{"total":19,"rows":[{"id":"2311.17084","title":"DepthSSC: Monocular 3D Semantic Scene Completion via Depth-Spatial Alignment and Voxel Adaptation","created":"2023-11-28","cited_by_count":32,"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":"2411.11288","title":"Neuron: Learning Context-Aware Evolving Representations for Zero-Shot Skeleton Action Recognition","created":"2024-11-18","cited_by_count":13,"area":null},{"id":"2409.16709","title":"Pose-Guided Fine-Grained Sign Language Video Generation","created":"2024-09-25","cited_by_count":8,"area":null},{"id":"2506.00915","title":"3D Skeleton-Based Action Recognition: A Review","created":"2025-06-01","cited_by_count":6,"area":null},{"id":"2404.17381","title":"Frequency-Guided Multi-Level Human Action Anomaly Detection with Normalizing Flows","created":"2024-04-26","cited_by_count":2,"area":null},{"id":"2407.13750","title":"PO-GUISE+: Pose and object guided transformer token selection for efficient driver action recognition","created":"2024-07-18","cited_by_count":2,"area":null},{"id":"2502.13385","title":"SNN-Driven Multimodal Human Action Recognition via Sparse Spatial-Temporal Data Fusion","created":"2025-02-19","cited_by_count":2,"area":null},{"id":"2504.05700","title":"Pose-Aware Weakly-Supervised Action Segmentation","created":"2025-04-08","cited_by_count":2,"area":null},{"id":"2409.11119","title":"Multi-Cohort Framework with Cohort-Aware Attention and Adversarial Mutual-Information Minimization for Whole Slide Image Classification","created":"2024-09-17","cited_by_count":1,"area":null},{"id":"2502.16493","title":"Trunk-branch Contrastive Network with Multi-view Deformable Aggregation for Multi-view Action Recognition","created":"2025-02-23","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":"2512.03837","title":"Heatmap Pooling Network for Action Recognition from RGB Videos","created":"2025-12-03","cited_by_count":1,"area":null},{"id":"2601.08205","title":"FUME: Fused Unified Multi-Gas Emission Network for Livestock Rumen Acidosis Detection","created":"2026-01-13","cited_by_count":1,"area":null},{"id":"2405.15962","title":"Wearable-based behaviour interpolation for semi-supervised human activity recognition","created":"2024-05-24","cited_by_count":0,"area":null},{"id":"2507.00752","title":"Multi-Modal Graph Convolutional Network with Sinusoidal Encoding for Robust Human Action Segmentation","created":"2025-07-01","cited_by_count":0,"area":null},{"id":"2509.00692","title":"CascadeFormer: A Family of Two-stage Cascading Transformers for Skeleton-based Human Action Recognition","created":"2025-08-31","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":"2607.17342","title":"STAR: Skeletal Token Alignment and Rearrangement for Interaction Recognition","created":"2026-07-19","cited_by_count":0,"area":null}],"next_cursor":null}