{"list":"other","total":82,"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":"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2375},{"id":"2107.03006","title":"Structured Denoising Diffusion Models in Discrete State-Spaces","created":"2021-07-07","cited_by_count":1719},{"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":"1908.07919","title":"Deep High-Resolution Representation Learning for Visual Recognition","created":"2019-08-20","cited_by_count":1420},{"id":"1904.03278","title":"AMASS: Archive of Motion Capture as Surface Shapes","created":"2019-04-05","cited_by_count":1236},{"id":"2202.04200","title":"MaskGIT: Masked Generative Image Transformer","created":"2022-02-08","cited_by_count":1099},{"id":"1712.06584","title":"End-to-end Recovery of Human Shape and Pose","created":"2017-12-18","cited_by_count":885},{"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":"2006.08218","title":"Self-supervised Learning: Generative or Contrastive","created":"2020-06-15","cited_by_count":694},{"id":"2301.00704","title":"Muse: Text-To-Image Generation via Masked Generative Transformers","created":"2023-01-02","cited_by_count":648},{"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":"1705.03122","title":"Convolutional Sequence to Sequence Learning","created":"2017-05-08","cited_by_count":552},{"id":"2111.11426","title":"Neural Fields in Visual Computing and Beyond","created":"2021-11-22","cited_by_count":540},{"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":"2012.09760","title":"End-to-End Human Pose and Mesh Reconstruction with Transformers","created":"2020-12-17","cited_by_count":418},{"id":"2312.00063","title":"MoMask: Generative Masked Modeling of 3D Human Motions","created":"2023-11-29","cited_by_count":400},{"id":"2305.20091","title":"Humans in 4D: Reconstructing and Tracking Humans with Transformers","created":"2023-05-31","cited_by_count":350},{"id":"2104.08527","title":"PARE: Part Attention Regressor for 3D Human Body Estimation","created":"2021-04-17","cited_by_count":337},{"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":"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":"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":"2306.16940","title":"BEDLAM: A Synthetic Dataset of Bodies Exhibiting Detailed Lifelike Animated Motion","created":"2023-06-29","cited_by_count":236},{"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":"2108.11944","title":"Probabilistic Modeling for Human Mesh Recovery","created":"2021-08-26","cited_by_count":153},{"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":"2303.18246","title":"3D Human Pose Estimation via Intuitive Physics","created":"2023-03-31","cited_by_count":103},{"id":"1903.02330","title":"Self-Supervised Learning of 3D Human Pose using Multi-view Geometry","created":"2019-03-06","cited_by_count":98},{"id":"1712.01337","title":"Self-supervised Learning of Motion Capture","created":"2017-12-04","cited_by_count":97},{"id":"2308.16894","title":"EMDB: The Electromagnetic Database of Global 3D Human Pose and Shape in the Wild","created":"2023-08-31","cited_by_count":97},{"id":"1904.04812","title":"Unsupervised 3D Pose Estimation with Geometric Self-Supervision","created":"2019-04-09","cited_by_count":95},{"id":"2404.16752","title":"TokenHMR: Advancing Human Mesh Recovery with a Tokenized Pose Representation","created":"2024-04-25","cited_by_count":95},{"id":"1904.05547","title":"Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Network","created":"2019-04-11","cited_by_count":92},{"id":"2110.01515","title":"A Review of the Gumbel-max Trick and its Extensions for Discrete Stochasticity in Machine Learning","created":"2021-10-04","cited_by_count":82},{"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":"1904.01324","title":"Monocular 3D Human Pose Estimation by Generation and Ordinal Ranking","created":"2019-04-02","cited_by_count":76},{"id":"2105.08825","title":"Multi-Person Extreme Motion Prediction","created":"2021-05-18","cited_by_count":75},{"id":"2011.14679","title":"CanonPose: Self-Supervised Monocular 3D Human Pose Estimation in the Wild","created":"2020-11-30","cited_by_count":65},{"id":"2104.07300","title":"Learning to Estimate Robust 3D Human Mesh from In-the-Wild Crowded Scenes","created":"2021-04-15","cited_by_count":65},{"id":"2208.00173","title":"A Survey on Masked Autoencoder for Self-supervised Learning in Vision and Beyond","created":"2022-07-30","cited_by_count":58},{"id":"2203.13349","title":"Occluded Human Mesh Recovery","created":"2022-03-24","cited_by_count":54},{"id":"2006.04325","title":"Fully Convolutional Mesh Autoencoder using Efficient Spatially Varying Kernels","created":"2020-06-08","cited_by_count":53},{"id":"2011.00980","title":"3D Multi-bodies: Fitting Sets of Plausible 3D Human Models to Ambiguous Image Data","created":"2020-11-02","cited_by_count":50},{"id":"2110.00990","title":"Hierarchical Kinematic Probability Distributions for 3D Human Shape and Pose Estimation from Images in the Wild","created":"2021-10-03","cited_by_count":48},{"id":"2303.11638","title":"Human Pose as Compositional Tokens","created":"2023-03-21","cited_by_count":45},{"id":"2305.08590","title":"NIKI: Neural Inverse Kinematics with Invertible Neural Networks for 3D Human Pose and Shape Estimation","created":"2023-05-15","cited_by_count":45},{"id":"2004.04400","title":"Self-Supervised 3D Human Pose Estimation via Part Guided Novel Image Synthesis","created":"2020-04-09","cited_by_count":44},{"id":"2303.11726","title":"3D Human Mesh Estimation from Virtual Markers","created":"2023-03-21","cited_by_count":44},{"id":"2306.09337","title":"Generative Proxemics: A Prior for 3D Social Interaction from Images","created":"2023-06-15","cited_by_count":43},{"id":"2211.10705","title":"TORE: Token Reduction for Efficient Human Mesh Recovery with Transformer","created":"2022-11-19","cited_by_count":41},{"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":"2305.13689","title":"Know Your Self-supervised Learning: A Survey on Image-based Generative and Discriminative Training","created":"2023-05-23","cited_by_count":39},{"id":"2205.06254","title":"Learned Vertex Descent: A New Direction for 3D Human Model Fitting","created":"2022-05-12","cited_by_count":37},{"id":"1702.02258","title":"Generating Multiple Diverse Hypotheses for Human 3D Pose Consistent with 2D Joint Detections","created":"2017-02-08","cited_by_count":30},{"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":"2209.10529","title":"Benchmarking and Analyzing 3D Human Pose and Shape Estimation Beyond Algorithms","created":"2022-09-21","cited_by_count":28},{"id":"2403.03122","title":"NRDF: Neural Riemannian Distance Fields for Learning Articulated Pose Priors","created":"2024-03-05","cited_by_count":27},{"id":"2304.09502","title":"Sampling is Matter: Point-guided 3D Human Mesh Reconstruction","created":"2023-04-19","cited_by_count":24},{"id":"2305.06968","title":"HuManiFlow: Ancestor-Conditioned Normalising Flows on SO(3) Manifolds for Human Pose and Shape Distribution Estimation","created":"2023-05-11","cited_by_count":24},{"id":"2208.10652","title":"Learning Visibility for Robust Dense Human Body Estimation","created":"2022-08-23","cited_by_count":15},{"id":"2308.02963","title":"Generative Approach for Probabilistic Human Mesh Recovery using Diffusion Models","created":"2023-08-05","cited_by_count":14},{"id":"2312.08291","title":"VQ-HPS: Human Pose and Shape Estimation in a Vector-Quantized Latent Space","created":"2023-12-13","cited_by_count":13},{"id":"2110.09243","title":"Leveraging MoCap Data for Human Mesh Recovery","created":"2021-10-18","cited_by_count":12},{"id":"2211.13357","title":"MPT: Mesh Pre-Training with Transformers for Human Pose and Mesh Reconstruction","created":"2022-11-24","cited_by_count":11},{"id":"2203.15865","title":"On Triangulation as a Form of Self-Supervision for 3D Human Pose Estimation","created":"2022-03-29","cited_by_count":10},{"id":"1802.00634","title":"Activity-conditioned continuous human pose estimation for performance analysis of athletes using the example of swimming","created":"2018-02-02","cited_by_count":9},{"id":"2304.11117","title":"A vector quantized masked autoencoder for speech emotion recognition","created":"2023-04-21","cited_by_count":8},{"id":"2303.05370","title":"Rethinking Self-Supervised Visual Representation Learning in Pre-training for 3D Human Pose and Shape Estimation","created":"2023-03-09","cited_by_count":7},{"id":"2305.03568","title":"A vector quantized masked autoencoder for audiovisual speech emotion recognition","created":"2023-05-05","cited_by_count":7},{"id":"2311.09104","title":"Cross-view and Cross-pose Completion for 3D Human Understanding","created":"2023-11-15","cited_by_count":6},{"id":"2210.04514","title":"Self-Supervised 3D Human Pose Estimation in Static Video Via Neural Rendering","created":"2022-10-10","cited_by_count":2}],"next_cursor":null}