{"list":"other","total":85,"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":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"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":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"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":"1902.09212","title":"Deep High-Resolution Representation Learning for Human Pose Estimation","created":"2019-02-25","cited_by_count":1339},{"id":"1812.07035","title":"On the Continuity of Rotation Representations in Neural Networks","created":"2018-12-17","cited_by_count":1214},{"id":"1709.02371","title":"PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume","created":"2017-09-07","cited_by_count":968},{"id":"2012.00364","title":"Pre-Trained Image Processing Transformer","created":"2020-12-01","cited_by_count":893},{"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":"1612.02177","title":"Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring","created":"2016-12-07","cited_by_count":727},{"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":"2012.15838","title":"Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humans","created":"2020-12-31","cited_by_count":634},{"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":"2101.08779","title":"AI Choreographer: Music Conditioned 3D Dance Generation with AIST++","created":"2021-01-21","cited_by_count":485},{"id":"2012.09760","title":"End-to-End Human Pose and Mesh Reconstruction with Transformers","created":"2020-12-17","cited_by_count":418},{"id":"2104.08527","title":"PARE: Part Attention Regressor for 3D Human Body Estimation","created":"2021-04-17","cited_by_count":337},{"id":"1812.01601","title":"Learning 3D Human Dynamics from Video","created":"2018-12-04","cited_by_count":316},{"id":"1611.07700","title":"3D Menagerie: Modeling the 3D shape and pose of animals","created":"2016-11-23","cited_by_count":312},{"id":"2011.14672","title":"HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimation","created":"2020-11-30","cited_by_count":307},{"id":"2008.03713","title":"I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Image","created":"2020-08-09","cited_by_count":274},{"id":"1905.03244","title":"Convolutional Mesh Regression for Single-Image Human Shape Reconstruction","created":"2019-05-08","cited_by_count":270},{"id":"2104.00272","title":"Mesh Graphormer","created":"2021-04-01","cited_by_count":265},{"id":"2103.16507","title":"PyMAF: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loop","created":"2021-03-30","cited_by_count":250},{"id":"2008.09047","title":"Pose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human Pose","created":"2020-08-20","cited_by_count":248},{"id":"1803.04758","title":"Video Based Reconstruction of 3D People Models","created":"2018-03-13","cited_by_count":238},{"id":"2007.03858","title":"PaMIR: Parametric Model-Conditioned Implicit Representation for Image-based Human Reconstruction","created":"2020-07-08","cited_by_count":231},{"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":"2008.12272","title":"Monocular, One-stage, Regression of Multiple 3D People","created":"2020-08-27","cited_by_count":218},{"id":"1701.02468","title":"Unite the People: Closing the Loop Between 3D and 2D Human Representations","created":"2017-01-10","cited_by_count":205},{"id":"1712.03453","title":"Single-Shot Multi-Person 3D Pose Estimation From Monocular RGB","created":"2017-12-09","cited_by_count":195},{"id":"1808.05942","title":"Neural Body Fitting: Unifying Deep Learning and Model-Based Human Pose and Shape Estimation","created":"2018-08-17","cited_by_count":185},{"id":"2108.06428","title":"FrankMocap: A Monocular 3D Whole-Body Pose Estimation System via Regression and Integration","created":"2021-08-13","cited_by_count":169},{"id":"1903.05885","title":"Learning to Reconstruct People in Clothing from a Single RGB Camera","created":"2019-03-14","cited_by_count":168},{"id":"1904.08645","title":"Tex2Shape: Detailed Full Human Body Geometry From a Single Image","created":"2019-04-18","cited_by_count":166},{"id":"2011.08627","title":"Beyond Static Features for Temporally Consistent 3D Human Pose and Shape from a Video","created":"2020-11-17","cited_by_count":163},{"id":"2102.07074","title":"TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Up","created":"2021-02-14","cited_by_count":162},{"id":"2109.07448","title":"Neural Human Performer: Learning Generalizable Radiance Fields for Human Performance Rendering","created":"2021-09-15","cited_by_count":158},{"id":"2108.11944","title":"Probabilistic Modeling for Human Mesh Recovery","created":"2021-08-26","cited_by_count":153},{"id":"2110.09408","title":"HRFormer: High-Resolution Transformer for Dense Prediction","created":"2021-10-18","cited_by_count":149},{"id":"2006.08586","title":"Coherent Reconstruction of Multiple Humans from a Single Image","created":"2020-06-15","cited_by_count":136},{"id":"2110.00620","title":"SPEC: Seeing People in the Wild with an Estimated Camera","created":"2021-10-01","cited_by_count":135},{"id":"2111.13817","title":"Video Frame Interpolation Transformer","created":"2021-11-27","cited_by_count":123},{"id":"2004.03686","title":"Exemplar Fine-Tuning for 3D Human Model Fitting Towards In-the-Wild 3D Human Pose Estimation","created":"2020-04-07","cited_by_count":113},{"id":"1905.04266","title":"Exploiting temporal context for 3D human pose estimation in the wild","created":"2019-05-10","cited_by_count":110},{"id":"1808.01338","title":"Detailed Human Avatars from Monocular Video","created":"2018-08-03","cited_by_count":109},{"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":"2008.03789","title":"3D Human Motion Estimation via Motion Compression and Refinement","created":"2020-08-09","cited_by_count":98},{"id":"1712.01337","title":"Self-supervised Learning of Motion Capture","created":"2017-12-04","cited_by_count":97},{"id":"2003.10350","title":"Weakly Supervised 3D Human Pose and Shape Reconstruction with Normalizing Flows","created":"2020-03-23","cited_by_count":94},{"id":"2109.01137","title":"The Power of Points for Modeling Humans in Clothing","created":"2021-09-02","cited_by_count":90},{"id":"1908.07172","title":"Human Mesh Recovery from Monocular Images via a Skeleton-disentangled Representation","created":"2019-08-20","cited_by_count":87},{"id":"2207.13807","title":"Pose-NDF: Modeling Human Pose Manifolds with Neural Distance Fields","created":"2022-07-27","cited_by_count":85},{"id":"2007.11110","title":"Who Left the Dogs Out? 3D Animal Reconstruction with Expectation Maximization in the Loop","created":"2020-07-21","cited_by_count":81},{"id":"2008.08474","title":"Human Body Model Fitting by Learned Gradient Descent","created":"2020-08-19","cited_by_count":81},{"id":"2011.11534","title":"Accurate 3D Hand Pose Estimation for Whole-Body 3D Human Mesh Estimation","created":"2020-11-23","cited_by_count":81},{"id":"1907.02499","title":"Sim2real transfer learning for 3D human pose estimation: motion to the rescue","created":"2019-07-04","cited_by_count":76},{"id":"1611.09010","title":"3D Human Pose Estimation from a Single Image via Distance Matrix Regression","created":"2016-11-28","cited_by_count":73},{"id":"2003.04232","title":"Hierarchical Kinematic Human Mesh Recovery","created":"2020-03-09","cited_by_count":71},{"id":"2104.09496","title":"Temporal Query Networks for Fine-grained Video Understanding","created":"2021-04-19","cited_by_count":68},{"id":"2006.05734","title":"3D Human Mesh Regression with Dense Correspondence","created":"2020-06-10","cited_by_count":66},{"id":"2104.08363","title":"StylePeople: A Generative Model of Fullbody Human Avatars","created":"2021-04-16","cited_by_count":62},{"id":"2109.02303","title":"Encoder-decoder with Multi-level Attention for 3D Human Shape and Pose Estimation","created":"2021-09-06","cited_by_count":62},{"id":"2008.06910","title":"Neural Descent for Visual 3D Human Pose and Shape","created":"2020-08-16","cited_by_count":60},{"id":"2003.02050","title":"Learning to Transfer Texture from Clothing Images to 3D Humans","created":"2020-03-04","cited_by_count":58},{"id":"2106.09336","title":"THUNDR: Transformer-based 3D HUmaN Reconstruction with Markers","created":"2021-06-17","cited_by_count":50},{"id":"1912.13344","title":"Learning 3D Human Shape and Pose from Dense Body Parts","created":"2019-12-31","cited_by_count":48},{"id":"2112.04312","title":"Geometry-Guided Progressive NeRF for Generalizable and Efficient Neural Human Rendering","created":"2021-12-08","cited_by_count":46},{"id":"2103.10978","title":"Probabilistic 3D Human Shape and Pose Estimation from Multiple Unconstrained Images in the Wild","created":"2021-03-19","cited_by_count":40},{"id":"2110.03480","title":"Learning to Regress Bodies from Images using Differentiable Semantic Rendering","created":"2021-10-07","cited_by_count":39},{"id":"2112.04203","title":"Adversarial Parametric Pose Prior","created":"2021-12-08","cited_by_count":38},{"id":"2109.02563","title":"3D Human Texture Estimation from a Single Image with Transformers","created":"2021-09-06","cited_by_count":35},{"id":"2311.04218","title":"Towards Garment Sewing Pattern Reconstruction from a Single Image","created":"2023-11-07","cited_by_count":34},{"id":"2303.13357","title":"POTTER: Pooling Attention Transformer for Efficient Human Mesh Recovery","created":"2023-03-23","cited_by_count":31},{"id":"2007.13666","title":"3D Human Shape and Pose from a Single Low-Resolution Image with Self-Supervised Learning","created":"2020-07-27","cited_by_count":28},{"id":"2103.06498","title":"3D Human Pose, Shape and Texture from Low-Resolution Images and Videos","created":"2021-03-11","cited_by_count":26},{"id":"2111.07868","title":"Tracking People with 3D Representations","created":"2021-11-15","cited_by_count":22},{"id":"1904.03385","title":"Re-Identification Supervised Texture Generation","created":"2019-04-06","cited_by_count":19},{"id":"2110.05458","title":"Learning Realistic Human Reposing using Cyclic Self-Supervision with 3D Shape, Pose, and Appearance Consistency","created":"2021-10-11","cited_by_count":15}],"next_cursor":null}