{"list":"other","total":53,"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":"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":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"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":"1603.08155","title":"Perceptual Losses for Real-Time Style Transfer and Super-Resolution","created":"2016-03-27","cited_by_count":2694},{"id":"1711.07971","title":"Non-local Neural Networks","created":"2017-11-21","cited_by_count":2293},{"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":"2102.04306","title":"TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation","created":"2021-02-08","cited_by_count":1558},{"id":"2012.15840","title":"Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers","created":"2020-12-31","cited_by_count":1369},{"id":"1903.07291","title":"Semantic Image Synthesis with Spatially-Adaptive Normalization","created":"2019-03-18","cited_by_count":1299},{"id":"2012.00364","title":"Pre-Trained Image Processing Transformer","created":"2020-12-01","cited_by_count":893},{"id":"1606.03657","title":"InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets","created":"2016-06-12","cited_by_count":860},{"id":"1804.04732","title":"Multimodal Unsupervised Image-to-Image Translation","created":"2018-04-12","cited_by_count":795},{"id":"2102.04378","title":"TransReID: Transformer-based Object Re-Identification","created":"2021-02-08","cited_by_count":435},{"id":"1610.07629","title":"A Learned Representation For Artistic Style","created":"2016-10-24","cited_by_count":341},{"id":"1705.09368","title":"Pose Guided Person Image Generation","created":"2017-05-25","cited_by_count":251},{"id":"1801.00055","title":"Deformable GANs for Pose-based Human Image Generation","created":"2017-12-29","cited_by_count":166},{"id":"2003.12267","title":"Controllable Person Image Synthesis with Attribute-Decomposed GAN","created":"2020-03-27","cited_by_count":150},{"id":"1904.03349","title":"Progressive Pose Attention Transfer for Person Image Generation","created":"2019-04-06","cited_by_count":138},{"id":"1803.02077","title":"The Contextual Loss for Image Transformation with Non-Aligned Data","created":"2018-03-06","cited_by_count":135},{"id":"1804.04694","title":"A Variational U-Net for Conditional Appearance and Shape Generation","created":"2018-04-12","cited_by_count":124},{"id":"1703.05446","title":"Look into Person: Self-supervised Structure-sensitive Learning and A New Benchmark for Human Parsing","created":"2017-03-16","cited_by_count":109},{"id":"1712.02621","title":"Disentangled Person Image Generation","created":"2017-12-07","cited_by_count":98},{"id":"2112.02749","title":"One-shot Talking Face Generation from Single-speaker Audio-Visual Correlation Learning","created":"2021-12-06","cited_by_count":87},{"id":"2103.04023","title":"PISE: Person Image Synthesis and Editing with Decoupled GAN","created":"2021-03-06","cited_by_count":62},{"id":"2003.12697","title":"Semantically Multi-modal Image Synthesis","created":"2020-03-28","cited_by_count":58},{"id":"1809.10280","title":"Unsupervised Person Image Synthesis in Arbitrary Poses","created":"2018-09-27","cited_by_count":55},{"id":"2204.06160","title":"Neural Texture Extraction and Distribution for Controllable Person Image Synthesis","created":"2022-04-13","cited_by_count":55},{"id":"2208.00712","title":"Cross Attention Based Style Distribution for Controllable Person Image Synthesis","created":"2022-08-01","cited_by_count":45},{"id":"2104.06650","title":"Learning Semantic Person Image Generation by Region-Adaptive Normalization","created":"2021-04-14","cited_by_count":44},{"id":"1704.03899","title":"Deep Reinforcement Learning-based Image Captioning with Embedding Reward","created":"2017-04-12","cited_by_count":40},{"id":"2108.07379","title":"DRB-GAN: A Dynamic ResBlock Generative Adversarial Network for Artistic Style Transfer","created":"2021-08-17","cited_by_count":39},{"id":"1904.03379","title":"Unsupervised Person Image Generation with Semantic Parsing Transformation","created":"2019-04-06","cited_by_count":32},{"id":"2108.02366","title":"Dual Graph Convolutional Networks with Transformer and Curriculum Learning for Image Captioning","created":"2021-08-05","cited_by_count":27},{"id":"2102.12593","title":"AniGAN: Style-Guided Generative Adversarial Networks for Unsupervised Anime Face Generation","created":"2021-02-24","cited_by_count":25},{"id":"2304.04420","title":"Feature Representation Learning with Adaptive Displacement Generation and Transformer Fusion for Micro-Expression Recognition","created":"2023-04-10","cited_by_count":17},{"id":"1608.04314","title":"Weakly Supervised Object Localization Using Size Estimates","created":"2016-08-15","cited_by_count":16},{"id":"2002.00774","title":"Hide-and-Tell: Learning to Bridge Photo Streams for Visual Storytelling","created":"2020-02-03","cited_by_count":13},{"id":"1902.05581","title":"Adversarially Approximated Autoencoder for Image Generation and Manipulation","created":"2019-02-14","cited_by_count":12},{"id":"2106.10876","title":"Total Generate: Cycle in Cycle Generative Adversarial Networks for Generating Human Faces, Hands, Bodies, and Natural Scenes","created":"2021-06-21","cited_by_count":12},{"id":"2304.00414","title":"Learning Dynamic Style Kernels for Artistic Style Transfer","created":"2023-04-02","cited_by_count":12},{"id":"1905.08766","title":"Toward Learning a Unified Many-to-Many Mapping for Diverse Image Translation","created":"2019-05-21","cited_by_count":10},{"id":"1909.00114","title":"Towards Learning Affine-Invariant Representations via Data-Efficient CNNs","created":"2019-08-31","cited_by_count":10},{"id":"1910.02101","title":"Adaptively Denoising Proposal Collection for Weakly Supervised Object Localization","created":"2019-10-04","cited_by_count":9},{"id":"2110.10837","title":"A Domain Gap Aware Generative Adversarial Network for Multi-domain Image Translation","created":"2021-10-21","cited_by_count":8},{"id":"2201.01087","title":"Learning Quality-aware Representation for Multi-person Pose Regression","created":"2022-01-04","cited_by_count":6},{"id":"1910.02560","title":"Stacked Wasserstein Autoencoder","created":"2019-10-04","cited_by_count":5}],"next_cursor":null}