{"list":"other","total":73,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"2301.00808","title":"ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders","created":"2023-01-02","cited_by_count":712},{"id":"1310.1531","title":"DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition","created":"2013-10-06","cited_by_count":424},{"id":"1511.06464","title":"Unitary Evolution Recurrent Neural Networks","created":"2015-11-20","cited_by_count":294},{"id":"1910.12892","title":"Hyperbolic Graph Neural Networks","created":"2019-10-28","cited_by_count":244},{"id":"1810.00760","title":"Riemannian Adaptive Optimization Methods","created":"2018-10-01","cited_by_count":194},{"id":"1810.01256","title":"Continual Learning of Context-dependent Processing in Neural Networks","created":"2018-09-29","cited_by_count":179},{"id":"1608.04233","title":"A Riemannian Network for SPD Matrix Learning","created":"2016-08-15","cited_by_count":162},{"id":"1901.08428","title":"Cheap Orthogonal Constraints in Neural Networks: A Simple Parametrization of the Orthogonal and Unitary Group","created":"2019-01-24","cited_by_count":134},{"id":"1911.12207","title":"Orthogonal Convolutional Neural Networks","created":"2019-11-27","cited_by_count":123},{"id":"2005.02819","title":"Geoopt: Riemannian Optimization in PyTorch","created":"2020-05-06","cited_by_count":114},{"id":"1308.5200","title":"Manopt, a Matlab toolbox for optimization on manifolds","created":"2013-08-23","cited_by_count":113},{"id":"2010.11635","title":"Continual Learning in Low-rank Orthogonal Subspaces","created":"2020-10-22","cited_by_count":99},{"id":"1603.03236","title":"Pymanopt: A Python Toolbox for Optimization on Manifolds using Automatic Differentiation","created":"2016-03-10","cited_by_count":94},{"id":"1611.00035","title":"Full-Capacity Unitary Recurrent Neural Networks","created":"2016-10-31","cited_by_count":94},{"id":"1709.06079","title":"Orthogonal Weight Normalization: Solution to Optimization over Multiple Dependent Stiefel Manifolds in Deep Neural Networks","created":"2017-09-16","cited_by_count":92},{"id":"2002.04999","title":"Differentiable Graph Module (DGM) for Graph Convolutional Networks","created":"2020-02-11","cited_by_count":86},{"id":"1702.00071","title":"On orthogonality and learning recurrent networks with long term dependencies","created":"2017-01-31","cited_by_count":83},{"id":"2006.10160","title":"Mat\\'ern Gaussian processes on Riemannian manifolds","created":"2020-06-17","cited_by_count":82},{"id":"1812.03794","title":"Unsupervised Deep Learning for Structured Shape Matching","created":"2018-12-10","cited_by_count":81},{"id":"1805.08308","title":"geomstats: a Python Package for Riemannian Geometry in Machine Learning","created":"2018-05-21","cited_by_count":71},{"id":"1312.6026","title":"How to Construct Deep Recurrent Neural Networks","created":"2013-12-20","cited_by_count":64},{"id":"1810.09102","title":"Can We Gain More from Orthogonality Regularizations in Training Deep CNNs?","created":"2018-10-22","cited_by_count":62},{"id":"1611.05742","title":"Building Deep Networks on Grassmann Manifolds","created":"2016-11-17","cited_by_count":58},{"id":"1612.00188","title":"Efficient Orthogonal Parametrisation of Recurrent Neural Networks Using Householder Reflections","created":"2016-12-01","cited_by_count":57},{"id":"2010.12135","title":"Graph Geometry Interaction Learning","created":"2020-10-23","cited_by_count":55},{"id":"1612.05877","title":"Deep Learning on Lie Groups for Skeleton-based Action Recognition","created":"2016-12-18","cited_by_count":42},{"id":"1611.01967","title":"Regularizing CNNs with Locally Constrained Decorrelations","created":"2016-11-07","cited_by_count":41},{"id":"2003.13620","title":"Latent-Graph Learning for Disease Prediction","created":"2020-03-27","cited_by_count":39},{"id":"1705.05502","title":"The power of deeper networks for expressing natural functions","created":"2017-05-16","cited_by_count":35},{"id":"1906.05450","title":"A Brief Introduction to Manifold Optimization","created":"2019-06-13","cited_by_count":35},{"id":"2106.01963","title":"A Survey on Optimal Transport for Machine Learning: Theory and Applications","created":"2021-06-03","cited_by_count":35},{"id":"2106.00286","title":"On Riemannian Optimization over Positive Definite Matrices with the Bures-Wasserstein Geometry","created":"2021-06-01","cited_by_count":32},{"id":"1706.02761","title":"Gated Orthogonal Recurrent Units: On Learning to Forget","created":"2017-06-08","cited_by_count":31},{"id":"1407.5965","title":"Optimization Techniques on Riemannian Manifolds","created":"2014-07-22","cited_by_count":27},{"id":"1610.06447","title":"Regularized Optimal Transport and the Rot Mover's Distance","created":"2016-10-20","cited_by_count":24},{"id":"2001.08876","title":"From Nesterov's Estimate Sequence to Riemannian Acceleration","created":"2020-01-24","cited_by_count":24},{"id":"2111.01460","title":"Geometry-aware Bayesian Optimization in Robotics using Riemannian Mat\\'ern Kernels","created":"2021-11-02","cited_by_count":24},{"id":"2108.04009","title":"Transductive Few-Shot Classification on the Oblique Manifold","created":"2021-08-09","cited_by_count":23},{"id":"2211.16199","title":"Latent Graph Inference using Product Manifolds","created":"2022-11-26","cited_by_count":23},{"id":"1407.1120","title":"From Manifold to Manifold: Geometry-Aware Dimensionality Reduction for SPD Matrices","created":"2014-07-04","cited_by_count":22},{"id":"1808.02229","title":"Grassmannian Learning: Embedding Geometry Awareness in Shallow and Deep Learning","created":"2018-08-07","cited_by_count":19},{"id":"1611.05927","title":"Generalized BackPropagation, \\'{E}tude De Cas: Orthogonality","created":"2016-11-17","cited_by_count":17},{"id":"1810.01811","title":"McTorch, a manifold optimization library for deep learning","created":"2018-10-03","cited_by_count":16},{"id":"2010.06097","title":"Gradient Descent Ascent for Minimax Problems on Riemannian Manifolds","created":"2020-10-13","cited_by_count":16},{"id":"1607.04903","title":"Learning Unitary Operators with Help From u(n)","created":"2016-07-17","cited_by_count":15},{"id":"1610.07008","title":"Optimization on Submanifolds of Convolution Kernels in CNNs","created":"2016-10-22","cited_by_count":15},{"id":"1310.4891","title":"Dictionary Learning and Sparse Coding on Grassmann Manifolds: An Extrinsic Solution","created":"2013-10-18","cited_by_count":13},{"id":"1806.02812","title":"Towards Riemannian Accelerated Gradient Methods","created":"2018-06-07","cited_by_count":12},{"id":"2110.10464","title":"Learning with symmetric positive definite matrices via generalized Bures-Wasserstein geometry","created":"2021-10-20","cited_by_count":10},{"id":"2201.12133","title":"O-ViT: Orthogonal Vision Transformer","created":"2022-01-28","cited_by_count":10},{"id":"1608.04914","title":"Geometry-aware Similarity Learning on SPD Manifolds for Visual Recognition","created":"2016-08-17","cited_by_count":9},{"id":"1705.10732","title":"Deep manifold-to-manifold transforming network for action recognition","created":"2017-05-30","cited_by_count":9},{"id":"1803.01347","title":"Greedy stochastic algorithms for entropy-regularized optimal transport problems","created":"2018-03-04","cited_by_count":9},{"id":"1807.07663","title":"Automatically Designing CNN Architectures for Medical Image Segmentation","created":"2018-07-19","cited_by_count":8},{"id":"2103.00902","title":"Manifold optimization for non-linear optimal transport problems","created":"2021-03-01","cited_by_count":8},{"id":"2104.01102","title":"Deep Manifold Learning for Dynamic MR Imaging","created":"2021-03-09","cited_by_count":8},{"id":"2004.00897","title":"Riemannian Adaptive Optimization Algorithm and Its Application to Natural Language Processing","created":"2020-04-02","cited_by_count":7},{"id":"2201.12933","title":"Riemannian block SPD coupling manifold and its application to optimal transport","created":"2022-01-30","cited_by_count":7},{"id":"1711.01577","title":"Wider and Deeper, Cheaper and Faster: Tensorized LSTMs for Sequence Learning","created":"2017-11-05","cited_by_count":6},{"id":"1712.06467","title":"Multi-modal Face Pose Estimation with Multi-task Manifold Deep Learning","created":"2017-12-18","cited_by_count":6},{"id":"1712.08364","title":"Differential geometry and stochastic dynamics with deep learning numerics","created":"2017-12-22","cited_by_count":4},{"id":"1303.5244","title":"Separable Dictionary Learning","created":"2013-03-21","cited_by_count":3},{"id":"1804.10432","title":"Variational Regularization of Inverse Problems for Manifold-Valued Data","created":"2018-04-27","cited_by_count":2},{"id":"1806.02587","title":"Fault-Tolerant Control of Linear Quantum Stochastic Systems","created":"2018-06-07","cited_by_count":2},{"id":"2205.15068","title":"Embedding Graphs on Grassmann Manifold","created":"2022-05-30","cited_by_count":2},{"id":"2212.02698","title":"CDOpt: A Python Package for a Class of Riemannian Optimization","created":"2022-12-06","cited_by_count":2}],"next_cursor":null}