{"total":81,"rows":[{"id":"2101.02702","title":"TrackFormer: Multi-Object Tracking with Transformers","created":"2021-01-07","cited_by_count":518,"area":null},{"id":"2306.16940","title":"BEDLAM: A Synthetic Dataset of Bodies Exhibiting Detailed Lifelike Animated Motion","created":"2023-06-29","cited_by_count":236,"area":null},{"id":"2103.14258","title":"Learning to Track with Object Permanence","created":"2021-03-26","cited_by_count":119,"area":null},{"id":"2312.16051","title":"Inter-X: Towards Versatile Human-Human Interaction Analysis","created":"2023-12-26","cited_by_count":98,"area":null},{"id":"2203.07706","title":"ActFormer: A GAN-based Transformer towards General Action-Conditioned 3D Human Motion Generation","created":"2022-03-15","cited_by_count":77,"area":null},{"id":"2108.09518","title":"MOTSynth: How Can Synthetic Data Help Pedestrian Detection and Tracking?","created":"2021-08-21","cited_by_count":69,"area":null},{"id":"2110.07588","title":"Playing for 3D Human Recovery","created":"2021-10-14","cited_by_count":64,"area":null},{"id":"2407.07532","title":"Neural Localizer Fields for Continuous 3D Human Pose and Shape Estimation","created":"2024-07-10","cited_by_count":59,"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":"2212.14474","title":"Learning 3D Human Pose Estimation from Dozens of Datasets using a Geometry-Aware Autoencoder to Bridge Between Skeleton Formats","created":"2022-12-29","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":"2105.08612","title":"SAIL-VOS 3D: A Synthetic Dataset and Baselines for Object Detection and 3D Mesh Reconstruction from Video Data","created":"2021-05-18","cited_by_count":38,"area":null},{"id":"2312.16168","title":"Social-Transmotion: Promptable Human Trajectory Prediction","created":"2023-12-26","cited_by_count":33,"area":null},{"id":"2111.06740","title":"Review of Pedestrian Trajectory Prediction Methods: Comparing Deep Learning and Knowledge-based Approaches","created":"2021-11-11","cited_by_count":30,"area":null},{"id":"2208.09191","title":"Synthetic Data in Human Analysis: A Survey","created":"2022-08-19","cited_by_count":28,"area":null},{"id":"2401.08739","title":"EgoGen: An Egocentric Synthetic Data Generator","created":"2024-01-16","cited_by_count":27,"area":null},{"id":"2210.11940","title":"JRDB-Pose: A Large-scale Dataset for Multi-Person Pose Estimation and Tracking","created":"2022-10-20","cited_by_count":25,"area":null},{"id":"2503.12763","title":"A Survey on Human Interaction Motion Generation","created":"2025-03-17","cited_by_count":25,"area":null},{"id":"2106.11650","title":"A Survey on Human-aware Robot Navigation","created":"2021-06-22","cited_by_count":24,"area":null},{"id":"2205.02301","title":"BodySLAM: Joint Camera Localisation, Mapping, and Human Motion Tracking","created":"2022-05-04","cited_by_count":24,"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":"2207.06167","title":"Unsupervised Visual Representation Learning by Synchronous Momentum Grouping","created":"2022-07-13","cited_by_count":22,"area":null},{"id":"2411.02673","title":"Multi-Transmotion: Pre-trained Model for Human Motion Prediction","created":"2024-11-04","cited_by_count":21,"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":"2308.15844","title":"Reconstructing Groups of People with Hypergraph Relational Reasoning","created":"2023-08-30","cited_by_count":18,"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":"2207.05025","title":"PSP-HDRI$+$: A Synthetic Dataset Generator for Pre-Training of Human-Centric Computer Vision Models","created":"2022-07-11","cited_by_count":15,"area":null},{"id":"2211.02175","title":"Large Scale Real-World Multi-Person Tracking","created":"2022-11-03","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":"2101.01394","title":"VersatileGait: A Large-Scale Synthetic Gait Dataset with Fine-GrainedAttributes and Complicated Scenarios","created":"2021-01-05","cited_by_count":12,"area":null},{"id":"2208.14167","title":"Synthehicle: Multi-Vehicle Multi-Camera Tracking in Virtual Cities","created":"2022-08-30","cited_by_count":12,"area":null},{"id":"2112.09290","title":"PeopleSansPeople: A Synthetic Data Generator for Human-Centric Computer Vision","created":"2021-12-17","cited_by_count":11,"area":null},{"id":"2206.14195","title":"Pedestrian 3D Bounding Box Prediction","created":"2022-06-28","cited_by_count":11,"area":null},{"id":"2211.01778","title":"Progressive Transformation Learning for Leveraging Virtual Images in Training","created":"2022-11-03","cited_by_count":10,"area":null},{"id":"2503.17267","title":"Physical Plausibility-aware Trajectory Prediction via Locomotion Embodiment","created":"2025-03-21","cited_by_count":10,"area":null},{"id":"2110.15267","title":"UltraPose: Synthesizing Dense Pose with 1 Billion Points by Human-body Decoupling 3D Model","created":"2021-10-28","cited_by_count":9,"area":null},{"id":"2308.14492","title":"PointHPS: Cascaded 3D Human Pose and Shape Estimation from Point Clouds","created":"2023-08-28","cited_by_count":9,"area":null},{"id":"2404.11426","title":"SPAMming Labels: Efficient Annotations for the Trackers of Tomorrow","created":"2024-04-17","cited_by_count":7,"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":"2308.07537","title":"AttMOT: Improving Multiple-Object Tracking by Introducing Auxiliary Pedestrian Attributes","created":"2023-08-15","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":"2306.16772","title":"M3Act: Learning from Synthetic Human Group Activities","created":"2023-06-29","cited_by_count":5,"area":null},{"id":"2404.17063","title":"WheelPose: Data Synthesis Techniques to Improve Pose Estimation Performance on Wheelchair Users","created":"2024-04-25","cited_by_count":5,"area":null},{"id":"2507.22742","title":"Social-Pose: Enhancing Trajectory Prediction with Human Body Pose","created":"2025-07-30","cited_by_count":5,"area":null},{"id":"2211.11165","title":"A Benchmark of Video-Based Clothes-Changing Person Re-Identification","created":"2022-11-21","cited_by_count":4,"area":null},{"id":"2310.04416","title":"Alice Benchmarks: Connecting Real World Re-Identification with the Synthetic","created":"2023-10-06","cited_by_count":4,"area":null},{"id":"2405.06574","title":"Deep video representation learning: a survey","created":"2024-05-10","cited_by_count":4,"area":null},{"id":"2406.19290","title":"Human Modelling and Pose Estimation Overview","created":"2024-06-27","cited_by_count":4,"area":null},{"id":"2605.05207","title":"Syn4D: A Multiview Synthetic 4D Dataset","created":"2026-05-06","cited_by_count":4,"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":"2403.19022","title":"WALT3D: Generating Realistic Training Data from Time-Lapse Imagery for Reconstructing Dynamic Objects under Occlusion","created":"2024-03-27","cited_by_count":3,"area":null},{"id":"2409.20324","title":"HEADS-UP: Head-Mounted Egocentric Dataset for Trajectory Prediction in Blind Assistance Systems","created":"2024-09-30","cited_by_count":3,"area":null},{"id":"2411.17376","title":"RealTraj: Towards Real-World Pedestrian Trajectory Forecasting","created":"2024-11-26","cited_by_count":3,"area":null},{"id":"2304.05090","title":"CrowdSim2: an Open Synthetic Benchmark for Object Detectors","created":"2023-04-11","cited_by_count":2,"area":null},{"id":"2404.00626","title":"Domain Generalizable Person Search Using Unreal Dataset","created":"2024-03-31","cited_by_count":2,"area":null},{"id":"2404.06741","title":"An Animation-based Augmentation Approach for Action Recognition from Discontinuous Video","created":"2024-04-10","cited_by_count":2,"area":null},{"id":"2410.14844","title":"SYNOSIS: Image synthesis pipeline for machine vision in metal surface inspection","created":"2024-10-18","cited_by_count":2,"area":null},{"id":"2506.00871","title":"Towards Predicting Any Human Trajectory In Context","created":"2025-06-01","cited_by_count":2,"area":null},{"id":"2608.15659","title":"WorldRover: A Scalable Synthetic Video Data Engine for World Exploration with Rich Annotations","created":"2026-08-16","cited_by_count":2,"area":null},{"id":"2104.04721","title":"Do as we do: Multiple Person Video-To-Video Transfer","created":"2021-04-10","cited_by_count":1,"area":null},{"id":"2106.16100","title":"Synthetic Data Are as Good as the Real for Association Knowledge Learning in Multi-object Tracking","created":"2021-06-30","cited_by_count":1,"area":null},{"id":"2206.03033","title":"Deep Learning Techniques for Visual Counting","created":"2022-06-07","cited_by_count":1,"area":null},{"id":"2208.03571","title":"Transformer-based assignment decision network for multiple object tracking","created":"2022-08-06","cited_by_count":1,"area":null},{"id":"2508.20892","title":"To New Beginnings: A Survey of Unified Perception in Autonomous Vehicle Software","created":"2025-08-28","cited_by_count":1,"area":null},{"id":"2602.03064","title":"JRDB-Pose3D: A Multi-person 3D Human Pose and Shape Estimation Dataset for Robotics","created":"2026-02-03","cited_by_count":1,"area":null},{"id":"2607.19971","title":"Unified Prediction and Planning via Conflict-Aware Disjoint Parameter Training","created":"2026-07-22","cited_by_count":1,"area":null},{"id":"2105.14421","title":"VersatileGait: A Large-Scale Synthetic Gait Dataset Towards in-the-Wild Simulation","created":"2021-05-30","cited_by_count":0,"area":null},{"id":"2202.04966","title":"Real-Time Siamese Multiple Object Tracker with Enhanced Proposals","created":"2022-02-10","cited_by_count":0,"area":null},{"id":"2207.11325","title":"PieTrack: An MOT solution based on synthetic data training and self-supervised domain adaptation","created":"2022-07-22","cited_by_count":0,"area":null},{"id":"2302.13891","title":"Supervised Virtual-to-Real Domain Adaptation for Object Detection Task using YOLO","created":"2023-02-27","cited_by_count":0,"area":null},{"id":"2306.11710","title":"Data-Driven but Privacy-Conscious: Pedestrian Dataset De-identification via Full-Body Person Synthesis","created":"2023-06-20","cited_by_count":0,"area":null},{"id":"2307.11360","title":"ParGANDA: Making Synthetic Pedestrians A Reality For Object Detection","created":"2023-07-21","cited_by_count":0,"area":null},{"id":"2312.02613","title":"A Unified Simulation Framework for Visual and Behavioral Fidelity in Crowd Analysis","created":"2023-12-05","cited_by_count":0,"area":null},{"id":"2401.13414","title":"GTAutoAct: An Automatic Datasets Generation Framework Based on Game Engine Redevelopment for Action Recognition","created":"2024-01-24","cited_by_count":0,"area":null},{"id":"2501.01877","title":"ANTHROPOS-V: benchmarking the novel task of Crowd Volume Estimation","created":"2025-01-03","cited_by_count":0,"area":null},{"id":"2510.15673","title":"Valeo Near-Field: a novel dataset for pedestrian intent detection","created":"2025-10-17","cited_by_count":0,"area":null},{"id":"2512.09005","title":"A Survey of Body and Face Motion: Datasets, Performance Evaluation Metrics and Generative Techniques","created":"2025-12-09","cited_by_count":0,"area":null},{"id":"2602.22791","title":"Robust Human Trajectory Prediction via Self-Supervised Skeleton Representation Learning","created":"2026-02-26","cited_by_count":0,"area":null},{"id":"2604.02032","title":"IndoorCrowd: A Multi-Scene Dataset for Human Detection, Segmentation, and Tracking with an Automated Annotation Pipeline","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2606.23058","title":"Three-Step Hierarchical Transformer for Multi-Pedestrian Trajectory Prediction","created":"2026-06-22","cited_by_count":0,"area":null},{"id":"2610.08826","title":"PanoPed: Beyond Bounding Boxes for Sim-to-Real Panoramic Pedestrian Tracking","created":"2026-09-25","cited_by_count":0,"area":null}],"next_cursor":null}