{"total":63,"rows":[{"id":"2606.03748","title":"Ultralytics YOLO26: Unified Real-Time End-to-End Vision Models","created":"2026-06-02","cited_by_count":57,"area":null},{"id":"2312.07526","title":"RTMO: Towards High-Performance One-Stage Real-Time Multi-Person Pose Estimation","created":"2023-12-12","cited_by_count":34,"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":"2309.17209","title":"Robots That Can See: Leveraging Human Pose for Trajectory Prediction","created":"2023-09-29","cited_by_count":23,"area":null},{"id":"2406.10447","title":"The BabyView dataset: High-resolution egocentric videos of infants' and young children's everyday experiences","created":"2024-06-14","cited_by_count":17,"area":null},{"id":"2209.13948","title":"Obj2Seq: Formatting Objects as Sequences with Class Prompt for Visual Tasks","created":"2022-09-28","cited_by_count":12,"area":null},{"id":"2503.19851","title":"Towards Online Multi-Modal Social Interaction Understanding","created":"2025-03-25","cited_by_count":12,"area":null},{"id":"2402.12810","title":"PIP-Net: Pedestrian Intention Prediction in the Wild","created":"2024-02-20","cited_by_count":11,"area":null},{"id":"2412.01537","title":"HandOS: 3D Hand Reconstruction in One Stage","created":"2024-12-02","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":"2408.09332","title":"YOLOv1 to YOLOv10: The fastest and most accurate real-time object detection systems","created":"2024-08-18","cited_by_count":7,"area":null},{"id":"2407.14224","title":"Hierarchical Windowed Graph Attention Network and a Large Scale Dataset for Isolated Indian Sign Language Recognition","created":"2024-07-19","cited_by_count":6,"area":null},{"id":"2409.08494","title":"WheelPoser: Sparse-IMU Based Body Pose Estimation for Wheelchair Users","created":"2024-09-13","cited_by_count":5,"area":null},{"id":"2303.05617","title":"KGNv2: Separating Scale and Pose Prediction for Keypoint-based 6-DoF Grasp Synthesis on RGB-D input","created":"2023-03-09","cited_by_count":4,"area":null},{"id":"2505.03165","title":"Improving the Reproducibility of Deep Learning Software: An Initial Investigation through a Case Study Analysis","created":"2025-05-06","cited_by_count":3,"area":null},{"id":"2509.12400","title":"From Orthomosaics to Raw UAV Imagery: Enhancing Palm Detection and Crown-Center Localization","created":"2025-09-15","cited_by_count":3,"area":null},{"id":"2603.18739","title":"EdgeCrafter: Compact ViTs for Edge Dense Prediction via Task-Specialized Distillation","created":"2026-03-19","cited_by_count":3,"area":null},{"id":"2304.10765","title":"BPJDet: Extended Object Representation for Generic Body-Part Joint Detection","created":"2023-04-21","cited_by_count":2,"area":null},{"id":"2307.11904","title":"Model Compression Methods for YOLOv5: A Review","created":"2023-07-21","cited_by_count":2,"area":null},{"id":"2408.03564","title":"Riverbed litter monitoring using consumer-grade aerial-aquatic speedy scanner (AASS) and deep learning based super-resolution reconstruction and detection network","created":"2024-08-07","cited_by_count":2,"area":null},{"id":"2412.16742","title":"EasyVis2: A Real Time Multi-view 3D Visualization System for Laparoscopic Surgery Training Enhanced by a Deep Neural Network YOLOv8-Pose","created":"2024-12-21","cited_by_count":2,"area":null},{"id":"2504.16443","title":"Marginalized Generalized IoU (MGIoU): A Unified Objective Function for Optimizing Any Convex Parametric Shapes","created":"2025-04-23","cited_by_count":2,"area":null},{"id":"2509.05031","title":"Pointing-Guided Target Estimation via Transformer-Based Attention","created":"2025-09-05","cited_by_count":2,"area":null},{"id":"2309.11773","title":"A Real-Time Multi-Task Learning System for Joint Detection of Face, Facial Landmark and Head Pose","created":"2023-09-21","cited_by_count":1,"area":null},{"id":"2310.10423","title":"YOLOv7 for Mosquito Breeding Grounds Detection and Tracking","created":"2023-10-16","cited_by_count":1,"area":null},{"id":"2402.07814","title":"PBADet: A One-Stage Anchor-Free Approach for Part-Body Association","created":"2024-02-12","cited_by_count":1,"area":null},{"id":"2409.20469","title":"PoseAdapt: Sustainable Human Pose Estimation via Continual Learning Benchmarks and Toolkit","created":"2024-09-30","cited_by_count":1,"area":null},{"id":"2506.13027","title":"DETRPose: Real-Time End-to-End Multi-Person Pose Estimation via Modified Transformer Decoder and Novel Denoising Keypoints","created":"2025-06-16","cited_by_count":1,"area":null},{"id":"2603.21803","title":"Timing In stand-up Comedy: Text, Audio, Laughter, Kinesics (TIC-TALK): Pipeline and Database for the Multimodal Study of Comedic Timing","created":"2026-03-23","cited_by_count":1,"area":null},{"id":"2607.07320","title":"SoccerNet 2026 Challenges Results","created":"2026-07-08","cited_by_count":1,"area":null},{"id":"2609.34220","title":"mmHRI: Towards Privacy-Preserving Human-Robot Interaction with Millimeter-Wave Radar","created":"2026-09-28","cited_by_count":1,"area":null},{"id":"2402.03989","title":"YOLOPoint Joint Keypoint and Object Detection","created":"2024-02-06","cited_by_count":0,"area":null},{"id":"2402.16640","title":"DRSI-Net: Dual-Residual Spatial Interaction Network for Multi-Person Pose Estimation","created":"2024-02-26","cited_by_count":0,"area":null},{"id":"2403.01766","title":"Improving Visual Perception of a Social Robot for Controlled and In-the-wild Human-robot Interaction","created":"2024-03-04","cited_by_count":0,"area":null},{"id":"2408.00193","title":"Resilience and Security of Deep Neural Networks Against Intentional and Unintentional Perturbations: Survey and Research Challenges","created":"2024-07-31","cited_by_count":0,"area":null},{"id":"2408.03559","title":"Enhanced hermit crabs detection using super-resolution reconstruction and improved YOLOv8 on UAV-captured imagery","created":"2024-08-07","cited_by_count":0,"area":null},{"id":"2503.13477","title":"Periodontal Bone Loss Analysis via Keypoint Detection With Heuristic Post-Processing","created":"2025-03-05","cited_by_count":0,"area":null},{"id":"2503.22965","title":"Pallet Detection And Localisation From Synthetic Data","created":"2025-03-29","cited_by_count":0,"area":null},{"id":"2506.20522","title":"AI-assisted radiographic analysis in detecting alveolar bone-loss severity and patterns","created":"2025-06-25","cited_by_count":0,"area":null},{"id":"2509.05490","title":"An Analysis of Layer-Freezing Strategies for Enhanced Transfer Learning in YOLO Architectures","created":"2025-09-05","cited_by_count":0,"area":null},{"id":"2511.05996","title":"Exploring Category-level Articulated Object Pose Tracking on SE(3) Manifolds","created":"2025-11-08","cited_by_count":0,"area":null},{"id":"2601.05747","title":"FlyPose: Towards Robust Human Pose Estimation From Aerial Views","created":"2026-01-09","cited_by_count":0,"area":null},{"id":"2602.21904","title":"UNet-Based Keypoint Regression for 3D Cone Localization in Autonomous Racing","created":"2026-02-25","cited_by_count":0,"area":null},{"id":"2603.08681","title":"ER-Pose: Rethinking Keypoint-Driven Representation Learning for Real-Time Human Pose Estimation","created":"2026-03-09","cited_by_count":0,"area":null},{"id":"2604.24609","title":"Evaluation of Pose Estimation Systems for Sign Language Translation","created":"2026-04-27","cited_by_count":0,"area":null},{"id":"2606.11739","title":"Multi-View In-Cabin Monitoring System for Public Transport Vehicles","created":"2026-06-10","cited_by_count":0,"area":null},{"id":"2607.07716","title":"Towards the Explainability of Temporal Graph Networks via Memory Backtracking and Topological Attribution","created":"2026-07-04","cited_by_count":0,"area":null},{"id":"2607.12076","title":"NEEDL-Bench: Dataset for Swiss Needle Cast and Stomata Detection in Microscopy Images","created":"2026-07-13","cited_by_count":0,"area":null},{"id":"2607.12450","title":"Let RGB Be the Language of Vision","created":"2026-07-14","cited_by_count":0,"area":null},{"id":"2607.15890","title":"Exo2EgoPose: Leveraging Exocentric Demonstrations for Vision-Language guided Egocentric 3D Hand Pose Forecasting","created":"2026-07-17","cited_by_count":0,"area":null},{"id":"2607.26921","title":"From Keypoints to Predictive Distributions: Post-Hoc Uncertainty for YOLO-Pose Models","created":"2026-07-29","cited_by_count":0,"area":null},{"id":"2608.05744","title":"Equipment-centric workpiece localization in near real-time using deep learning-based vision and event-driven finite state machines","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2608.13047","title":"Topology-Unified 2D Pose Estimation across Intact, Residual and Prosthetic Limbs","created":"2026-08-13","cited_by_count":0,"area":null},{"id":"2608.15297","title":"TinyDETR-Pose: Towards End-to-End Real-Time Single-Stage 6DoF Object Pose Estimation with Lightweight Transformers","created":"2026-08-15","cited_by_count":0,"area":null},{"id":"2608.25495","title":"Pose-Anchored Optical Flow for Low-Latency Human Action Anticipation in Human-Robot Teaming","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2608.30521","title":"MEOM: Multi-View Expected-OKS Maximization for Human Pose Triangulation","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.03569","title":"Occlusion-Robust Multimodal Emotion Recognition in VR via Fusion of Facial Images and EMG","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2609.08013","title":"A Black-Box Adversarial Attack on Human Pose Estimation and Keypoint-Based Action Recognition Models","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2609.12155","title":"Single-Query Person-Centric Bimanual Hand-Object Interaction Detection","created":"2026-09-10","cited_by_count":0,"area":null},{"id":"2609.18634","title":"GenStream: Semantic Streaming Framework for Generative Reconstruction of Human-centric Media","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2609.20178","title":"MTF-Net: Multi-Modal Temporal Feature Fusion Network for Pedestrian Intention Prediction","created":"2026-07-24","cited_by_count":0,"area":null},{"id":"2610.13549","title":"ELMA: Benchmarking Anaphoric Compositions for Long-Term Text-to-Motion Generation","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.19494","title":"Robust Real-Time Monocular Human Pose Estimation with Insole-Based Sensor Fusion","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}