{"total":50,"rows":[{"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,"area":null},{"id":"2112.12761","title":"BANMo: Building Animatable 3D Neural Models from Many Casual Videos","created":"2021-12-23","cited_by_count":197,"area":null},{"id":"2110.00620","title":"SPEC: Seeing People in the Wild with an Estimated Camera","created":"2021-10-01","cited_by_count":135,"area":null},{"id":"2107.11291","title":"Human Pose Regression with Residual Log-likelihood Estimation","created":"2021-07-23","cited_by_count":131,"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":"2106.03336","title":"Wide-Baseline Relative Camera Pose Estimation with Directional Learning","created":"2021-06-07","cited_by_count":49,"area":null},{"id":"2107.00434","title":"Learning to Disambiguate Strongly Interacting Hands via Probabilistic Per-pixel Part Segmentation","created":"2021-07-01","cited_by_count":40,"area":null},{"id":"2304.11431","title":"A Review of Deep Learning for Video Captioning","created":"2023-04-22","cited_by_count":28,"area":null},{"id":"2304.00600","title":"Recurrence without Recurrence: Stable Video Landmark Detection with Deep Equilibrium Models","created":"2023-04-02","cited_by_count":27,"area":null},{"id":"2106.11650","title":"A Survey on Human-aware Robot Navigation","created":"2021-06-22","cited_by_count":24,"area":null},{"id":"2204.07370","title":"2D Human Pose Estimation: A Survey","created":"2022-04-15","cited_by_count":21,"area":null},{"id":"2310.13766","title":"U-BEV: Height-aware Bird's-Eye-View Segmentation and Neural Map-based Relocalization","created":"2023-10-20","cited_by_count":13,"area":null},{"id":"2106.12556","title":"Real-time Outdoor Localization Using Radio Maps: A Deep Learning Approach","created":"2021-06-23","cited_by_count":12,"area":null},{"id":"2405.12607","title":"S3O: A Dual-Phase Approach for Reconstructing Dynamic Shape and Skeleton of Articulated Objects from Single Monocular Video","created":"2024-05-21","cited_by_count":12,"area":null},{"id":"2110.08825","title":"Localization with Sampling-Argmax","created":"2021-10-17","cited_by_count":11,"area":null},{"id":"2205.13271","title":"Unsupervised Multi-object Segmentation Using Attention and Soft-argmax","created":"2022-05-26","cited_by_count":11,"area":null},{"id":"2109.09090","title":"Low-resolution Human Pose Estimation","created":"2021-09-19","cited_by_count":10,"area":null},{"id":"2304.06937","title":"CAMM: Building Category-Agnostic and Animatable 3D Models from Monocular Videos","created":"2023-04-14","cited_by_count":10,"area":null},{"id":"2308.02177","title":"Scene-aware Human Pose Generation using Transformer","created":"2023-08-04","cited_by_count":9,"area":null},{"id":"2401.08809","title":"Learning Implicit Representation for Reconstructing Articulated Objects","created":"2024-01-16","cited_by_count":9,"area":null},{"id":"2412.02254","title":"ProbPose: A Probabilistic Approach to 2D Human Pose Estimation","created":"2024-12-03","cited_by_count":9,"area":null},{"id":"2204.06818","title":"Interpretable Vertebral Fracture Quantification via Anchor-Free Landmarks Localization","created":"2022-04-14","cited_by_count":8,"area":null},{"id":"2102.03939","title":"Single-Shot Cuboids: Geodesics-based End-to-end Manhattan Aligned Layout Estimation from Spherical Panoramas","created":"2021-02-07","cited_by_count":7,"area":null},{"id":"2107.00559","title":"SALYPATH: A Deep-Based Architecture for visual attention prediction","created":"2021-06-29","cited_by_count":7,"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":"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":"2503.23094","title":"FRAME: Floor-aligned Representation for Avatar Motion from Egocentric Video","created":"2025-03-29","cited_by_count":5,"area":null},{"id":"2201.00096","title":"SalyPath360: Saliency and Scanpath Prediction Framework for Omnidirectional Images","created":"2022-01-01","cited_by_count":4,"area":null},{"id":"2204.11548","title":"PedRecNet: Multi-task deep neural network for full 3D human pose and orientation estimation","created":"2022-04-25","cited_by_count":4,"area":null},{"id":"2301.10431","title":"Bias-Compensated Integral Regression for Human Pose Estimation","created":"2023-01-25","cited_by_count":3,"area":null},{"id":"2511.07862","title":"MonoCLUE : Object-Aware Clustering Enhances Monocular 3D Object Detection","created":"2025-11-11","cited_by_count":2,"area":null},{"id":"2101.06663","title":"Separable Batch Normalization for Robust Facial Landmark Localization with Cross-protocol Network Training","created":"2021-01-17","cited_by_count":1,"area":null},{"id":"2211.10963","title":"A Lightweight Domain Adaptive Absolute Pose Regressor Using Barlow Twins Objective","created":"2022-11-20","cited_by_count":1,"area":null},{"id":"2306.03538","title":"SDR-GAIN: A High Real-Time Occluded Pedestrian Pose Completion Method for Autonomous Driving","created":"2023-06-06","cited_by_count":1,"area":null},{"id":"2409.15834","title":"Deep Learning Techniques for Automatic Lateral X-ray Cephalometric Landmark Detection: Is the Problem Solved?","created":"2024-09-24","cited_by_count":1,"area":null},{"id":"2103.10567","title":"CLTA: Contents and Length-based Temporal Attention for Few-shot Action Recognition","created":"2021-03-18","cited_by_count":0,"area":null},{"id":"2210.10247","title":"Performance of different machine learning methods on activity recognition and pose estimation datasets","created":"2022-10-19","cited_by_count":0,"area":null},{"id":"2212.11344","title":"Advanced Baseline for 3D Human Pose Estimation: A Two-Stage Approach","created":"2022-12-21","cited_by_count":0,"area":null},{"id":"2303.12728","title":"LocalEyenet: Deep Attention framework for Localization of Eyes","created":"2023-03-13","cited_by_count":0,"area":null},{"id":"2305.17245","title":"Error Estimation for Single-Image Human Body Mesh Reconstruction","created":"2023-05-26","cited_by_count":0,"area":null},{"id":"2309.14330","title":"Noise-in, Bias-out: Balanced and Real-time MoCap Solving","created":"2023-09-25","cited_by_count":0,"area":null},{"id":"2404.09499","title":"Learning Human Motion from Monocular Videos via Cross-Modal Manifold Alignment","created":"2024-04-15","cited_by_count":0,"area":null},{"id":"2404.14835","title":"Semi-supervised 2D Human Pose Estimation via Adaptive Keypoint Masking","created":"2024-04-23","cited_by_count":0,"area":null},{"id":"2410.22079","title":"HRPVT: High-Resolution Pyramid Vision Transformer for medium and small-scale human pose estimation","created":"2024-10-29","cited_by_count":0,"area":null},{"id":"2501.11069","title":"Refinement Module based on Parse Graph for Human Pose Estimation","created":"2025-01-19","cited_by_count":0,"area":null},{"id":"2504.01764","title":"Dual-stream Transformer-GCN Model with Contextualized Representations Learning for Monocular 3D Human Pose Estimation","created":"2025-04-02","cited_by_count":0,"area":null},{"id":"2601.15200","title":"BBoxMaskPose v2: Expanding Mutual Conditioning to 3D","created":"2026-01-21","cited_by_count":0,"area":null},{"id":"2603.19538","title":"MoCA3D: Monocular 3D Bounding Box Prediction in the Image Plane","created":"2026-03-20","cited_by_count":0,"area":null},{"id":"2608.09083","title":"Learning human joint torques from pixels","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2609.00521","title":"Soft-Argmax for the Projective Plane via the Veronese Embedding","created":"2026-09-01","cited_by_count":0,"area":null}],"next_cursor":null}