on Mathematical Theory of Networks and Systems","author":"Kleinsteuber Martin","year":"2010","unstructured":"Martin Kleinsteuber and Hao Shen. 2010. Intrinsic Newton\u2019s method on oblique manifolds for overdetermined blind source separation. In Proceedings of the International Symposium on Mathematical Theory of Networks and Systems."},{"key":"e_1_3_3_76_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00830"},{"key":"e_1_3_3_77_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2022.05.001"},{"key":"e_1_3_3_78_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.52"},{"key":"e_1_3_3_79_2","first-page":"3262","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Kasai Hiroyuki","year":"2019","unstructured":"Hiroyuki Kasai, Pratik Jawanpuria, and Bamdev Mishra. 2019. Riemannian adaptive stochastic gradient algorithms on matrix manifolds. In Proceedings of the International Conference on Machine Learning. 3262\u20133271."},{"key":"e_1_3_3_80_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3049845"},{"key":"e_1_3_3_81_2","article-title":"Riemannian adaptive optimization methods","author":"B\u00e9cigneul Gary","year":"2018","unstructured":"Gary B\u00e9cigneul and Octavian-Eugen Ganea. 2018. Riemannian adaptive optimization methods. arXiv preprint arXiv:1810.00760 (2018).","journal-title":"arXiv preprint arXiv:1810.00760"},{"key":"e_1_3_3_82_2","article-title":"Towards Riemannian accelerated gradient methods","author":"Zhang Hongyi","year":"2018","unstructured":"Hongyi Zhang and Suvrit Sra. 2018. Towards Riemannian accelerated gradient methods. arXiv preprint arXiv:1806.02812 (2018).","journal-title":"arXiv preprint arXiv:1806.02812"},{"key":"e_1_3_3_83_2","first-page":"84","volume-title":"Proceedings of the Conference on Learning Theory","author":"Ahn Kwangjun","year":"2020","unstructured":"Kwangjun Ahn and Suvrit Sra. 2020. From Nesterov\u2019s estimate sequence to Riemannian acceleration. In Proceedings of the Conference on Learning Theory. 84\u2013118."},{"key":"e_1_3_3_84_2","first-page":"1351","volume-title":"Proceedings of the International Conference on Artificial Intelligence and Statistics","author":"Alimisis Foivos","year":"2021","unstructured":"Foivos Alimisis, Antonio Orvieto, Gary Becigneul, and Aurelien Lucchi. 2021. Momentum improves optimization on Riemannian manifolds. In Proceedings of the International Conference on Artificial Intelligence and Statistics. 1351\u20131359."},{"key":"e_1_3_3_85_2","article-title":"A Riemannian ADMM","author":"Li Jiaxiang","year":"2022","unstructured":"Jiaxiang Li, Shiqian Ma, and Tejes Srivastava. 2022. A Riemannian ADMM. arXiv preprint arXiv:2211.02163 (2022).","journal-title":"arXiv preprint arXiv:2211.02163"},{"issue":"5","key":"e_1_3_3_86_2","first-page":"5935","article-title":"Learning to optimize on Riemannian manifolds","volume":"45","author":"Gao Zhi","year":"2022","unstructured":"Zhi Gao, Yuwei Wu, Xiaomeng Fan, Mehrtash Harandi, and Yunde Jia. 2022. Learning to optimize on Riemannian manifolds. IEEE Trans. Pattern Anal. Mach. Intell. 45, 5 (2022), 5935\u20135952.","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"e_1_3_3_87_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i4.20287"},{"key":"e_1_3_3_88_2","doi-asserted-by":"publisher","DOI":"10.1287\/moor.2022.1302"},{"key":"e_1_3_3_89_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3112139"},{"key":"e_1_3_3_90_2","article-title":"Riemannian bilevel optimization","author":"Li Jiaxiang","year":"2024","unstructured":"Jiaxiang Li and Shiqian Ma. 2024. Riemannian bilevel optimization. arXiv preprint arXiv:2402.02019 (2024).","journal-title":"arXiv preprint arXiv:2402.02019"},{"key":"e_1_3_3_91_2","article-title":"A framework for bi-level optimization on Riemannian manifolds","author":"Han Andi","year":"2024","unstructured":"Andi Han, Bamdev Mishra, Pratik Jawanpuria, and Akiko Takeda. 2024. A framework for bi-level optimization on Riemannian manifolds. arXiv preprint arXiv:2402.03883 (2024).","journal-title":"arXiv preprint arXiv:2402.03883"},{"key":"e_1_3_3_92_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_32"},{"key":"e_1_3_3_93_2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2925510"},{"key":"e_1_3_3_94_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.106332"},{"key":"e_1_3_3_95_2","doi-asserted-by":"publisher","DOI":"10.1049\/iet-rsn.2009.0294"},{"key":"e_1_3_3_96_2","doi-asserted-by":"publisher","DOI":"10.3390\/rs11060681"},{"key":"e_1_3_3_97_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-40763-5_78"},{"key":"e_1_3_3_98_2","doi-asserted-by":"publisher","DOI":"10.3390\/jimaging5010005"},{"key":"e_1_3_3_99_2","doi-asserted-by":"publisher","DOI":"10.1002\/hbm.25561"},{"key":"e_1_3_3_100_2","doi-asserted-by":"publisher","DOI":"10.1002\/wics.1222"},{"key":"e_1_3_3_101_2","article-title":"Manifold learning: What, how, and why","volume":"11","author":"Meil\u0103 Marina","year":"2023","unstructured":"Marina Meil\u0103 and Hanyu Zhang. 2023. Manifold learning: What, how, and why. Ann. Rev. Statist. Its Applic. 11 (2023), 393\u2013417.","journal-title":"Ann. Rev. Statist. Its Applic."},{"key":"e_1_3_3_102_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2003.08.006"},{"key":"e_1_3_3_103_2","doi-asserted-by":"publisher","DOI":"10.2307\/2985919"},{"key":"e_1_3_3_104_2","doi-asserted-by":"publisher","DOI":"10.1016\/0169-7439(87)80084-9"},{"key":"e_1_3_3_105_2","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2018.2846588"},{"key":"e_1_3_3_106_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447172"},{"key":"e_1_3_3_107_2","doi-asserted-by":"publisher","DOI":"10.1007\/11552253_29"},{"key":"e_1_3_3_108_2","doi-asserted-by":"publisher","DOI":"10.1198\/106186008X318440"},{"key":"e_1_3_3_109_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.acha.2006.04.006"},{"issue":"11","key":"e_1_3_3_110_2","article-title":"Visualizing data using t-SNE.","volume":"9","author":"Maaten Laurens Van der","year":"2008","unstructured":"Laurens Van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE. J. Mach. Learn. Res. 9, 11 (2008), 2579\u20132605.","journal-title":"J. Mach. Learn. Res."},{"key":"e_1_3_3_111_2","doi-asserted-by":"publisher","DOI":"10.1038\/nbt.4314"},{"key":"e_1_3_3_112_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41587-019-0336-3"},{"key":"e_1_3_3_113_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2012.98"},{"key":"e_1_3_3_114_2","doi-asserted-by":"publisher","DOI":"10.3390\/s20030767"},{"key":"e_1_3_3_115_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.06.077"},{"key":"e_1_3_3_116_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2726188"},{"key":"e_1_3_3_117_2","volume-title":"Proceedings of the International Symposium of Mathematical Theory of Networks and Systems","author":"Shen Hao","year":"2010","unstructured":"Hao Shen, Klaus Diepold, and Knut H\u00fcper. 2010. A geometric revisit to the trace quotient problem. In Proceedings of the International Symposium of Mathematical Theory of Networks and Systems."},{"key":"e_1_3_3_118_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2836802"},{"key":"e_1_3_3_119_2","doi-asserted-by":"publisher","DOI":"10.1002\/nla.743"},{"key":"e_1_3_3_120_2","article-title":"Riemannian metrics for neural networks","volume":"2","author":"Ollivier Yann","year":"2013","unstructured":"Yann Ollivier. 2013. Riemannian metrics for neural networks. Inf. Infer.: J. IMA 2 (2013), 108\u2013193.","journal-title":"Inf. Infer.: J. IMA"},{"key":"e_1_3_3_121_2","article-title":"Riemannian SVRG: Fast stochastic optimization on Riemannian manifolds","volume":"29","author":"Zhang Hongyi","year":"2016","unstructured":"Hongyi Zhang, Sashank J. Reddi, and Suvrit Sra. 2016. Riemannian SVRG: Fast stochastic optimization on Riemannian manifolds. Proc. Advan. Neural Inf. Process. Syst. 29 (2016), 4599\u20134607.","journal-title":"Proc. Advan. Neural Inf. Process. Syst."},{"key":"e_1_3_3_122_2","article-title":"Generalized backpropagation, \u00c9tude de cas: Orthogonality","volume":"1611","author":"Harandi Mehrtash","year":"2016","unstructured":"Mehrtash Harandi and Basura Fernando. 2016. Generalized backpropagation, \u00c9tude de cas: Orthogonality. arXiv abs\/1611.05927 (2016).","journal-title":"arXiv"},{"key":"e_1_3_3_123_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.137"},{"key":"e_1_3_3_124_2","doi-asserted-by":"publisher","DOI":"10.1214\/24-EJS2227"},{"key":"e_1_3_3_125_2","article-title":"Optimization on submanifolds of convolution kernels in CNNs","volume":"1610","author":"Ozay M.","year":"2016","unstructured":"M. Ozay and Takayuki Okatani. 2016. Optimization on submanifolds of convolution kernels in CNNs. arXiv abs\/1610.07008 (2016).","journal-title":"arXiv"},{"key":"e_1_3_3_126_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2866688"},{"key":"e_1_3_3_127_2","doi-asserted-by":"publisher","DOI":"10.1145\/2663204.2666274"},{"key":"e_1_3_3_128_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2014.2359471"},{"key":"e_1_3_3_129_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11768"},{"key":"e_1_3_3_130_2","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2018.2884211"},{"key":"e_1_3_3_131_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00170"},{"key":"e_1_3_3_132_2","article-title":"How to construct deep recurrent neural networks","volume":"1312","author":"Pascanu Razvan","year":"2014","unstructured":"Razvan Pascanu, \u00c7aglar G\u00fcl\u00e7ehre, Kyunghyun Cho, and Yoshua Bengio. 2014. How to construct deep recurrent neural networks. arXiv abs\/1312.6026 (2014).","journal-title":"arXiv"},{"key":"e_1_3_3_133_2","first-page":"315","volume-title":"Proceedings of the International Conference on Artificial Intelligence and Statistics","author":"Glorot Xavier","year":"2011","unstructured":"Xavier Glorot, Antoine Bordes, and Yoshua Bengio. 2011. Deep sparse rectifier neural networks. In Proceedings of the International Conference on Artificial Intelligence and Statistics. 315\u2013323."},{"key":"e_1_3_3_134_2","first-page":"807","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Nair Vinod","year":"2010","unstructured":"Vinod Nair and Geoffrey E. Hinton. 2010. Rectified linear units improve restricted Boltzmann machines. In Proceedings of the International Conference on Machine Learning. 807\u2013814."},{"key":"e_1_3_3_135_2","first-page":"435","volume-title":"Proceedings of the International Conference on Neural Information Processing Systems","author":"Kanai Sekitoshi","year":"2017","unstructured":"Sekitoshi Kanai, Yasuhiro Fujiwara, and Sotetsu Iwamura. 2017. Preventing gradient explosions in gated recurrent units. In Proceedings of the International Conference on Neural Information Processing Systems. 435\u2013444."},{"key":"e_1_3_3_136_2","first-page":"8230","volume-title":"Proceedings of the Conference on Advances in Neural Information Processing Systems","volume":"32","author":"Liu Qi","year":"2019","unstructured":"Qi Liu, Maximilian Nickel, and Douwe Kiela. 2019. Hyperbolic graph neural networks. In Proceedings of the Conference on Advances in Neural Information Processing Systems, Vol. 32. 8230\u20138241."},{"key":"e_1_3_3_137_2","first-page":"7548","volume-title":"Proceedings of the Conference on Advances in Neural Information Processing Systems","volume":"33","author":"Zhu Shichao","year":"2020","unstructured":"Shichao Zhu, Shirui Pan, Chuan Zhou, Jia Wu, Yanan Cao, and Bin Wang. 2020. Graph geometry interaction learning. In Proceedings of the Conference on Advances in Neural Information Processing Systems, Vol. 33. 7548\u20137558."},{"key":"e_1_3_3_138_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.12.150"},{"key":"e_1_3_3_139_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Borde Haitz S\u00e1ez de Oc\u00e1riz","year":"2022","unstructured":"Haitz S\u00e1ez de Oc\u00e1riz Borde, Anees Kazi, Federico Barbero, and Pietro Lio. 2022. Latent graph inference using product manifolds. In Proceedings of the International Conference on Learning Representations."},{"key":"e_1_3_3_140_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3170249"},{"key":"e_1_3_3_141_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-59713-9_62"},{"key":"e_1_3_3_142_2","article-title":"FMGNN: Fused manifold graph neural network","volume":"2304","author":"Deng Cheng","year":"2023","unstructured":"Cheng Deng, Fan Xu, Jiaxing Ding, Luoyi Fu, Weinan Zhang, and Xinbing Wang. 2023. FMGNN: Fused manifold graph neural network. arXiv abs\/2304.01081 (2023).","journal-title":"arXiv"},{"key":"e_1_3_3_143_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2019.05.009"},{"key":"e_1_3_3_144_2","article-title":"Deep manifold learning for dynamic MR imaging","volume":"2104","author":"Ke Ziwen","year":"2021","unstructured":"Ziwen Ke, Zhuoxu Cui, Wenqi Huang, Jing Cheng, Seng Jia, Haifeng Wang, Xin Liu, Hairong Zheng, Leslie Ying, Yanjie Zhu et\u00a0al. 2021. Deep manifold learning for dynamic MR imaging. arXiv abs\/2104.01102 (2021).","journal-title":"arXiv"},{"key":"e_1_3_3_145_2","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.27706"},{"key":"e_1_3_3_146_2","first-page":"12426","volume-title":"Proceedings of the Conference on Advances in Neural Information Processing Systems","volume":"33","author":"Borovitskiy Viacheslav","year":"2020","unstructured":"Viacheslav Borovitskiy, Alexander Terenin, Peter Mostowsky, and Marc Deisenroth. 2020. Mat\u00e9rn Gaussian processes on Riemannian manifolds. In Proceedings of the Conference on Advances in Neural Information Processing Systems, Vol. 33. 12426\u201312437."},{"key":"e_1_3_3_147_2","first-page":"794","volume-title":"Proceedings of the Conference on Robot Learning","author":"Jaquier No\u00e9mie","year":"2022","unstructured":"No\u00e9mie Jaquier, Viacheslav Borovitskiy, Andrei Smolensky, Alexander Terenin, Tamim Asfour, and Leonel Rozo. 2022. Geometry-aware Bayesian optimization in robotics using Riemannian Mat\u00e9rn kernels. In Proceedings of the Conference on Robot Learning. 794\u2013805."},{"key":"e_1_3_3_148_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2018.8451626"},{"key":"e_1_3_3_149_2","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781107297296"},{"key":"e_1_3_3_150_2","article-title":"A survey on optimal transport for machine learning: Theory and applications","author":"Torres Luis Caicedo","year":"2021","unstructured":"Luis Caicedo Torres, Luiz Manella Pereira, and M. Hadi Amini. 2021. A survey on optimal transport for machine learning: Theory and applications. arXiv preprint arXiv:2106.01963 (2021).","journal-title":"arXiv preprint arXiv:2106.01963"},{"key":"e_1_3_3_151_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-022-10342-x"},{"key":"e_1_3_3_152_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-020-05931-2"},{"key":"e_1_3_3_153_2","first-page":"1505","volume-title":"Proceedings of the International Conference on Artificial Intelligence and Statistics","author":"Abid Brahim Khalil","year":"2018","unstructured":"Brahim Khalil Abid and Robert Gower. 2018. Stochastic algorithms for entropy-regularized optimal transport problems. In Proceedings of the International Conference on Artificial Intelligence and Statistics. 1505\u20131512."},{"issue":"15","key":"e_1_3_3_154_2","first-page":"1","article-title":"Regularized optimal transport and the rot mover\u2019s distance","volume":"19","author":"Dessein Arnaud","year":"2018","unstructured":"Arnaud Dessein, Nicolas Papadakis, and Jean-Luc Rouas. 2018. Regularized optimal transport and the rot mover\u2019s distance. J. Mach. Learn. Res. 19, 15 (2018), 1\u201353.","journal-title":"J. Mach. Learn. Res."},{"key":"e_1_3_3_155_2","article-title":"Manifold optimization for non-linear optimal transport problems","author":"Mishra Bamdev","year":"2021","unstructured":"Bamdev Mishra, N. T. V. Satyadev, Hiroyuki Kasai, and Pratik Jawanpuria. 2021. Manifold optimization for non-linear optimal transport problems. arXiv preprint arXiv:2103.00902 (2021).","journal-title":"arXiv preprint arXiv:2103.00902"},{"key":"e_1_3_3_156_2","first-page":"9900","article-title":"Continual learning in low-rank orthogonal subspaces","volume":"33","author":"Chaudhry Arslan","year":"2020","unstructured":"Arslan Chaudhry, Naeemullah Khan, Puneet Dokania, and Philip Torr. 2020. Continual learning in low-rank orthogonal subspaces. Proc. Advan. Neural Inf. Process. Syst. 33 (2020), 9900\u20139911.","journal-title":"Proc. Advan. Neural Inf. Process. Syst."},{"key":"e_1_3_3_157_2","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-019-0080-x"},{"key":"e_1_3_3_158_2","doi-asserted-by":"publisher","DOI":"10.5555\/2627435.2638581"},{"key":"e_1_3_3_159_2","first-page":"1","article-title":"Pymanopt: A Python toolbox for optimization on manifolds using automatic differentiation","volume":"17","author":"Koep Niklas","year":"2016","unstructured":"Niklas Koep and Sebastian Weichwald. 2016. Pymanopt: A Python toolbox for optimization on manifolds using automatic differentiation. J. Mach. Learn. Res. 17 (2016), 1\u20135.","journal-title":"J. Mach. Learn. Res."},{"key":"e_1_3_3_160_2","doi-asserted-by":"publisher","DOI":"10.1145\/3618296"},{"key":"e_1_3_3_161_2","doi-asserted-by":"publisher","DOI":"10.18637\/jss.v093.i01"},{"key":"e_1_3_3_162_2","volume-title":"McTorch, a Manifold Optimization Library for Deep Learning","author":"Meghwanshi Mayank","year":"2018","unstructured":"Mayank Meghwanshi, Pratik Jawanpuria, Anoop Kunchukuttan, Hiroyuki Kasai, and Bamdev Mishra. 2018. McTorch, a Manifold Optimization Library for Deep Learning. Technical Report. arXiv."},{"key":"e_1_3_3_163_2","article-title":"Geoopt: Riemannian optimization in PyTorch","volume":"2005","author":"Kochurov Max","year":"2020","unstructured":"Max Kochurov, Rasul Karimov, and Sergei Kozlukov. 2020. Geoopt: Riemannian optimization in PyTorch. arXiv abs\/2005.02819 (2020).","journal-title":"arXiv"},{"key":"e_1_3_3_164_2","article-title":"TensorFlow RiemOpt: A library for optimization on Riemannian manifolds","volume":"2105","author":"Smirnov Oleg","year":"2021","unstructured":"Oleg Smirnov. 2021. TensorFlow RiemOpt: A library for optimization on Riemannian manifolds. arXiv abs\/2105.13921 (2021).","journal-title":"arXiv"},{"key":"e_1_3_3_165_2","article-title":"Rieoptax: Riemannian optimization in JAX","volume":"2210","author":"Utpala Saiteja","year":"2022","unstructured":"Saiteja Utpala, Andi Han, Pratik Jawanpuria, and Bamdev Mishra. 2022. Rieoptax: Riemannian optimization in JAX. arXiv abs\/2210.04840 (2022).","journal-title":"arXiv"},{"key":"e_1_3_3_166_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-67675-3_15"},{"key":"e_1_3_3_167_2","article-title":"CDOpt: A Python package for a class of Riemannian optimization","volume":"2212","author":"Xiao Nachuan","year":"2022","unstructured":"Nachuan Xiao, Xiaoyin Hu, Xin Liu, and Kim-Chuan Toh. 2022. CDOpt: A Python package for a class of Riemannian optimization. arXiv abs\/2212.02698 (2022).","journal-title":"arXiv"},{"issue":"223","key":"e_1_3_3_168_2","first-page":"1","article-title":"Geomstats: A Python package for Riemannian geometry in machine learning","volume":"21","author":"Miolane Nina","year":"2020","unstructured":"Nina Miolane, Nicolas Guigui, Alice Le Brigant, Johan Mathe, Benjamin Hou, Yann Thanwerdas, Stefan Heyder, Olivier Peltre, Niklas Koep, Hadi Zaatiti et\u00a0al. 2020. Geomstats: A Python package for Riemannian geometry in machine learning. J. Mach. Learn. Res. 21, 223 (2020), 1\u20139.","journal-title":"J. Mach. Learn. Res."},{"key":"e_1_3_3_169_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.amc.2019.03.044"},{"key":"e_1_3_3_170_2","volume-title":"Documentation Mocap Database HDM05","author":"M\u00fcller M.","year":"2007","unstructured":"M. M\u00fcller, T. R\u00f6der, M. Clausen, B. Eberhardt, B. Kr\u00fcger, and A. Weber. 2007. Documentation Mocap Database HDM05. Technical Report CG-2007-2. Universit\u00e4t Bonn."},{"key":"e_1_3_3_171_2","doi-asserted-by":"publisher","DOI":"10.1145\/2663204.2666275"},{"key":"e_1_3_3_172_2","doi-asserted-by":"publisher","DOI":"10.5555\/1126250.1126340"},{"key":"e_1_3_3_173_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-89991-4_6"},{"key":"e_1_3_3_174_2","doi-asserted-by":"publisher","DOI":"10.1109\/BTAS.2013.6712704"},{"key":"e_1_3_3_175_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.16"},{"key":"e_1_3_3_176_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2007.4408872"},{"key":"e_1_3_3_177_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"e_1_3_3_178_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0748-y"},{"key":"e_1_3_3_179_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"e_1_3_3_180_2","doi-asserted-by":"publisher","unstructured":"Sepp Hochreiter and J\u00fcrgen Schmidhuber. 1997. Long short-term memory. Neural Computation 9 8 (1997) 1735\u20131780. DOI:10.1162\/neco.1997.9.8.1735","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_3_3_181_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.226"},{"key":"e_1_3_3_182_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.1037"},{"key":"e_1_3_3_183_2","first-page":"601","volume-title":"Proceedings of the Conference on Advances in Neural Information Processing Systems","author":"Hamm Jihun","year":"2009","unstructured":"Jihun Hamm and Daniel D. Lee. 2009. Extended Grassmann kernels for subspace-based learning. In Proceedings of the Conference on Advances in Neural Information Processing Systems. 601\u2013608."},{"key":"e_1_3_3_184_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298609"},{"key":"e_1_3_3_185_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.339"},{"issue":"6","key":"e_1_3_3_186_2","first-page":"1031","article-title":"Optimal feature selection for 3D facial expression recognition using coarse-to-fine classification","volume":"18","author":"Soyel Hamit","year":"2010","unstructured":"Hamit Soyel and Hasan Demirel. 2010. Optimal feature selection for 3D facial expression recognition using coarse-to-fine classification. Turk. J. Electric. Eng. Comput. Sci. 18, 6 (2010), 1031\u20131040.","journal-title":"Turk. J. Electric. Eng. Comput. Sci."},{"key":"e_1_3_3_187_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2010.1002"},{"key":"e_1_3_3_188_2","first-page":"441","volume-title":"Information Science and Applications","author":"Huynh Xuan-Phung","year":"2016","unstructured":"Xuan-Phung Huynh, Tien-Duc Tran, and Yong-Guk Kim. 2016. Convolutional neural network models for facial expression recognition using BU-3DFE database. In Information Science and Applications. Springer, 441\u2013450."},{"key":"e_1_3_3_189_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2014.10.042"},{"key":"e_1_3_3_190_2","doi-asserted-by":"publisher","DOI":"10.1145\/3432867.3432890"},{"key":"e_1_3_3_191_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-007-6738-6_124"},{"key":"e_1_3_3_192_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICIG.2013.112"},{"key":"e_1_3_3_193_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2011.6116669"},{"key":"e_1_3_3_194_2","doi-asserted-by":"publisher","DOI":"10.5244\/C.29.41"},{"key":"e_1_3_3_195_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.68"},{"key":"e_1_3_3_196_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995674"},{"key":"e_1_3_3_197_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33765-9_26"},{"key":"e_1_3_3_198_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2014.2307532"},{"key":"e_1_3_3_199_2","first-page":"630","volume-title":"Proceedings of the IEEE International Conference on Computer Vision","author":"Wu Jianxin","year":"2009","unstructured":"Jianxin Wu and James M. Rehg. 2009. Beyond the Euclidean distance: Creating effective visual codebooks using the histogram intersection kernel. In Proceedings of the IEEE International Conference on Computer Vision. 630\u2013637."},{"key":"e_1_3_3_200_2","first-page":"647","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Donahue Jeff","year":"2014","unstructured":"Jeff Donahue, Yangqing Jia, Oriol Vinyals, Judy Hoffman, Ning Zhang, Eric Tzeng, and Trevor Darrell. 2014. DeCAF: A deep convolutional activation feature for generic visual recognition. In Proceedings of the International Conference on Machine Learning. 647\u2013655."},{"key":"e_1_3_3_201_2","article-title":"Federated learning on Riemannian manifolds","author":"Li Jiaxiang","year":"2022","unstructured":"Jiaxiang Li and Shiqian Ma. 2022. Federated learning on Riemannian manifolds. arXiv preprint arXiv:2206.05668 (2022).","journal-title":"arXiv preprint arXiv:2206.05668"},{"key":"e_1_3_3_202_2","doi-asserted-by":"publisher","DOI":"10.5555\/3455716.3455856"},{"key":"e_1_3_3_203_2","article-title":"WanJuan: A comprehensive multimodal dataset for advancing English and Chinese large models","volume":"2308","author":"He Conghui","year":"2023","unstructured":"Conghui He, Zhenjiang Jin, Chao Xu, Jiantao Qiu, Bin Wang, Wei Li, Hang Yan, JiaQi Wang, and Dahua Lin. 2023. WanJuan: A comprehensive multimodal dataset for advancing English and Chinese large models. arXiv abs\/2308.10755 (2023).","journal-title":"arXiv"},{"key":"e_1_3_3_204_2","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913491297"}],"container-title":["ACM Computing Surveys"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3708498","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3708498","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:09:54Z","timestamp":1750295394000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3708498"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,24]]},"references-count":203,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2025,5,31]]}},"alternative-id":["10.1145\/3708498"],"URL":"https:\/\/doi.org\/10.1145\/3708498","relation":{},"ISSN":["0360-0300","1557-7341"],"issn-type":[{"value":"0360-0300","type":"print"},{"value":"1557-7341","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1,24]]},"assertion":[{"value":"2022-10-22","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-11-18","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-01-24","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}