{"list":"other","total":73,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"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":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1812.04948","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","created":"2018-12-12","cited_by_count":6013},{"id":"1611.07004","title":"Image-to-Image Translation with Conditional Adversarial Networks","created":"2016-11-21","cited_by_count":4527},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"2112.10741","title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models","created":"2021-12-20","cited_by_count":3614},{"id":"1912.04958","title":"Analyzing and Improving the Image Quality of StyleGAN","created":"2019-12-03","cited_by_count":3588},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"1704.00028","title":"Improved Training of Wasserstein GANs","created":"2017-03-31","cited_by_count":2235},{"id":"1311.3618","title":"Describing Textures in the Wild","created":"2013-11-14","cited_by_count":2125},{"id":"1707.02921","title":"Enhanced Deep Residual Networks for Single Image Super-Resolution","created":"2017-07-10","cited_by_count":1552},{"id":"2201.09865","title":"RePaint: Inpainting using Denoising Diffusion Probabilistic Models","created":"2022-01-24","cited_by_count":1430},{"id":"1604.07379","title":"Context Encoders: Feature Learning by Inpainting","created":"2016-04-25","cited_by_count":1428},{"id":"1709.06158","title":"Matterport3D: Learning from RGB-D Data in Indoor Environments","created":"2017-09-18","cited_by_count":1376},{"id":"2012.15840","title":"Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers","created":"2020-12-31","cited_by_count":1369},{"id":"2111.05826","title":"Palette: Image-to-Image Diffusion Models","created":"2021-11-10","cited_by_count":1300},{"id":"1711.11585","title":"High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs","created":"2017-11-30","cited_by_count":1179},{"id":"1511.07122","title":"Multi-Scale Context Aggregation by Dilated Convolutions","created":"2015-11-23","cited_by_count":1133},{"id":"1608.05442","title":"Semantic Understanding of Scenes through the ADE20K Dataset","created":"2016-08-18","cited_by_count":1069},{"id":"2002.04745","title":"On Layer Normalization in the Transformer Architecture","created":"2020-02-12","cited_by_count":922},{"id":"2109.07161","title":"Resolution-robust Large Mask Inpainting with Fourier Convolutions","created":"2021-09-15","cited_by_count":738},{"id":"1811.11721","title":"CCNet: Criss-Cross Attention for Semantic Segmentation","created":"2018-11-28","cited_by_count":718},{"id":"1806.03589","title":"Free-Form Image Inpainting with Gated Convolution","created":"2018-06-10","cited_by_count":594},{"id":"1504.06375","title":"Holistically-Nested Edge Detection","created":"2015-04-24","cited_by_count":592},{"id":"1801.07892","title":"Generative Image Inpainting with Contextual Attention","created":"2018-01-24","cited_by_count":580},{"id":"2112.09133","title":"Masked Feature Prediction for Self-Supervised Visual Pre-Training","created":"2021-12-16","cited_by_count":576},{"id":"2206.00941","title":"Improving Diffusion Models for Inverse Problems using Manifold Constraints","created":"2022-06-02","cited_by_count":508},{"id":"1804.07723","title":"Image Inpainting for Irregular Holes Using Partial Convolutions","created":"2018-04-20","cited_by_count":505},{"id":"2106.14881","title":"Early Convolutions Help Transformers See Better","created":"2021-06-28","cited_by_count":396},{"id":"1912.12180","title":"Axial Attention in Multidimensional Transformers","created":"2019-12-20","cited_by_count":358},{"id":"2112.05146","title":"Come-Closer-Diffuse-Faster: Accelerating Conditional Diffusion Models for Inverse Problems through Stochastic Contraction","created":"2021-12-09","cited_by_count":307},{"id":"2003.04887","title":"ReZero is All You Need: Fast Convergence at Large Depth","created":"2020-03-10","cited_by_count":264},{"id":"2103.10428","title":"Large Scale Image Completion via Co-Modulated Generative Adversarial Networks","created":"2021-03-18","cited_by_count":220},{"id":"2203.15270","title":"MAT: Mask-Aware Transformer for Large Hole Image Inpainting","created":"2022-03-29","cited_by_count":218},{"id":"2202.09741","title":"Visual Attention Network","created":"2022-02-20","cited_by_count":210},{"id":"1906.02569","title":"Gradio: Hassle-Free Sharing and Testing of ML Models in the Wild","created":"2019-06-06","cited_by_count":178},{"id":"2001.08248","title":"How Much Position Information Do Convolutional Neural Networks Encode?","created":"2020-01-22","cited_by_count":172},{"id":"2203.06717","title":"Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNs","created":"2022-03-13","cited_by_count":155},{"id":"2207.03620","title":"More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using Sparsity","created":"2022-07-07","cited_by_count":142},{"id":"2103.14031","title":"High-Fidelity Pluralistic Image Completion with Transformers","created":"2021-03-25","cited_by_count":134},{"id":"2005.09704","title":"Contextual Residual Aggregation for Ultra High-Resolution Image Inpainting","created":"2020-05-19","cited_by_count":124},{"id":"1908.03852","title":"StructureFlow: Image Inpainting via Structure-aware Appearance Flow","created":"2019-08-11","cited_by_count":118},{"id":"2204.02663","title":"Towards An End-to-End Framework for Flow-Guided Video Inpainting","created":"2022-04-06","cited_by_count":113},{"id":"1902.06838","title":"SC-FEGAN: Face Editing Generative Adversarial Network with User's Sketch and Color","created":"2019-02-18","cited_by_count":106},{"id":"2009.01835","title":"Flow-edge Guided Video Completion","created":"2020-09-03","cited_by_count":104},{"id":"2007.06929","title":"Rethinking Image Inpainting via a Mutual Encoder-Decoder with Feature Equalizations","created":"2020-07-14","cited_by_count":102},{"id":"1909.06399","title":"Image inpainting: A review","created":"2019-09-13","cited_by_count":89},{"id":"2104.01431","title":"Aggregated Contextual Transformations for High-Resolution Image Inpainting","created":"2021-04-03","cited_by_count":89},{"id":"2203.00867","title":"Incremental Transformer Structure Enhanced Image Inpainting with Masking Positional Encoding","created":"2022-03-02","cited_by_count":83},{"id":"2104.12335","title":"Diverse Image Inpainting with Bidirectional and Autoregressive Transformers","created":"2021-04-26","cited_by_count":80},{"id":"2005.11742","title":"High-Resolution Image Inpainting with Iterative Confidence Feedback and Guided Upsampling","created":"2020-05-24","cited_by_count":79},{"id":"1905.03246","title":"End-to-End Wireframe Parsing","created":"2019-05-08","cited_by_count":72},{"id":"2007.07527","title":"Learning to Parse Wireframes in Images of Man-Made Environments","created":"2020-07-15","cited_by_count":71},{"id":"2012.05217","title":"Positional Encoding as Spatial Inductive Bias in GANs","created":"2020-12-09","cited_by_count":69},{"id":"2108.09760","title":"Image Inpainting via Conditional Texture and Structure Dual Generation","created":"2021-08-22","cited_by_count":66},{"id":"2003.01663","title":"Holistically-Attracted Wireframe Parsing","created":"2020-03-03","cited_by_count":64},{"id":"2104.03963","title":"InfinityGAN: Towards Infinite-Pixel Image Synthesis","created":"2021-04-08","cited_by_count":61},{"id":"2009.11278","title":"X-LXMERT: Paint, Caption and Answer Questions with Multi-Modal Transformers","created":"2020-09-23","cited_by_count":59},{"id":"2208.06768","title":"Flow-Guided Transformer for Video Inpainting","created":"2022-08-14","cited_by_count":59},{"id":"1805.03356","title":"SPG-Net: Segmentation Prediction and Guidance Network for Image Inpainting","created":"2018-05-09","cited_by_count":58},{"id":"2003.06877","title":"Guidance and Evaluation: Semantic-Aware Image Inpainting for Mixed Scenes","created":"2020-03-15","cited_by_count":43},{"id":"2010.06138","title":"Incorporating BERT into Parallel Sequence Decoding with Adapters","created":"2020-10-13","cited_by_count":39},{"id":"2112.02250","title":"Dense Extreme Inception Network for Edge Detection","created":"2021-12-04","cited_by_count":39},{"id":"2002.04170","title":"Learning to Incorporate Structure Knowledge for Image Inpainting","created":"2020-02-11","cited_by_count":37},{"id":"2011.09808","title":"Unmixing Convolutional Features for Crisp Edge Detection","created":"2020-11-19","cited_by_count":32},{"id":"2103.15087","title":"Learning a Sketch Tensor Space for Image Inpainting of Man-made Scenes","created":"2021-03-28","cited_by_count":25},{"id":"2106.07220","title":"Context-Aware Image Inpainting with Learned Semantic Priors","created":"2021-06-14","cited_by_count":9},{"id":"2206.13644","title":"Feature Refinement to Improve High Resolution Image Inpainting","created":"2022-06-27","cited_by_count":8}],"next_cursor":null}