{"list":"other","total":80,"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":"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":"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":"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":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"2004.05150","title":"Longformer: The Long-Document Transformer","created":"2020-04-10","cited_by_count":3413},{"id":"2105.15203","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","created":"2021-05-31","cited_by_count":2940},{"id":"1603.08155","title":"Perceptual Losses for Real-Time Style Transfer and Super-Resolution","created":"2016-03-27","cited_by_count":2694},{"id":"1703.06868","title":"Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization","created":"2017-03-20","cited_by_count":2010},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"id":"2012.15840","title":"Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers","created":"2020-12-31","cited_by_count":1369},{"id":"2111.09883","title":"Swin Transformer V2: Scaling Up Capacity and Resolution","created":"2021-11-18","cited_by_count":1228},{"id":"1607.08022","title":"Instance Normalization: The Missing Ingredient for Fast Stylization","created":"2016-07-27","cited_by_count":1198},{"id":"2101.11986","title":"Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet","created":"2021-01-28","cited_by_count":1101},{"id":"2202.04200","title":"MaskGIT: Masked Generative Image Transformer","created":"2022-02-08","cited_by_count":1099},{"id":"2103.15808","title":"CvT: Introducing Convolutions to Vision Transformers","created":"2021-03-29","cited_by_count":947},{"id":"2002.04745","title":"On Layer Normalization in the Transformer Architecture","created":"2020-02-12","cited_by_count":922},{"id":"2104.11227","title":"Multiscale Vision Transformers","created":"2021-04-22","cited_by_count":897},{"id":"1804.04732","title":"Multimodal Unsupervised Image-to-Image Translation","created":"2018-04-12","cited_by_count":795},{"id":"1703.10593","title":"Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks","created":"2017-03-30","cited_by_count":707},{"id":"2103.00112","title":"Transformer in Transformer","created":"2021-02-27","cited_by_count":633},{"id":"2107.00652","title":"CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows","created":"2021-07-01","cited_by_count":527},{"id":"2112.01526","title":"MViTv2: Improved Multiscale Vision Transformers for Classification and Detection","created":"2021-12-02","cited_by_count":519},{"id":"1508.06576","title":"A Neural Algorithm of Artistic Style","created":"2015-08-26","cited_by_count":483},{"id":"2204.01697","title":"MaxViT: Multi-Axis Vision Transformer","created":"2022-04-04","cited_by_count":476},{"id":"2104.01136","title":"LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference","created":"2021-04-02","cited_by_count":475},{"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":"1711.11575","title":"Relation Networks for Object Detection","created":"2017-11-30","cited_by_count":305},{"id":"1701.02096","title":"Improved Texture Networks: Maximizing Quality and Diversity in Feed-forward Stylization and Texture Synthesis","created":"2017-01-09","cited_by_count":215},{"id":"1904.11491","title":"Local Relation Networks for Image Recognition","created":"2019-04-25","cited_by_count":210},{"id":"2002.12804","title":"UniLMv2: Pseudo-Masked Language Models for Unified Language Model Pre-Training","created":"2020-02-28","cited_by_count":204},{"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":"2105.14576","title":"StyTr$^2$: Image Style Transfer with Transformers","created":"2021-05-30","cited_by_count":187},{"id":"2108.03647","title":"AdaAttN: Revisit Attention Mechanism in Arbitrary Neural Style Transfer","created":"2021-08-08","cited_by_count":178},{"id":"2108.01390","title":"Evo-ViT: Slow-Fast Token Evolution for Dynamic Vision Transformer","created":"2021-08-03","cited_by_count":177},{"id":"1603.03417","title":"Texture Networks: Feed-forward Synthesis of Textures and Stylized Images","created":"2016-03-10","cited_by_count":174},{"id":"1601.06733","title":"Long Short-Term Memory-Networks for Machine Reading","created":"2016-01-25","cited_by_count":161},{"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":"2111.11429","title":"Benchmarking Detection Transfer Learning with Vision Transformers","created":"2021-11-22","cited_by_count":131},{"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":"2205.09542","title":"Domain Enhanced Arbitrary Image Style Transfer via Contrastive Learning","created":"2022-05-19","cited_by_count":93},{"id":"1612.04337","title":"Fast Patch-based Style Transfer of Arbitrary Style","created":"2016-12-13","cited_by_count":92},{"id":"1703.09210","title":"StyleBank: An Explicit Representation for Neural Image Style Transfer","created":"2017-03-27","cited_by_count":89},{"id":"2009.08003","title":"Arbitrary Video Style Transfer via Multi-Channel Correlation","created":"2020-09-17","cited_by_count":84},{"id":"2012.09958","title":"Toward Transformer-Based Object Detection","created":"2020-12-17","cited_by_count":84},{"id":"1911.06953","title":"Dynamic Instance Normalization for Arbitrary Style Transfer","created":"2019-11-16","cited_by_count":83},{"id":"1805.04103","title":"Arbitrary Style Transfer with Deep Feature Reshuffle","created":"2018-05-10","cited_by_count":75},{"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":"1703.06953","title":"Multi-style Generative Network for Real-time Transfer","created":"2017-03-20","cited_by_count":61},{"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":"1606.05897","title":"Preserving Color in Neural Artistic Style Transfer","created":"2016-06-19","cited_by_count":20},{"id":"1707.01253","title":"Laplacian-Steered Neural Style Transfer","created":"2017-07-05","cited_by_count":18},{"id":"2203.16015","title":"ITTR: Unpaired Image-to-Image Translation with Transformers","created":"2022-03-30","cited_by_count":15},{"id":"2106.02514","title":"The Image Local Autoregressive Transformer","created":"2021-06-04","cited_by_count":14},{"id":"2202.13562","title":"Name Your Style: An Arbitrary Artist-aware Image Style Transfer","created":"2022-02-28","cited_by_count":14},{"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":"2007.05471","title":"Geometric Style Transfer","created":"2020-07-10","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}