{"list":"other","total":51,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"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":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"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":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"1906.08237","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","created":"2019-06-19","cited_by_count":2811},{"id":"1603.08155","title":"Perceptual Losses for Real-Time Style Transfer and Super-Resolution","created":"2016-03-27","cited_by_count":2694},{"id":"2006.03654","title":"DeBERTa: Decoding-enhanced BERT with Disentangled Attention","created":"2020-06-05","cited_by_count":2181},{"id":"1703.06868","title":"Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization","created":"2017-03-20","cited_by_count":2010},{"id":"2012.15840","title":"Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers","created":"2020-12-31","cited_by_count":1369},{"id":"1803.02155","title":"Self-Attention with Relative Position Representations","created":"2018-03-06","cited_by_count":1120},{"id":"2002.04745","title":"On Layer Normalization in the Transformer Architecture","created":"2020-02-12","cited_by_count":922},{"id":"2012.00364","title":"Pre-Trained Image Processing Transformer","created":"2020-12-01","cited_by_count":893},{"id":"1804.04732","title":"Multimodal Unsupervised Image-to-Image Translation","created":"2018-04-12","cited_by_count":795},{"id":"2007.15651","title":"Contrastive Learning for Unpaired Image-to-Image Translation","created":"2020-07-30","cited_by_count":639},{"id":"2011.14503","title":"End-to-End Video Instance Segmentation with Transformers","created":"2020-11-30","cited_by_count":443},{"id":"1705.08086","title":"Universal Style Transfer via Feature Transforms","created":"2017-05-23","cited_by_count":354},{"id":"1610.07629","title":"A Learned Representation For Artistic Style","created":"2016-10-24","cited_by_count":341},{"id":"2006.03677","title":"Visual Transformers: Token-based Image Representation and Processing for Computer Vision","created":"2020-06-05","cited_by_count":334},{"id":"2105.07581","title":"Vision Transformers are Robust Learners","created":"2021-05-17","cited_by_count":207},{"id":"1812.02342","title":"Arbitrary Style Transfer with Style-Attentional Networks","created":"2018-12-06","cited_by_count":198},{"id":"1604.04382","title":"Precomputed Real-Time Texture Synthesis with Markovian Generative Adversarial Networks","created":"2016-04-15","cited_by_count":192},{"id":"2001.08248","title":"How Much Position Information Do Convolutional Neural Networks Encode?","created":"2020-01-22","cited_by_count":172},{"id":"2102.07074","title":"TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Up","created":"2021-02-14","cited_by_count":162},{"id":"1701.01036","title":"Demystifying Neural Style Transfer","created":"2017-01-04","cited_by_count":152},{"id":"1802.06474","title":"A Closed-form Solution to Photorealistic Image Stylization","created":"2018-02-19","cited_by_count":133},{"id":"1805.03857","title":"Avatar-Net: Multi-scale Zero-shot Style Transfer by Feature Decoration","created":"2018-05-10","cited_by_count":115},{"id":"2103.16877","title":"ArtFlow: Unbiased Image Style Transfer via Reversible Neural Flows","created":"2021-03-31","cited_by_count":113},{"id":"1703.09210","title":"StyleBank: An Explicit Representation for Neural Image Style Transfer","created":"2017-03-27","cited_by_count":89},{"id":"1905.05621","title":"Style Transformer: Unpaired Text Style Transfer without Disentangled Latent Representation","created":"2019-05-14","cited_by_count":84},{"id":"2009.08003","title":"Arbitrary Video Style Transfer via Multi-Channel Correlation","created":"2020-09-17","cited_by_count":84},{"id":"2005.13219","title":"Arbitrary Style Transfer via Multi-Adaptation Network","created":"2020-05-27","cited_by_count":70},{"id":"1701.08893","title":"Stable and Controllable Neural Texture Synthesis and Style Transfer Using Histogram Losses","created":"2017-01-31","cited_by_count":69},{"id":"2012.05217","title":"Positional Encoding as Spatial Inductive Bias in GANs","created":"2020-12-09","cited_by_count":69},{"id":"2003.08436","title":"Collaborative Distillation for Ultra-Resolution Universal Style Transfer","created":"2020-03-18","cited_by_count":52},{"id":"1901.05127","title":"Attention-aware Multi-stroke Style Transfer","created":"2019-01-16","cited_by_count":47},{"id":"1906.00668","title":"A Closed-form Solution to Universal Style Transfer","created":"2019-06-03","cited_by_count":42},{"id":"1909.08223","title":"Diversified Arbitrary Style Transfer via Deep Feature Perturbation","created":"2019-09-18","cited_by_count":42},{"id":"2104.05376","title":"Drafting and Revision: Laplacian Pyramid Network for Fast High-Quality Artistic Style Transfer","created":"2021-04-12","cited_by_count":41},{"id":"1912.02398","title":"Ultrafast Photorealistic Style Transfer via Neural Architecture Search","created":"2019-12-05","cited_by_count":39},{"id":"1906.02913","title":"Two-Stage Peer-Regularized Feature Recombination for Arbitrary Image Style Transfer","created":"2019-06-07","cited_by_count":36},{"id":"1811.10352","title":"EFANet: Exchangeable Feature Alignment Network for Arbitrary Style Transfer","created":"2018-11-26","cited_by_count":13},{"id":"2006.01431","title":"Distribution Aligned Multimodal and Multi-Domain Image Stylization","created":"2020-06-02","cited_by_count":10},{"id":"2006.09029","title":"Real-time Universal Style Transfer on High-resolution Images via Zero-channel Pruning","created":"2020-06-16","cited_by_count":9}],"next_cursor":null}