{"list":"other","total":53,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"1605.07146","title":"Wide Residual Networks","created":"2016-05-23","cited_by_count":3070},{"id":"1901.05103","title":"DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation","created":"2019-01-16","cited_by_count":2689},{"id":"2006.09661","title":"Implicit Neural Representations with Periodic Activation Functions","created":"2020-06-17","cited_by_count":2238},{"id":"1611.01578","title":"Neural Architecture Search with Reinforcement Learning","created":"2016-11-05","cited_by_count":1499},{"id":"1703.06211","title":"Deformable Convolutional Networks","created":"2017-03-17","cited_by_count":1488},{"id":"1803.01271","title":"An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling","created":"2018-03-04","cited_by_count":1476},{"id":"2106.12423","title":"Alias-Free Generative Adversarial Networks","created":"2021-06-23","cited_by_count":1184},{"id":"1804.03209","title":"Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition","created":"2018-04-09","cited_by_count":752},{"id":"1802.08219","title":"Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point clouds","created":"2018-02-22","cited_by_count":746},{"id":"1312.4400","title":"Network In Network","created":"2013-12-16","cited_by_count":605},{"id":"2008.07669","title":"HiPPO: Recurrent Memory with Optimal Polynomial Projections","created":"2020-08-17","cited_by_count":605},{"id":"1706.08566","title":"SchNet: A continuous-filter convolutional neural network for modeling quantum interactions","created":"2017-06-26","cited_by_count":571},{"id":"2005.08926","title":"Neural Controlled Differential Equations for Irregular Time Series","created":"2020-05-18","cited_by_count":506},{"id":"1904.11486","title":"Making Convolutional Networks Shift-Invariant Again","created":"2019-04-25","cited_by_count":391},{"id":"1707.08819","title":"A Downsampled Variant of ImageNet as an Alternative to the CIFAR datasets","created":"2017-07-27","cited_by_count":377},{"id":"1907.03670","title":"From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Network","created":"2019-07-08","cited_by_count":368},{"id":"1811.00075","title":"The UEA multivariate time series classification archive, 2018","created":"2018-10-31","cited_by_count":338},{"id":"1704.02901","title":"Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs","created":"2017-04-10","cited_by_count":310},{"id":"1911.03584","title":"On the Relationship between Self-Attention and Convolutional Layers","created":"2019-11-08","cited_by_count":300},{"id":"2002.12880","title":"Generalizing Convolutional Neural Networks for Equivariance to Lie Groups on Arbitrary Continuous Data","created":"2020-02-25","cited_by_count":248},{"id":"1906.06423","title":"Fixing the train-test resolution discrepancy","created":"2019-06-14","cited_by_count":209},{"id":"1703.02719","title":"Large Kernel Matters -- Improve Semantic Segmentation by Global Convolutional Network","created":"2017-03-08","cited_by_count":208},{"id":"2101.06742","title":"Deep Parametric Continuous Convolutional Neural Networks","created":"2021-01-17","cited_by_count":161},{"id":"1803.04831","title":"Independently Recurrent Neural Network (IndRNN): Building A Longer and Deeper RNN","created":"2018-03-13","cited_by_count":143},{"id":"2003.07064","title":"On Translation Invariance in CNNs: Convolutional Layers can Exploit Absolute Spatial Location","created":"2020-03-16","cited_by_count":142},{"id":"1504.00941","title":"A Simple Way to Initialize Recurrent Networks of Rectified Linear Units","created":"2015-04-03","cited_by_count":130},{"id":"2102.02611","title":"CKConv: Continuous Kernel Convolution For Sequential Data","created":"2021-02-04","cited_by_count":120},{"id":"1902.09689","title":"AntisymmetricRNN: A Dynamical System View on Recurrent Neural Networks","created":"2019-02-26","cited_by_count":112},{"id":"2006.12070","title":"Lipschitz Recurrent Neural Networks","created":"2020-06-22","cited_by_count":89},{"id":"1710.02224","title":"Dilated Recurrent Neural Networks","created":"2017-10-05","cited_by_count":83},{"id":"2010.00951","title":"Coupled Oscillatory Recurrent Neural Network (coRNN): An accurate and (gradient) stable architecture for learning long time dependencies","created":"2020-10-02","cited_by_count":82},{"id":"1803.00144","title":"Learning Longer-term Dependencies in RNNs with Auxiliary Losses","created":"2018-03-01","cited_by_count":58},{"id":"2103.05487","title":"UnICORNN: A recurrent model for learning very long time dependencies","created":"2021-03-09","cited_by_count":56},{"id":"1810.06682","title":"Trellis Networks for Sequence Modeling","created":"2018-10-15","cited_by_count":52},{"id":"2101.12491","title":"Efficient-CapsNet: Capsule Network with Self-Attention Routing","created":"2021-01-29","cited_by_count":41},{"id":"2007.03347","title":"SpinalNet: Deep Neural Network with Gradual Input","created":"2020-07-07","cited_by_count":40},{"id":"1605.02971","title":"Structured Receptive Fields in CNNs","created":"2016-05-10","cited_by_count":32},{"id":"2106.03412","title":"Resolution learning in deep convolutional networks using scale-space theory","created":"2021-06-07","cited_by_count":26},{"id":"2011.14759","title":"Scale-covariant and scale-invariant Gaussian derivative networks","created":"2020-11-30","cited_by_count":25},{"id":"2108.03489","title":"Impact of Aliasing on Generalization in Deep Convolutional Networks","created":"2021-08-07","cited_by_count":25},{"id":"2102.11417","title":"Parallelizing Legendre Memory Unit Training","created":"2021-02-22","cited_by_count":23},{"id":"1904.11487","title":"Blurring the Line Between Structure and Learning to Optimize and Adapt Receptive Fields","created":"2019-04-25","cited_by_count":11},{"id":"1902.07474","title":"Spatially-Adaptive Filter Units for Compact and Efficient Deep Neural Networks","created":"2019-02-20","cited_by_count":7},{"id":"1707.08630","title":"Optimizing Filter Size in Convolutional Neural Networks for Facial Action Unit Recognition","created":"2017-07-26","cited_by_count":6},{"id":"2003.05569","title":"Extended Batch Normalization","created":"2020-03-12","cited_by_count":5}],"next_cursor":null}