{"list":"other","total":151,"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":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"1810.00826","title":"How Powerful are Graph Neural Networks?","created":"2018-10-01","cited_by_count":4393},{"id":"1312.6114","title":"Auto-Encoding Variational Bayes","created":"2013-12-20","cited_by_count":4053},{"id":"1612.01474","title":"Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles","created":"2016-12-05","cited_by_count":3926},{"id":"1806.07366","title":"Neural Ordinary Differential Equations","created":"2018-06-19","cited_by_count":3779},{"id":"1411.7766","title":"Deep Learning Face Attributes in the Wild","created":"2014-11-28","cited_by_count":3693},{"id":"2004.05150","title":"Longformer: The Long-Document Transformer","created":"2020-04-10","cited_by_count":3413},{"id":"1703.05175","title":"Prototypical Networks for Few-shot Learning","created":"2017-03-15","cited_by_count":3015},{"id":"1512.03012","title":"ShapeNet: An Information-Rich 3D Model Repository","created":"2015-12-09","cited_by_count":2897},{"id":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"id":"1611.07725","title":"iCaRL: Incremental Classifier and Representation Learning","created":"2016-11-23","cited_by_count":2333},{"id":"1709.07871","title":"FiLM: Visual Reasoning with a General Conditioning Layer","created":"2017-09-22","cited_by_count":2333},{"id":"1606.04080","title":"Matching Networks for One Shot Learning","created":"2016-06-13","cited_by_count":2255},{"id":"1801.07829","title":"Dynamic Graph CNN for Learning on Point Clouds","created":"2018-01-24","cited_by_count":2223},{"id":"1403.6652","title":"DeepWalk: Online Learning of Social Representations","created":"2014-03-26","cited_by_count":1547},{"id":"1703.06114","title":"Deep Sets","created":"2017-03-10","cited_by_count":1421},{"id":"1611.07308","title":"Variational Graph Auto-Encoders","created":"2016-11-21","cited_by_count":1382},{"id":"1811.04551","title":"Learning Latent Dynamics for Planning from Pixels","created":"2018-11-12","cited_by_count":1264},{"id":"1709.04875","title":"Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting","created":"2017-09-14","cited_by_count":1136},{"id":"1606.05328","title":"Conditional Image Generation with PixelCNN Decoders","created":"2016-06-16","cited_by_count":862},{"id":"1906.00121","title":"Graph WaveNet for Deep Spatial-Temporal Graph Modeling","created":"2019-05-31","cited_by_count":829},{"id":"2107.07511","title":"A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantification","created":"2021-07-15","cited_by_count":792},{"id":"1801.10112","title":"Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence","created":"2018-01-30","cited_by_count":742},{"id":"1906.01563","title":"Hamiltonian Neural Networks","created":"2019-06-04","cited_by_count":712},{"id":"1511.06349","title":"Generating Sentences from a Continuous Space","created":"2015-11-19","cited_by_count":612},{"id":"1506.02557","title":"Variational Dropout and the Local Reparameterization Trick","created":"2015-06-08","cited_by_count":490},{"id":"1911.08251","title":"General $E(2)$-Equivariant Steerable CNNs","created":"2019-11-19","cited_by_count":446},{"id":"1511.02222","title":"Deep Kernel Learning","created":"2015-11-06","cited_by_count":445},{"id":"1807.01613","title":"Conditional Neural Processes","created":"2018-07-04","cited_by_count":426},{"id":"1706.01427","title":"A simple neural network module for relational reasoning","created":"2017-06-05","cited_by_count":346},{"id":"1903.03096","title":"Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examples","created":"2019-03-07","cited_by_count":315},{"id":"1807.01622","title":"Neural Processes","created":"2018-07-04","cited_by_count":311},{"id":"1810.09502","title":"How to train your MAML","created":"2018-10-22","cited_by_count":309},{"id":"1502.05700","title":"Scalable Bayesian Optimization Using Deep Neural Networks","created":"2015-02-19","cited_by_count":284},{"id":"1901.05761","title":"Attentive Neural Processes","created":"2019-01-17","cited_by_count":283},{"id":"1703.09312","title":"Dex-Net 2.0: Deep Learning to Plan Robust Grasps with Synthetic Point Clouds and Analytic Grasp Metrics","created":"2017-03-27","cited_by_count":264},{"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":"1811.02017","title":"A General Theory of Equivariant CNNs on Homogeneous Spaces","created":"2018-11-05","cited_by_count":228},{"id":"1911.12247","title":"Contrastive Learning of Structured World Models","created":"2019-11-27","cited_by_count":209},{"id":"1801.08930","title":"Recasting Gradient-Based Meta-Learning as Hierarchical Bayes","created":"2018-01-26","cited_by_count":180},{"id":"1611.02731","title":"Variational Lossy Autoencoder","created":"2016-11-08","cited_by_count":176},{"id":"2007.11498","title":"CrossTransformers: spatially-aware few-shot transfer","created":"2020-07-22","cited_by_count":174},{"id":"1802.09127","title":"Deep Bayesian Bandits Showdown: An Empirical Comparison of Bayesian Deep Networks for Thompson Sampling","created":"2018-02-26","cited_by_count":169},{"id":"2101.12699","title":"Exploring Deep Neural Networks via Layer-Peeled Model: Minority Collapse in Imbalanced Training","created":"2021-01-29","cited_by_count":166},{"id":"2004.00345","title":"Editable Neural Networks","created":"2020-04-01","cited_by_count":155},{"id":"2103.02242","title":"FFB6D: A Full Flow Bidirectional Fusion Network for 6D Pose Estimation","created":"2021-03-03","cited_by_count":144},{"id":"1910.13556","title":"Convolutional Conditional Neural Processes","created":"2019-10-29","cited_by_count":142},{"id":"1906.07697","title":"Fast and Flexible Multi-Task Classification Using Conditional Neural Adaptive Processes","created":"2019-06-18","cited_by_count":131},{"id":"2207.04179","title":"Transformer Neural Processes: Uncertainty-Aware Meta Learning Via Sequence Modeling","created":"2022-07-09","cited_by_count":127},{"id":"1606.02185","title":"Towards a Neural Statistician","created":"2016-06-07","cited_by_count":121},{"id":"2007.12036","title":"Implicit Latent Variable Model for Scene-Consistent Motion Forecasting","created":"2020-07-23","cited_by_count":116},{"id":"2103.05180","title":"An Introduction to Deep Generative Modeling","created":"2021-03-09","cited_by_count":104},{"id":"1811.01900","title":"Janossy Pooling: Learning Deep Permutation-Invariant Functions for Variable-Size Inputs","created":"2018-11-05","cited_by_count":98},{"id":"2002.08599","title":"On Learning Sets of Symmetric Elements","created":"2020-02-20","cited_by_count":98},{"id":"1901.09006","title":"On the Limitations of Representing Functions on Sets","created":"2019-01-25","cited_by_count":90},{"id":"1809.11142","title":"EDDI: Efficient Dynamic Discovery of High-Value Information with Partial VAE","created":"2018-09-28","cited_by_count":87},{"id":"1905.06214","title":"GMNN: Graph Markov Neural Networks","created":"2019-05-15","cited_by_count":82},{"id":"2111.05040","title":"A survey on high-dimensional Gaussian process modeling with application to Bayesian optimization","created":"2021-11-09","cited_by_count":77},{"id":"2007.01332","title":"Meta-Learning Stationary Stochastic Process Prediction with Convolutional Neural Processes","created":"2020-07-02","cited_by_count":76},{"id":"2008.10546","title":"SDE-Net: Equipping Deep Neural Networks with Uncertainty Estimates","created":"2020-08-24","cited_by_count":75},{"id":"1909.01515","title":"Meta Relational Learning for Few-Shot Link Prediction in Knowledge Graphs","created":"2019-09-04","cited_by_count":73},{"id":"1810.11738","title":"Gaussian Process Prior Variational Autoencoders","created":"2018-10-28","cited_by_count":72},{"id":"1511.03198","title":"Sliced Wasserstein Kernels for Probability Distributions","created":"2015-11-10","cited_by_count":65},{"id":"2107.01959","title":"Universal Approximation of Functions on Sets","created":"2021-07-05","cited_by_count":62},{"id":"1504.07027","title":"On Sparse variational methods and the Kullback-Leibler divergence between stochastic processes","created":"2015-04-27","cited_by_count":57},{"id":"2103.12413","title":"Neural ODE Processes","created":"2021-03-23","cited_by_count":57},{"id":"1906.10264","title":"Sequential Neural Processes","created":"2019-06-24","cited_by_count":55},{"id":"2010.10604","title":"Bayesian Attention Modules","created":"2020-10-20","cited_by_count":51},{"id":"1807.08912","title":"Meta-Learning Priors for Efficient Online Bayesian Regression","created":"2018-07-24","cited_by_count":48},{"id":"1906.08324","title":"The Functional Neural Process","created":"2019-06-19","cited_by_count":43},{"id":"1806.02390","title":"Variational Implicit Processes","created":"2018-06-06","cited_by_count":41},{"id":"2008.02956","title":"Bootstrapping Neural Processes","created":"2020-08-07","cited_by_count":40},{"id":"1905.08737","title":"On the marginal likelihood and cross-validation","created":"2019-05-21","cited_by_count":37},{"id":"1912.02738","title":"MetaFun: Meta-Learning with Iterative Functional Updates","created":"2019-12-05","cited_by_count":34},{"id":"2005.09234","title":"Anomalous sound detection based on interpolation deep neural network","created":"2020-05-19","cited_by_count":34},{"id":"2101.03606","title":"The Gaussian Neural Process","created":"2021-01-10","cited_by_count":34},{"id":"2008.09469","title":"Doubly Stochastic Variational Inference for Neural Processes with Hierarchical Latent Variables","created":"2020-08-21","cited_by_count":33},{"id":"1806.05490","title":"Inference in Deep Gaussian Processes using Stochastic Gradient Hamiltonian Monte Carlo","created":"2018-06-14","cited_by_count":32},{"id":"2103.06137","title":"Task-adaptive Neural Process for User Cold-Start Recommendation","created":"2021-02-26","cited_by_count":32},{"id":"2011.12916","title":"Equivariant Learning of Stochastic Fields: Gaussian Processes and Steerable Conditional Neural Processes","created":"2020-11-25","cited_by_count":29},{"id":"2101.07950","title":"Convolutional conditional neural processes for local climate downscaling","created":"2021-01-20","cited_by_count":29},{"id":"1711.02653","title":"Neural system identification for large populations separating \"what\" and \"where\"","created":"2017-11-07","cited_by_count":28},{"id":"2001.01349","title":"Learning and Memorizing Representative Prototypes for 3D Point Cloud Semantic and Instance Segmentation","created":"2020-01-06","cited_by_count":26},{"id":"2008.09624","title":"Optimization of Graph Neural Networks with Natural Gradient Descent","created":"2020-08-21","cited_by_count":26},{"id":"2203.08775","title":"Practical Conditional Neural Processes Via Tractable Dependent Predictions","created":"2022-03-16","cited_by_count":25},{"id":"2207.01066","title":"NP-Match: When Neural Processes meet Semi-Supervised Learning","created":"2022-07-03","cited_by_count":25},{"id":"2007.04813","title":"Graph-Based Continual Learning","created":"2020-07-09","cited_by_count":24},{"id":"1807.08919","title":"The Variational Homoencoder: Learning to learn high capacity generative models from few examples","created":"2018-07-24","cited_by_count":23},{"id":"1907.11864","title":"Uncertainty in Model-Agnostic Meta-Learning using Variational Inference","created":"2019-07-27","cited_by_count":23},{"id":"2203.13167","title":"Towards Exemplar-Free Continual Learning in Vision Transformers: an Account of Attention, Functional and Weight Regularization","created":"2022-03-24","cited_by_count":23},{"id":"2001.10362","title":"The Final Frontier: Deep Learning in Space","created":"2020-01-27","cited_by_count":21},{"id":"2104.09396","title":"Continual Learning in Sensor-based Human Activity Recognition: an Empirical Benchmark Analysis","created":"2021-04-19","cited_by_count":21}],"next_cursor":"100"}