{"list":"other","total":63,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"2105.01601","title":"MLP-Mixer: An all-MLP Architecture for Vision","created":"2021-05-04","cited_by_count":1446},{"id":"1908.07919","title":"Deep High-Resolution Representation Learning for Visual Recognition","created":"2019-08-20","cited_by_count":1420},{"id":"1603.06937","title":"Stacked Hourglass Networks for Human Pose Estimation","created":"2016-03-22","cited_by_count":915},{"id":"2009.06732","title":"Efficient Transformers: A Survey","created":"2020-09-14","cited_by_count":790},{"id":"1611.09813","title":"Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervision","created":"2016-11-29","cited_by_count":494},{"id":"2112.09127","title":"ICON: Implicit Clothed humans Obtained from Normals","created":"2021-12-16","cited_by_count":283},{"id":"2208.00571","title":"CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimation","created":"2022-08-01","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":"2012.13392","title":"Deep Learning-Based Human Pose Estimation: A Survey","created":"2020-12-24","cited_by_count":207},{"id":"2211.03375","title":"AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time","created":"2022-11-07","cited_by_count":200},{"id":"1712.03453","title":"Single-Shot Multi-Person 3D Pose Estimation From Monocular RGB","created":"2017-12-09","cited_by_count":195},{"id":"2008.09062","title":"Monocular Expressive Body Regression through Body-Driven Attention","created":"2020-08-20","cited_by_count":155},{"id":"2207.06400","title":"PyMAF-X: Towards Well-aligned Full-body Model Regression from Monocular Images","created":"2022-07-13","cited_by_count":153},{"id":"2105.05301","title":"Collaborative Regression of Expressive Bodies using Moderation","created":"2021-05-11","cited_by_count":137},{"id":"2007.11432","title":"Combining Implicit Function Learning and Parametric Models for 3D Human Reconstruction","created":"2020-07-22","cited_by_count":133},{"id":"2005.05732","title":"Skeleton-Aware Networks for Deep Motion Retargeting","created":"2020-05-12","cited_by_count":124},{"id":"2004.00214","title":"BCNet: Learning Body and Cloth Shape from A Single Image","created":"2020-04-01","cited_by_count":120},{"id":"2006.08072","title":"Geo-PIFu: Geometry and Pixel Aligned Implicit Functions for Single-view Human Reconstruction","created":"2020-06-15","cited_by_count":112},{"id":"2203.01923","title":"Recovering 3D Human Mesh from Monocular Images: A Survey","created":"2022-03-03","cited_by_count":103},{"id":"2003.10350","title":"Weakly Supervised 3D Human Pose and Shape Reconstruction with Normalizing Flows","created":"2020-03-23","cited_by_count":94},{"id":"1803.00455","title":"LCR-Net++: Multi-person 2D and 3D Pose Detection in Natural Images","created":"2018-03-01","cited_by_count":88},{"id":"2004.13985","title":"Motion Guided 3D Pose Estimation from Videos","created":"2020-04-29","cited_by_count":85},{"id":"2207.13820","title":"Cross-Attention of Disentangled Modalities for 3D Human Mesh Recovery with Transformers","created":"2022-07-27","cited_by_count":81},{"id":"2203.07628","title":"P-STMO: Pre-Trained Spatial Temporal Many-to-One Model for 3D Human Pose Estimation","created":"2022-03-15","cited_by_count":80},{"id":"2007.13988","title":"Monocular Real-Time Volumetric Performance Capture","created":"2020-07-28","cited_by_count":74},{"id":"2203.16875","title":"MPS-NeRF: Generalizable 3D Human Rendering from Multiview Images","created":"2022-03-31","cited_by_count":53},{"id":"2008.11469","title":"SMAP: Single-Shot Multi-Person Absolute 3D Pose Estimation","created":"2020-08-26","cited_by_count":52},{"id":"2104.11536","title":"Recent Advances in Monocular 2D and 3D Human Pose Estimation: A Deep Learning Perspective","created":"2021-04-23","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":"2008.00206","title":"HMOR: Hierarchical Multi-Person Ordinal Relations for Monocular Multi-Person 3D Pose Estimation","created":"2020-08-01","cited_by_count":44},{"id":"2010.13302","title":"AdaFuse: Adaptive Multiview Fusion for Accurate Human Pose Estimation in the Wild","created":"2020-10-26","cited_by_count":40},{"id":"2006.15561","title":"Joint Hand-object 3D Reconstruction from a Single Image with Cross-branch Feature Fusion","created":"2020-06-28","cited_by_count":39},{"id":"2108.02452","title":"VoxelTrack: Multi-Person 3D Human Pose Estimation and Tracking in the Wild","created":"2021-08-05","cited_by_count":39},{"id":"1912.08077","title":"Multi-task Deep Learning for Real-Time 3D Human Pose Estimation and Action Recognition","created":"2019-12-15","cited_by_count":35},{"id":"2203.08713","title":"DeciWatch: A Simple Baseline for 10x Efficient 2D and 3D Pose Estimation","created":"2022-03-16","cited_by_count":29},{"id":"1901.04877","title":"Feature Boosting Network For 3D Pose Estimation","created":"2019-01-15","cited_by_count":26},{"id":"2110.10355","title":"Dynamic Multi-Person Mesh Recovery From Uncalibrated Multi-View Cameras","created":"2021-10-20","cited_by_count":26},{"id":"2107.00606","title":"Action Transformer: A Self-Attention Model for Short-Time Pose-Based Human Action Recognition","created":"2021-07-01","cited_by_count":24},{"id":"2111.04017","title":"Out-of-Domain Human Mesh Reconstruction via Dynamic Bilevel Online Adaptation","created":"2021-11-07","cited_by_count":24},{"id":"2003.07564","title":"Feedback Graph Convolutional Network for Skeleton-based Action Recognition","created":"2020-03-17","cited_by_count":22},{"id":"2311.02191","title":"SparsePoser: Real-time Full-body Motion Reconstruction from Sparse Data","created":"2023-11-03","cited_by_count":21},{"id":"2110.05092","title":"Adaptive Multi-view and Temporal Fusing Transformer for 3D Human Pose Estimation","created":"2021-10-11","cited_by_count":19},{"id":"1901.03798","title":"3D Human Pose Machines with Self-supervised Learning","created":"2019-01-12","cited_by_count":17},{"id":"2108.02931","title":"Detailed Avatar Recovery from Single Image","created":"2021-08-06","cited_by_count":16},{"id":"2105.10882","title":"Weakly-supervised 3D Human Pose Estimation with Cross-view U-shaped Graph Convolutional Network","created":"2021-05-23","cited_by_count":13},{"id":"2108.06834","title":"Human Pose and Shape Estimation from Single Polarization Images","created":"2021-08-15","cited_by_count":13},{"id":"2109.07353","title":"Learning Dynamical Human-Joint Affinity for 3D Pose Estimation in Videos","created":"2021-09-15","cited_by_count":13},{"id":"2112.10082","title":"MoCaNet: Motion Retargeting in-the-wild via Canonicalization Networks","created":"2021-12-19","cited_by_count":13},{"id":"2205.00748","title":"Dual networks based 3D Multi-Person Pose Estimation from Monocular Video","created":"2022-05-02","cited_by_count":13},{"id":"2003.04894","title":"HEMlets PoSh: Learning Part-Centric Heatmap Triplets for 3D Human Pose and Shape Estimation","created":"2020-03-10","cited_by_count":12},{"id":"1901.10841","title":"View Invariant 3D Human Pose Estimation","created":"2019-01-30","cited_by_count":11},{"id":"2305.05785","title":"Regular Splitting Graph Network for 3D Human Pose Estimation","created":"2023-05-09","cited_by_count":11},{"id":"1911.09245","title":"Consensus-based Optimization for 3D Human Pose Estimation in Camera Coordinates","created":"2019-11-21","cited_by_count":9},{"id":"2103.15596","title":"A Shape-Aware Retargeting Approach to Transfer Human Motion and Appearance in Monocular Videos","created":"2021-03-29","cited_by_count":8},{"id":"2108.00351","title":"LASOR: Learning Accurate 3D Human Pose and Shape Via Synthetic Occlusion-Aware Data and Neural Mesh Rendering","created":"2021-08-01","cited_by_count":8},{"id":"2012.01511","title":"Temporal Representation Learning on Monocular Videos for 3D Human Pose Estimation","created":"2020-12-02","cited_by_count":7},{"id":"2307.13282","title":"High-Resolution Volumetric Reconstruction for Clothed Humans","created":"2023-07-25","cited_by_count":5},{"id":"2009.04930","title":"Orientation Keypoints for 6D Human Pose Estimation","created":"2020-09-10","cited_by_count":3},{"id":"2106.12282","title":"Deep unsupervised 3D human body reconstruction from a sparse set of landmarks","created":"2021-06-23","cited_by_count":2}],"next_cursor":null}