{"list":"other","total":58,"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":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1812.04948","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","created":"2018-12-12","cited_by_count":6013},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1312.6114","title":"Auto-Encoding Variational Bayes","created":"2013-12-20","cited_by_count":4053},{"id":"1912.04958","title":"Analyzing and Improving the Image Quality of StyleGAN","created":"2019-12-03","cited_by_count":3588},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"1809.11096","title":"Large Scale GAN Training for High Fidelity Natural Image Synthesis","created":"2018-09-28","cited_by_count":2626},{"id":"1605.08803","title":"Density estimation using Real NVP","created":"2016-05-27","cited_by_count":2042},{"id":"2006.16236","title":"Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention","created":"2020-06-29","cited_by_count":2022},{"id":"1609.03499","title":"WaveNet: A Generative Model for Raw Audio","created":"2016-09-12","cited_by_count":1722},{"id":"1904.10509","title":"Generating Long Sequences with Sparse Transformers","created":"2019-04-23","cited_by_count":1546},{"id":"1807.03039","title":"Glow: Generative Flow with Invertible 1x1 Convolutions","created":"2018-07-09","cited_by_count":1545},{"id":"1803.02155","title":"Self-Attention with Relative Position Representations","created":"2018-03-06","cited_by_count":1120},{"id":"1912.01865","title":"StarGAN v2: Diverse Image Synthesis for Multiple Domains","created":"2019-12-04","cited_by_count":1098},{"id":"1711.09020","title":"StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation","created":"2017-11-24","cited_by_count":1039},{"id":"1802.05751","title":"Image Transformer","created":"2018-02-15","cited_by_count":772},{"id":"2005.00341","title":"Jukebox: A Generative Model for Music","created":"2020-04-30","cited_by_count":542},{"id":"1611.08974","title":"Semantic Scene Completion from a Single Depth Image","created":"2016-11-28","cited_by_count":472},{"id":"1701.05517","title":"PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modifications","created":"2017-01-19","cited_by_count":417},{"id":"2011.09127","title":"3D-FRONT: 3D Furnished Rooms with layOuts and semaNTics","created":"2020-11-18","cited_by_count":380},{"id":"2009.09633","title":"3D-FUTURE: 3D Furniture shape with TextURE","created":"2020-09-21","cited_by_count":311},{"id":"1606.02147","title":"ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation","created":"2016-06-07","cited_by_count":291},{"id":"1703.01925","title":"Grammar Variational Autoencoder","created":"2017-03-06","cited_by_count":285},{"id":"2002.10880","title":"PolyGen: An Autoregressive Generative Model of 3D Meshes","created":"2020-02-23","cited_by_count":269},{"id":"1904.04745","title":"Cross-Modal Self-Attention Network for Referring Image Segmentation","created":"2019-04-09","cited_by_count":263},{"id":"1806.00187","title":"Scaling Neural Machine Translation","created":"2018-06-01","cited_by_count":204},{"id":"2101.02692","title":"Where2Act: From Pixels to Actions for Articulated 3D Objects","created":"2021-01-07","cited_by_count":182},{"id":"1612.00404","title":"Learning Shape Abstractions by Assembling Volumetric Primitives","created":"2016-12-01","cited_by_count":181},{"id":"2012.09793","title":"SceneFormer: Indoor Scene Generation with Transformers","created":"2020-12-17","cited_by_count":158},{"id":"1810.00825","title":"Set Transformer: A Framework for Attention-based Permutation-Invariant Neural Networks","created":"2018-10-01","cited_by_count":132},{"id":"1904.11621","title":"Meta-Sim: Learning to Generate Synthetic Datasets","created":"2019-04-25","cited_by_count":128},{"id":"1904.09970","title":"Superquadrics Revisited: Learning 3D Shape Parsing beyond Cuboids","created":"2019-04-22","cited_by_count":124},{"id":"1907.10719","title":"LayoutVAE: Stochastic Scene Layout Generation From a Label Set","created":"2019-07-24","cited_by_count":119},{"id":"1811.12463","title":"Fast and Flexible Indoor Scene Synthesis via Deep Convolutional Generative Models","created":"2018-11-29","cited_by_count":106},{"id":"2103.10429","title":"Neural Parts: Learning Expressive 3D Shape Abstractions with Invertible Neural Networks","created":"2021-03-18","cited_by_count":103},{"id":"1810.10093","title":"Structured Domain Randomization: Bridging the Reality Gap by Context-Aware Synthetic Data","created":"2018-10-23","cited_by_count":94},{"id":"2103.13915","title":"An Image is Worth 16x16 Words, What is a Video Worth?","created":"2021-03-25","cited_by_count":87},{"id":"1808.08473","title":"Human-centric Indoor Scene Synthesis Using Stochastic Grammar","created":"2018-08-25","cited_by_count":74},{"id":"2004.01176","title":"Learning Unsupervised Hierarchical Part Decomposition of 3D Objects from a Single RGB Image","created":"2020-04-02","cited_by_count":72},{"id":"1808.02084","title":"Deep Generative Modeling for Scene Synthesis via Hybrid Representations","created":"2018-08-06","cited_by_count":63},{"id":"2008.09092","title":"Meta-Sim2: Unsupervised Learning of Scene Structure for Synthetic Data Generation","created":"2020-08-20","cited_by_count":58},{"id":"1907.11308","title":"SceneGraphNet: Neural Message Passing for 3D Indoor Scene Augmentation","created":"2019-07-25","cited_by_count":55},{"id":"2008.05927","title":"End-to-end Contextual Perception and Prediction with Interaction Transformer","created":"2020-08-13","cited_by_count":54},{"id":"2007.11744","title":"End-to-End Optimization of Scene Layout","created":"2020-07-23","cited_by_count":52},{"id":"2104.11222","title":"On Aliased Resizing and Surprising Subtleties in GAN Evaluation","created":"2021-04-22","cited_by_count":51},{"id":"1807.09193","title":"GRAINS: Generative Recursive Autoencoders for INdoor Scenes","created":"2018-07-24","cited_by_count":38},{"id":"2006.16841","title":"Conditional Set Generation with Transformers","created":"2020-06-26","cited_by_count":32},{"id":"2103.15813","title":"PixelTransformer: Sample Conditioned Signal Generation","created":"2021-03-29","cited_by_count":12},{"id":"2009.12395","title":"SceneGen: Generative Contextual Scene Augmentation using Scene Graph Priors","created":"2020-09-25","cited_by_count":11},{"id":"2002.00328","title":"Fast 3D Indoor Scene Synthesis with Discrete and Exact Layout Pattern Extraction","created":"2020-02-02","cited_by_count":7},{"id":"2008.01323","title":"Structural Plan of Indoor Scenes with Personalized Preferences","created":"2020-08-04","cited_by_count":3}],"next_cursor":null}