{"list":"other","total":57,"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"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":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"1611.07004","title":"Image-to-Image Translation with Conditional Adversarial Networks","created":"2016-11-21","cited_by_count":4527},{"id":"2103.13413","title":"Vision Transformers for Dense Prediction","created":"2021-03-24","cited_by_count":1803},{"id":"1904.05866","title":"Expressive Body Capture: 3D Hands, Face, and Body from a Single Image","created":"2019-04-11","cited_by_count":1612},{"id":"1712.06584","title":"End-to-end Recovery of Human Shape and Pose","created":"2017-12-18","cited_by_count":885},{"id":"1805.08318","title":"Self-Attention Generative Adversarial Networks","created":"2018-05-21","cited_by_count":809},{"id":"2007.08501","title":"Accelerating 3D Deep Learning with PyTorch3D","created":"2020-07-16","cited_by_count":784},{"id":"1802.05751","title":"Image Transformer","created":"2018-02-15","cited_by_count":772},{"id":"1607.08128","title":"Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image","created":"2016-07-27","cited_by_count":695},{"id":"1909.12828","title":"Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loop","created":"2019-09-27","cited_by_count":627},{"id":"1912.05656","title":"VIBE: Video Inference for Human Body Pose and Shape Estimation","created":"2019-12-11","cited_by_count":620},{"id":"1802.00434","title":"DensePose: Dense Human Pose Estimation In The Wild","created":"2018-02-01","cited_by_count":575},{"id":"2004.00452","title":"PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization","created":"2020-04-01","cited_by_count":521},{"id":"1912.08193","title":"PointRend: Image Segmentation as Rendering","created":"2019-12-17","cited_by_count":440},{"id":"1412.0035","title":"Understanding Deep Image Representations by Inverting Them","created":"2014-11-26","cited_by_count":403},{"id":"1905.03244","title":"Convolutional Mesh Regression for Single-Image Human Shape Reconstruction","created":"2019-05-08","cited_by_count":270},{"id":"1908.06903","title":"Multi-Garment Net: Learning to Dress 3D People from Images","created":"2019-08-19","cited_by_count":245},{"id":"1705.02894","title":"Geometric GAN","created":"2017-05-08","cited_by_count":233},{"id":"1805.04092","title":"Learning to Estimate 3D Human Pose and Shape from a Single Color Image","created":"2018-05-10","cited_by_count":226},{"id":"2104.14643","title":"AGORA: Avatars in Geography Optimized for Regression Analysis","created":"2021-04-29","cited_by_count":205},{"id":"1903.06473","title":"DeepHuman: 3D Human Reconstruction from a Single Image","created":"2019-03-15","cited_by_count":182},{"id":"2108.07845","title":"ARCH++: Animation-Ready Clothed Human Reconstruction Revisited","created":"2021-08-17","cited_by_count":174},{"id":"1904.08645","title":"Tex2Shape: Detailed Full Human Body Geometry From a Single Image","created":"2019-04-18","cited_by_count":166},{"id":"1909.12224","title":"Liquid Warping GAN: A Unified Framework for Human Motion Imitation, Appearance Transfer and Novel View Synthesis","created":"2019-09-26","cited_by_count":161},{"id":"2008.09062","title":"Monocular Expressive Body Regression through Body-Driven Attention","created":"2020-08-20","cited_by_count":155},{"id":"2105.05301","title":"Collaborative Regression of Expressive Bodies using Moderation","created":"2021-05-11","cited_by_count":137},{"id":"1912.02792","title":"CLOTH3D: Clothed 3D Humans","created":"2019-12-05","cited_by_count":116},{"id":"2010.12447","title":"LoopReg: Self-supervised Learning of Implicit Surface Correspondences, Pose and Shape for 3D Human Mesh Registration","created":"2020-10-23","cited_by_count":108},{"id":"2004.00626","title":"Background Matting: The World is Your Green Screen","created":"2020-04-01","cited_by_count":105},{"id":"2003.12753","title":"Deep Fashion3D: A Dataset and Benchmark for 3D Garment Reconstruction from Single Images","created":"2020-03-28","cited_by_count":103},{"id":"1910.00116","title":"DenseRaC: Joint 3D Pose and Shape Estimation by Dense Render-and-Compare","created":"2019-09-30","cited_by_count":100},{"id":"2102.05644","title":"Training Vision Transformers for Image Retrieval","created":"2021-02-10","cited_by_count":90},{"id":"2007.11610","title":"SIZER: A Dataset and Model for Parsing 3D Clothing and Learning Size Sensitive 3D Clothing","created":"2020-07-22","cited_by_count":87},{"id":"1809.01995","title":"Dense Pose Transfer","created":"2018-09-06","cited_by_count":83},{"id":"2105.06462","title":"Self-Supervised Collision Handling via Generative 3D Garment Models for Virtual Try-On","created":"2021-05-13","cited_by_count":81},{"id":"2011.12438","title":"Continuous Surface Embeddings","created":"2020-11-24","cited_by_count":80},{"id":"1908.07117","title":"360-Degree Textures of People in Clothing from a Single Image","created":"2019-08-20","cited_by_count":75},{"id":"2008.08324","title":"FrankMocap: Fast Monocular 3D Hand and Body Motion Capture by Regression and Integration","created":"2020-08-19","cited_by_count":73},{"id":"2006.05734","title":"3D Human Mesh Regression with Dense Correspondence","created":"2020-06-10","cited_by_count":66},{"id":"2101.04104","title":"Neural Re-Rendering of Humans from a Single Image","created":"2021-01-11","cited_by_count":59},{"id":"2109.02563","title":"3D Human Texture Estimation from a Single Image with Transformers","created":"2021-09-06","cited_by_count":35},{"id":"2004.14231","title":"Image Captioning through Image Transformer","created":"2020-04-29","cited_by_count":29},{"id":"2201.08141","title":"SPAMs: Structured Implicit Parametric Models","created":"2022-01-20","cited_by_count":29},{"id":"2103.17266","title":"Semi-supervised Synthesis of High-Resolution Editable Textures for 3D Humans","created":"2021-03-31","cited_by_count":21},{"id":"2007.15506","title":"SimPose: Effectively Learning DensePose and Surface Normals of People from Simulated Data","created":"2020-07-30","cited_by_count":17},{"id":"2106.09758","title":"Discovering Relationships between Object Categories via Universal Canonical Maps","created":"2021-06-17","cited_by_count":13},{"id":"2103.15573","title":"HumanGPS: Geodesic PreServing Feature for Dense Human Correspondences","created":"2021-03-29","cited_by_count":12},{"id":"2104.08013","title":"Data-Driven 3D Reconstruction of Dressed Humans From Sparse Views","created":"2021-04-16","cited_by_count":11},{"id":"2110.15267","title":"UltraPose: Synthesizing Dense Pose with 1 Billion Points by Human-body Decoupling 3D Model","created":"2021-10-28","cited_by_count":9},{"id":"2102.00062","title":"Neural 3D Clothes Retargeting from a Single Image","created":"2021-01-29","cited_by_count":5}],"next_cursor":null}