{"total":88,"rows":[{"id":"2403.03950","title":"Stop Regressing: Training Value Functions via Classification for Scalable Deep RL","created":"2024-03-06","cited_by_count":144,"area":"deeprl"},{"id":"2107.11291","title":"Human Pose Regression with Residual Log-likelihood Estimation","created":"2021-07-23","cited_by_count":131,"area":null},{"id":"2106.05969","title":"Dynamics-Regulated Kinematic Policy for Egocentric Pose Estimation","created":"2021-06-10","cited_by_count":101,"area":null},{"id":"2210.10542","title":"PoseGPT: Quantization-based 3D Human Motion Generation and Forecasting","created":"2022-10-19","cited_by_count":78,"area":null},{"id":"2105.08825","title":"Multi-Person Extreme Motion Prediction","created":"2021-05-18","cited_by_count":75,"area":null},{"id":"2105.01057","title":"Neural Monocular 3D Human Motion Capture with Physical Awareness","created":"2021-05-03","cited_by_count":71,"area":null},{"id":"2105.00261","title":"DeepMultiCap: Performance Capture of Multiple Characters Using Sparse Multiview Cameras","created":"2021-05-01","cited_by_count":67,"area":null},{"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,"area":null},{"id":"2104.00340","title":"Reconstructing 3D Human Pose by Watching Humans in the Mirror","created":"2021-04-01","cited_by_count":47,"area":null},{"id":"2105.02467","title":"Body Meshes as Points","created":"2021-05-06","cited_by_count":45,"area":null},{"id":"2105.08141","title":"VPN++: Rethinking Video-Pose embeddings for understanding Activities of Daily Living","created":"2021-05-17","cited_by_count":35,"area":null},{"id":"2107.08580","title":"UNIK: A Unified Framework for Real-world Skeleton-based Action Recognition","created":"2021-07-19","cited_by_count":35,"area":null},{"id":"2108.03619","title":"Learning an Augmented RGB Representation with Cross-Modal Knowledge Distillation for Action Detection","created":"2021-08-08","cited_by_count":32,"area":"distill"},{"id":"2108.08844","title":"Gravity-Aware Monocular 3D Human-Object Reconstruction","created":"2021-08-19","cited_by_count":30,"area":null},{"id":"2210.05895","title":"DG-STGCN: Dynamic Spatial-Temporal Modeling for Skeleton-based Action Recognition","created":"2022-10-12","cited_by_count":26,"area":null},{"id":"2305.03595","title":"HSCNet++: Hierarchical Scene Coordinate Classification and Regression for Visual Localization with Transformer","created":"2023-05-05","cited_by_count":26,"area":null},{"id":"2202.10336","title":"Artificial Intelligence for the Metaverse: A Survey","created":"2022-02-15","cited_by_count":25,"area":null},{"id":"2203.15293","title":"Uncertainty-Aware Adaptation for Self-Supervised 3D Human Pose Estimation","created":"2022-03-29","cited_by_count":25,"area":null},{"id":"2110.02330","title":"Shape-aware Multi-Person Pose Estimation from Multi-View Images","created":"2021-10-05","cited_by_count":24,"area":null},{"id":"2108.08557","title":"DECA: Deep viewpoint-Equivariant human pose estimation using Capsule Autoencoders","created":"2021-08-19","cited_by_count":23,"area":null},{"id":"2211.15692","title":"H3WB: Human3.6M 3D WholeBody Dataset and Benchmark","created":"2022-11-28","cited_by_count":23,"area":null},{"id":"2211.16951","title":"Weakly Supervised 3D Multi-person Pose Estimation for Large-scale Scenes based on Monocular Camera and Single LiDAR","created":"2022-11-30","cited_by_count":23,"area":null},{"id":"2101.02471","title":"PandaNet : Anchor-Based Single-Shot Multi-Person 3D Pose Estimation","created":"2021-01-07","cited_by_count":22,"area":null},{"id":"2209.00065","title":"ViA: View-invariant Skeleton Action Representation Learning via Motion Retargeting","created":"2022-08-31","cited_by_count":22,"area":null},{"id":"2312.01697","title":"Hulk: A Universal Knowledge Translator for Human-Centric Tasks","created":"2023-12-04","cited_by_count":22,"area":null},{"id":"2308.13872","title":"Vision-Based Human Pose Estimation via Deep Learning: A Survey","created":"2023-08-26","cited_by_count":20,"area":null},{"id":"2301.05175","title":"Scene-Aware 3D Multi-Human Motion Capture from a Single Camera","created":"2023-01-12","cited_by_count":19,"area":null},{"id":"2311.18840","title":"Just Add $\\pi$! Pose Induced Video Transformers for Understanding Activities of Daily Living","created":"2023-11-30","cited_by_count":19,"area":null},{"id":"2308.15844","title":"Reconstructing Groups of People with Hypergraph Relational Reasoning","created":"2023-08-30","cited_by_count":18,"area":null},{"id":"2207.10130","title":"Latent Discriminant deterministic Uncertainty","created":"2022-07-20","cited_by_count":17,"area":null},{"id":"2104.01797","title":"Monocular 3D Multi-Person Pose Estimation by Integrating Top-Down and Bottom-Up Networks","created":"2021-04-05","cited_by_count":16,"area":null},{"id":"2208.10211","title":"PoseBERT: A Generic Transformer Module for Temporal 3D Human Modeling","created":"2022-08-22","cited_by_count":15,"area":null},{"id":"2308.16316","title":"Ten Years of Generative Adversarial Nets (GANs): A survey of the state-of-the-art","created":"2023-08-30","cited_by_count":14,"area":null},{"id":"2205.00748","title":"Dual networks based 3D Multi-Person Pose Estimation from Monocular Video","created":"2022-05-02","cited_by_count":13,"area":null},{"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,"area":null},{"id":"2110.09243","title":"Leveraging MoCap Data for Human Mesh Recovery","created":"2021-10-18","cited_by_count":12,"area":null},{"id":"2301.09376","title":"Crowd3D: Towards Hundreds of People Reconstruction from a Single Image","created":"2023-01-23","cited_by_count":12,"area":null},{"id":"2111.01884","title":"Body Size and Depth Disambiguation in Multi-Person Reconstruction from Single Images","created":"2021-11-02","cited_by_count":11,"area":null},{"id":"2402.18844","title":"Deep learning for 3D human pose estimation and mesh recovery: A survey","created":"2024-02-29","cited_by_count":11,"area":null},{"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,"area":null},{"id":"2207.09949","title":"VirtualPose: Learning Generalizable 3D Human Pose Models from Virtual Data","created":"2022-07-20","cited_by_count":10,"area":null},{"id":"2208.00090","title":"Explicit Occlusion Reasoning for Multi-person 3D Human Pose Estimation","created":"2022-07-29","cited_by_count":10,"area":null},{"id":"2101.09745","title":"Iterative Greedy Matching for 3D Human Pose Tracking from Multiple Views","created":"2021-01-24","cited_by_count":9,"area":null},{"id":"2105.05528","title":"WildGait: Learning Gait Representations from Raw Surveillance Streams","created":"2021-05-12","cited_by_count":9,"area":null},{"id":"2203.07697","title":"Distribution-Aware Single-Stage Models for Multi-Person 3D Pose Estimation","created":"2022-03-15","cited_by_count":9,"area":null},{"id":"2207.11341","title":"Dynamic Graph Reasoning for Multi-person 3D Pose Estimation","created":"2022-07-22","cited_by_count":9,"area":null},{"id":"2104.03520","title":"Deep Monocular 3D Human Pose Estimation via Cascaded Dimension-Lifting","created":"2021-04-08","cited_by_count":8,"area":null},{"id":"2205.00508","title":"The Best of Both Worlds: Combining Model-based and Nonparametric Approaches for 3D Human Body Estimation","created":"2022-05-01","cited_by_count":8,"area":null},{"id":"2211.16210","title":"PaCMO: Partner Dependent Human Motion Generation in Dyadic Human Activity using Neural Operators","created":"2022-11-25","cited_by_count":8,"area":null},{"id":"2410.06777","title":"HERM: Benchmarking and Enhancing Multimodal LLMs for Human-Centric Understanding","created":"2024-10-09","cited_by_count":7,"area":"mllm"},{"id":"2202.04533","title":"NIMBLE: A Non-rigid Hand Model with Bones and Muscles","created":"2022-02-09","cited_by_count":6,"area":null},{"id":"2207.04320","title":"Snipper: A Spatiotemporal Transformer for Simultaneous Multi-Person 3D Pose Estimation Tracking and Forecasting on a Video Snippet","created":"2022-07-09","cited_by_count":6,"area":null},{"id":"2211.11983","title":"Weakly-supervised Pre-training for 3D Human Pose Estimation via Perspective Knowledge","created":"2022-11-22","cited_by_count":6,"area":null},{"id":"2310.13039","title":"Human Pose-based Estimation, Tracking and Action Recognition with Deep Learning: A Survey","created":"2023-10-19","cited_by_count":6,"area":null},{"id":"2401.15616","title":"Multi-Person 3D Pose Estimation from Multi-View Uncalibrated Depth Cameras","created":"2024-01-28","cited_by_count":6,"area":null},{"id":"2109.00033","title":"DensePose 3D: Lifting Canonical Surface Maps of Articulated Objects to the Third Dimension","created":"2021-08-31","cited_by_count":5,"area":null},{"id":"2109.14306","title":"Three-Stream 3D/1D CNN for Fine-Grained Action Classification and Segmentation in Table Tennis","created":"2021-09-29","cited_by_count":5,"area":null},{"id":"2112.12180","title":"Multimodal Personality Recognition using Cross-Attention Transformer and Behaviour Encoding","created":"2021-12-22","cited_by_count":5,"area":null},{"id":"2305.13765","title":"Human Body Pose Estimation for Gait Identification: A Comprehensive Survey of Datasets and Models","created":"2023-05-23","cited_by_count":5,"area":null},{"id":"2102.03503","title":"Template-Free Try-on Image Synthesis via Semantic-guided Optimization","created":"2021-02-06","cited_by_count":4,"area":null},{"id":"2406.06309","title":"Is Value Functions Estimation with Classification Plug-and-play for Offline Reinforcement Learning?","created":"2024-06-10","cited_by_count":4,"area":"offlinerl"},{"id":"2406.19290","title":"Human Modelling and Pose Estimation Overview","created":"2024-06-27","cited_by_count":4,"area":null},{"id":"2112.12074","title":"Spatio-Temporal CNN baseline method for the Sports Video Task of MediaEval 2021 benchmark","created":"2021-12-16","cited_by_count":3,"area":null},{"id":"2204.04913","title":"Permutation-Invariant Relational Network for Multi-person 3D Pose Estimation","created":"2022-04-11","cited_by_count":3,"area":null},{"id":"2302.01921","title":"Transformers in Action Recognition: A Review on Temporal Modeling","created":"2022-12-29","cited_by_count":3,"area":null},{"id":"2304.09240","title":"The Metaverse: Survey, Trends, Novel Pipeline Ecosystem & Future Directions","created":"2023-04-18","cited_by_count":3,"area":null},{"id":"2409.11985","title":"An Efficient Model-Agnostic Approach for Uncertainty Estimation in Data-Restricted Pedometric Applications","created":"2024-09-18","cited_by_count":3,"area":null},{"id":"2411.03086","title":"HFGaussian: Learning Generalizable Gaussian Human with Integrated Human Features","created":"2024-11-05","cited_by_count":3,"area":null},{"id":"2212.08731","title":"Multi-person 3D pose estimation from unlabelled data","created":"2022-12-16","cited_by_count":2,"area":null},{"id":"2404.06246","title":"GHNeRF: Learning Generalizable Human Features with Efficient Neural Radiance Fields","created":"2024-04-09","cited_by_count":2,"area":null},{"id":"2103.02521","title":"On the role of depth predictions for 3D human pose estimation","created":"2021-03-03","cited_by_count":1,"area":null},{"id":"2105.10837","title":"Adapted Human Pose: Monocular 3D Human Pose Estimation with Zero Real 3D Pose Data","created":"2021-05-23","cited_by_count":1,"area":null},{"id":"2206.06714","title":"Interpretable Gait Recognition by Granger Causality","created":"2022-06-14","cited_by_count":1,"area":null},{"id":"2210.08562","title":"A New Spatio-Temporal Loss Function for 3D Motion Reconstruction and Extended Temporal Metrics for Motion Evaluation","created":"2022-10-16","cited_by_count":1,"area":null},{"id":"2212.00731","title":"FuRPE: Learning Full-body Reconstruction from Part Experts","created":"2022-11-30","cited_by_count":1,"area":null},{"id":"2406.01196","title":"3D WholeBody Pose Estimation based on Semantic Graph Attention Network and Distance Information","created":"2024-06-03","cited_by_count":1,"area":null},{"id":"2407.02990","title":"Graph and Skipped Transformer: Exploiting Spatial and Temporal Modeling Capacities for Efficient 3D Human Pose Estimation","created":"2024-07-03","cited_by_count":1,"area":null},{"id":"2601.02267","title":"DiffProxy: Multi-View Human Mesh Recovery via Diffusion-Generated Dense Proxies","created":"2026-01-05","cited_by_count":1,"area":null},{"id":"2607.09089","title":"DETRAM: End-to-end DEtection, Tracking and Recovery of HumAn Meshes","created":"2026-07-10","cited_by_count":1,"area":null},{"id":"2203.02453","title":"Real-Time Hybrid Mapping of Populated Indoor Scenes using a Low-Cost Monocular UAV","created":"2022-03-04","cited_by_count":0,"area":null},{"id":"2205.04087","title":"Single-view 3D Body and Cloth Reconstruction under Complex Poses","created":"2022-05-09","cited_by_count":0,"area":null},{"id":"2207.07900","title":"Mutual Adaptive Reasoning for Monocular 3D Multi-Person Pose Estimation","created":"2022-07-16","cited_by_count":0,"area":null},{"id":"2302.06194","title":"Capsules as viewpoint learners for human pose estimation","created":"2023-02-13","cited_by_count":0,"area":null},{"id":"2306.09331","title":"Seeing the Pose in the Pixels: Learning Pose-Aware Representations in Vision Transformers","created":"2023-06-15","cited_by_count":0,"area":null},{"id":"2511.16418","title":"End-to-End Motion Capture from Rigid Body Markers with Geodesic Loss","created":"2025-11-20","cited_by_count":0,"area":null},{"id":"2512.21916","title":"Patch as Node: Human-Centric Graph Representation Learning for Multimodal Action Recognition","created":"2025-12-26","cited_by_count":0,"area":null},{"id":"2602.09918","title":"SARS: A Novel Face and Body Shape and Appearance Aware 3D Reconstruction System extends Morphable Models","created":"2026-02-10","cited_by_count":0,"area":null},{"id":"2603.05963","title":"Skeleton-to-Image Encoding: Enabling Skeleton Representation Learning via Vision-Pretrained Models","created":"2026-03-06","cited_by_count":0,"area":null}],"next_cursor":null}