{"list":"other","total":63,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"1910.13461","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","created":"2019-10-29","cited_by_count":5893},{"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":"2004.05150","title":"Longformer: The Long-Document Transformer","created":"2020-04-10","cited_by_count":3413},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"1606.00915","title":"DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs","created":"2016-06-02","cited_by_count":3241},{"id":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"1711.07971","title":"Non-local Neural Networks","created":"2017-11-21","cited_by_count":2293},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"id":"2007.14062","title":"Big Bird: Transformers for Longer Sequences","created":"2020-07-28","cited_by_count":1684},{"id":"2001.04451","title":"Reformer: The Efficient Transformer","created":"2020-01-13","cited_by_count":1668},{"id":"1904.10509","title":"Generating Long Sequences with Sparse Transformers","created":"2019-04-23","cited_by_count":1546},{"id":"2006.04768","title":"Linformer: Self-Attention with Linear Complexity","created":"2020-06-08","cited_by_count":1474},{"id":"1903.07291","title":"Semantic Image Synthesis with Spatially-Adaptive Normalization","created":"2019-03-18","cited_by_count":1299},{"id":"2103.17249","title":"StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery","created":"2021-03-31","cited_by_count":991},{"id":"1612.03716","title":"COCO-Stuff: Thing and Stuff Classes in Context","created":"2016-12-12","cited_by_count":864},{"id":"2009.06732","title":"Efficient Transformers: A Survey","created":"2020-09-14","cited_by_count":790},{"id":"2005.00928","title":"Quantifying Attention Flow in Transformers","created":"2020-05-02","cited_by_count":775},{"id":"1802.05751","title":"Image Transformer","created":"2018-02-15","cited_by_count":772},{"id":"2109.07161","title":"Resolution-robust Large Mask Inpainting with Fourier Convolutions","created":"2021-09-15","cited_by_count":738},{"id":"1907.11922","title":"MaskGAN: Towards Diverse and Interactive Facial Image Manipulation","created":"2019-07-27","cited_by_count":628},{"id":"1806.03589","title":"Free-Form Image Inpainting with Gated Convolution","created":"2018-06-10","cited_by_count":594},{"id":"1801.07892","title":"Generative Image Inpainting with Contextual Attention","created":"2018-01-24","cited_by_count":580},{"id":"2104.13840","title":"Twins: Revisiting the Design of Spatial Attention in Vision Transformers","created":"2021-04-28","cited_by_count":565},{"id":"1804.07723","title":"Image Inpainting for Irregular Holes Using Partial Convolutions","created":"2018-04-20","cited_by_count":505},{"id":"2102.10882","title":"Conditional Positional Encodings for Vision Transformers","created":"2021-02-22","cited_by_count":406},{"id":"1905.01164","title":"SinGAN: Learning a Generative Model from a Single Natural Image","created":"2019-05-02","cited_by_count":348},{"id":"2107.00641","title":"Focal Self-attention for Local-Global Interactions in Vision Transformers","created":"2021-07-01","cited_by_count":288},{"id":"1712.06087","title":"\"Zero-Shot\" Super-Resolution using Deep Internal Learning","created":"2017-12-17","cited_by_count":286},{"id":"1911.12861","title":"SEAN: Image Synthesis with Semantic Region-Adaptive Normalization","created":"2019-11-28","cited_by_count":253},{"id":"1707.09405","title":"Photographic Image Synthesis with Cascaded Refinement Networks","created":"2017-07-28","cited_by_count":223},{"id":"2103.15358","title":"Multi-Scale Vision Longformer: A New Vision Transformer for High-Resolution Image Encoding","created":"2021-03-29","cited_by_count":207},{"id":"2005.07727","title":"Semantic Photo Manipulation with a Generative Image Prior","created":"2020-05-15","cited_by_count":178},{"id":"1903.04227","title":"Pluralistic Image Completion","created":"2019-03-11","cited_by_count":162},{"id":"2111.03186","title":"EditGAN: High-Precision Semantic Image Editing","created":"2021-11-04","cited_by_count":156},{"id":"2103.14031","title":"High-Fidelity Pluralistic Image Completion with Transformers","created":"2021-03-25","cited_by_count":134},{"id":"2108.08827","title":"ImageBART: Bidirectional Context with Multinomial Diffusion for Autoregressive Image Synthesis","created":"2021-08-19","cited_by_count":122},{"id":"2004.05571","title":"Cross-domain Correspondence Learning for Exemplar-based Image Translation","created":"2020-04-12","cited_by_count":116},{"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":"1611.09969","title":"High-Resolution Image Inpainting using Multi-Scale Neural Patch Synthesis","created":"2016-11-30","cited_by_count":90},{"id":"1810.11919","title":"Text-Adaptive Generative Adversarial Networks: Manipulating Images with Natural Language","created":"2018-10-29","cited_by_count":90},{"id":"2004.03677","title":"Semantic Image Manipulation Using Scene Graphs","created":"2020-04-07","cited_by_count":82},{"id":"2104.12335","title":"Diverse Image Inpainting with Bidirectional and Autoregressive Transformers","created":"2021-04-26","cited_by_count":80},{"id":"2105.02201","title":"PD-GAN: Probabilistic Diverse GAN for Image Inpainting","created":"2021-05-05","cited_by_count":80},{"id":"2003.11512","title":"Improved Techniques for Training Single-Image GANs","created":"2020-03-25","cited_by_count":78},{"id":"1905.10346","title":"Mask-Guided Portrait Editing with Conditional GANs","created":"2019-05-24","cited_by_count":61},{"id":"1911.10375","title":"Region Normalization for Image Inpainting","created":"2019-11-23","cited_by_count":54},{"id":"2103.06878","title":"Diverse Semantic Image Synthesis via Probability Distribution Modeling","created":"2021-03-11","cited_by_count":49},{"id":"2012.02992","title":"Spatially-Adaptive Pixelwise Networks for Fast Image Translation","created":"2020-12-05","cited_by_count":45},{"id":"2004.04977","title":"SESAME: Semantic Editing of Scenes by Adding, Manipulating or Erasing Objects","created":"2020-04-10","cited_by_count":43},{"id":"1901.00686","title":"Generating Multiple Objects at Spatially Distinct Locations","created":"2019-01-03","cited_by_count":41},{"id":"1812.08352","title":"Sequential Attention GAN for Interactive Image Editing","created":"2018-12-20","cited_by_count":33},{"id":"1808.07535","title":"Learning Hierarchical Semantic Image Manipulation through Structured Representations","created":"2018-08-22","cited_by_count":27},{"id":"2103.12723","title":"DeFLOCNet: Deep Image Editing via Flexible Low-level Controls","created":"2021-03-23","cited_by_count":26},{"id":"2106.02514","title":"The Image Local Autoregressive Transformer","created":"2021-06-04","cited_by_count":14},{"id":"2007.01289","title":"Image Shape Manipulation from a Single Augmented Training Sample","created":"2020-07-02","cited_by_count":13},{"id":"2103.15813","title":"PixelTransformer: Sample Conditioned Signal Generation","created":"2021-03-29","cited_by_count":12},{"id":"2012.07288","title":"Semantic Layout Manipulation with High-Resolution Sparse Attention","created":"2020-12-14","cited_by_count":10}],"next_cursor":null}