{"total":38,"rows":[{"id":"2407.06886","title":"Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AI","created":"2024-07-09","cited_by_count":179,"area":null},{"id":"2411.18941","title":"Revealing Key Details to See Differences: A Novel Prototypical Perspective for Skeleton-based Action Recognition","created":"2024-11-28","cited_by_count":29,"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":"2406.06907","title":"SignMusketeers: An Efficient Multi-Stream Approach for Sign Language Translation at Scale","created":"2024-06-11","cited_by_count":19,"area":null},{"id":"2412.09220","title":"USDRL: Unified Skeleton-Based Dense Representation Learning with Multi-Grained Feature Decorrelation","created":"2024-12-12","cited_by_count":16,"area":null},{"id":"2401.00897","title":"Masked Modeling for Self-supervised Representation Learning on Vision and Beyond","created":"2023-12-31","cited_by_count":13,"area":null},{"id":"2508.12586","title":"Foundation Model for Skeleton-Based Human Action Understanding","created":"2025-08-18","cited_by_count":11,"area":null},{"id":"2404.15806","title":"Where to Mask: Structure-Guided Masking for Graph Masked Autoencoders","created":"2024-04-24","cited_by_count":7,"area":null},{"id":"2410.20349","title":"Idempotent Unsupervised Representation Learning for Skeleton-Based Action Recognition","created":"2024-10-27","cited_by_count":7,"area":null},{"id":"2402.00290","title":"MEIA: Multimodal Embodied Perception and Interaction in Unknown Environments","created":"2024-02-01","cited_by_count":5,"area":null},{"id":"2406.02978","title":"Self-Supervised Skeleton-Based Action Representation Learning: A Benchmark and Beyond","created":"2024-06-05","cited_by_count":5,"area":null},{"id":"2501.09411","title":"Towards Robust and Realistic Human Pose Estimation via WiFi Signals","created":"2025-01-16","cited_by_count":5,"area":null},{"id":"2505.23012","title":"Spatio-Temporal Joint Density Driven Learning for Skeleton-Based Action Recognition","created":"2025-05-29","cited_by_count":4,"area":null},{"id":"2407.10935","title":"STARS: Self-supervised Tuning for 3D Action Recognition in Skeleton Sequences","created":"2024-07-15","cited_by_count":3,"area":null},{"id":"2411.00128","title":"Muscles in Time: Learning to Understand Human Motion by Simulating Muscle Activations","created":"2024-10-31","cited_by_count":3,"area":null},{"id":"2605.17179","title":"iMiGUE-3K: A Large-Scale Benchmark for Micro-Gesture Analysis with Self-Supervised Learning","created":"2026-05-16","cited_by_count":3,"area":null},{"id":"2401.00921","title":"Skeleton2vec: A Self-supervised Learning Framework with Contextualized Target Representations for Skeleton Sequence","created":"2024-01-01","cited_by_count":2,"area":null},{"id":"2406.05773","title":"Scalable and Generalizable Correspondence Pruning via Geometry-Consistent Pre-training","created":"2024-06-09","cited_by_count":2,"area":null},{"id":"2407.01397","title":"Mask and Compress: Efficient Skeleton-based Action Recognition in Continual Learning","created":"2024-07-01","cited_by_count":2,"area":null},{"id":"2404.11554","title":"Predicting Long-horizon Futures by Conditioning on Geometry and Time","created":"2024-04-17","cited_by_count":1,"area":null},{"id":"2405.10642","title":"Hi-GMAE: Hierarchical Graph Masked Autoencoders","created":"2024-05-17","cited_by_count":1,"area":null},{"id":"2506.20795","title":"How do Foundation Models Compare to Skeleton-Based Approaches for Gesture Recognition in Human-Robot Interaction?","created":"2025-06-25","cited_by_count":1,"area":null},{"id":"2512.21064","title":"Multimodal Skeleton-Based Action Representation Learning via Decomposition and Composition","created":"2025-12-24","cited_by_count":1,"area":null},{"id":"2512.23860","title":"Lifelong Domain Adaptive 3D Human Pose Estimation","created":"2025-12-29","cited_by_count":1,"area":null},{"id":"2605.22715","title":"AnyMo: Geometry-Aware Setup-Agnostic Modeling of Human Motion in the Wild","created":"2026-05-21","cited_by_count":1,"area":null},{"id":"2311.10873","title":"Multi-entity Video Transformers for Fine-Grained Video Representation Learning","created":"2023-11-17","cited_by_count":0,"area":null},{"id":"2409.17951","title":"Spatial Hierarchy and Temporal Attention Guided Cross Masking for Self-supervised Skeleton-based Action Recognition","created":"2024-09-26","cited_by_count":0,"area":null},{"id":"2503.12519","title":"Multi Activity Sequence Alignment via Implicit Clustering","created":"2025-03-16","cited_by_count":0,"area":null},{"id":"2508.12948","title":"MaskSem: Semantic-Guided Masking for Learning 3D Hybrid High-Order Motion Representation","created":"2025-08-18","cited_by_count":0,"area":null},{"id":"2512.16504","title":"Skeleton-Snippet Contrastive Learning with Multiscale Feature Fusion for Action Localization","created":"2025-12-18","cited_by_count":0,"area":null},{"id":"2601.16694","title":"Affinity Contrastive Learning for Skeleton-based Human Activity Understanding","created":"2026-01-23","cited_by_count":0,"area":null},{"id":"2602.06251","title":"ASMa: Asymmetric Spatio-temporal Masking for Skeleton Action Representation Learning","created":"2026-02-05","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":"2603.13410","title":"Bridging the Visual-to-Physical Gap: Physically Aligned Representations for Fall Risk Analysis","created":"2026-03-12","cited_by_count":0,"area":null},{"id":"2603.19546","title":"Subspace Kernel Learning on Tensor Sequences","created":"2026-03-20","cited_by_count":0,"area":null},{"id":"2604.01997","title":"GenGait: A Transformer-Based Model for Human Gait Anomaly Detection and Normative Twin Generation","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2604.28173","title":"Action Motifs: Self-Supervised Hierarchical Representation of Human Body Movements","created":"2026-04-30","cited_by_count":0,"area":null},{"id":"2609.35444","title":"DiMoP: Diffusion-Driven Motion Representation Learning With Frame-Level Pseudo-Classification for Skeleton-Based Action Recognition","created":"2026-09-28","cited_by_count":0,"area":null}],"next_cursor":null}