{"total":18,"rows":[{"id":"2403.14852","title":"KeyPoint Relative Position Encoding for Face Recognition","created":"2024-03-21","cited_by_count":38,"area":null},{"id":"2404.00532","title":"LLMs are Good Action Recognizers","created":"2024-03-31","cited_by_count":37,"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":"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":"2404.18952","title":"CUE-Net: Violence Detection Video Analytics with Spatial Cropping, Enhanced UniformerV2 and Modified Efficient Additive Attention","created":"2024-04-27","cited_by_count":8,"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":"2406.18011","title":"Expressive Keypoints for Skeleton-based Action Recognition via Skeleton Transformation","created":"2024-06-26","cited_by_count":6,"area":null},{"id":"2407.19497","title":"Skeleton-based Group Activity Recognition via Spatial-Temporal Panoramic Graph","created":"2024-07-28","cited_by_count":6,"area":null},{"id":"2405.02961","title":"JOSENet: A Joint Stream Embedding Network for Violence Detection in Surveillance Videos","created":"2024-05-05","cited_by_count":2,"area":null},{"id":"2411.06553","title":"Extended multi-stream temporal-attention module for skeleton-based human action recognition (HAR)","created":"2024-11-10","cited_by_count":2,"area":null},{"id":"2306.09331","title":"Seeing the Pose in the Pixels: Learning Pose-Aware Representations in Vision Transformers","created":"2023-06-15","cited_by_count":0,"area":null},{"id":"2412.05386","title":"DIFEM: Key-points Interaction based Feature Extraction Module for Violence Recognition in Videos","created":"2024-12-06","cited_by_count":0,"area":null},{"id":"2511.10866","title":"Short-Window Sliding Learning for Real-Time Violence Detection via LLM-based Auto-Labeling","created":"2025-11-14","cited_by_count":0,"area":null},{"id":"2601.00369","title":"BHaRNet: Reliability-Aware Body-Hand Modality Expertized Networks for Fine-grained Skeleton Action Recognition","created":"2026-01-01","cited_by_count":0,"area":null},{"id":"2603.05604","title":"From Decoupled to Coupled: Robustness Verification for Learning-based Keypoint Detection with Joint Specifications","created":"2026-03-05","cited_by_count":0,"area":null},{"id":"2604.02946","title":"Learning from Synthetic Data via Provenance-Based Input Gradient Guidance","created":"2026-04-03","cited_by_count":0,"area":null},{"id":"2604.03590","title":"SBF: An Effective Representation to Augment Skeleton for Video-based Human Action Recognition","created":"2026-04-04","cited_by_count":0,"area":null},{"id":"2608.25701","title":"Skeleton-based Zero-Shot Spatio-Temporal Action Localization via Weakly-Supervised Pretraining","created":"2026-08-26","cited_by_count":0,"area":null}],"next_cursor":null}