{"total":15,"rows":[{"id":"2309.12172","title":"SANPO: A Scene Understanding, Accessibility and Human Navigation Dataset","created":"2023-09-21","cited_by_count":10,"area":null},{"id":"2401.15900","title":"MV2MAE: Multi-View Video Masked Autoencoders","created":"2024-01-29","cited_by_count":6,"area":null},{"id":"2408.13126","title":"CathAction: A Benchmark for Endovascular Intervention Understanding","created":"2024-08-23","cited_by_count":6,"area":null},{"id":"2510.04899","title":"Human Behavior Atlas: Benchmarking Unified Psychological and Social Behavior Understanding","created":"2025-10-06","cited_by_count":6,"area":null},{"id":"2403.03309","title":"Learning Zero-Shot Material States Segmentation, by Implanting Natural Image Patterns in Synthetic Data","created":"2024-03-05","cited_by_count":2,"area":null},{"id":"2406.01073","title":"Understanding the Cross-Domain Capabilities of Video-Based Few-Shot Action Recognition Models","created":"2024-06-03","cited_by_count":2,"area":null},{"id":"2506.03662","title":"Zero-Shot Temporal Interaction Localization for Egocentric Videos","created":"2025-06-04","cited_by_count":2,"area":null},{"id":"2506.09411","title":"Synthetic Human Action Video Data Generation with Pose Transfer","created":"2025-06-11","cited_by_count":2,"area":null},{"id":"2410.02152","title":"An Evaluation of Large Pre-Trained Models for Gesture Recognition using Synthetic Videos","created":"2024-10-03","cited_by_count":1,"area":null},{"id":"2504.02158","title":"UAVTwin: Neural Digital Twins for UAVs using Gaussian Splatting","created":"2025-04-02","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":"2510.09731","title":"Multi Camera Connected Vision System with Multi View Analytics: A Comprehensive Survey","created":"2025-10-10","cited_by_count":1,"area":null},{"id":"2501.10081","title":"Leveraging Confident Image Regions for Source-Free Domain-Adaptive Object Detection","created":"2025-01-17","cited_by_count":0,"area":null},{"id":"2601.14101","title":"Curriculum-Based Strategies for Efficient Cross-Domain Action Recognition","created":"2026-01-20","cited_by_count":0,"area":null},{"id":"2609.06876","title":"Novel Methods for Catheter and Guidewire Segmentation in X-ray Fluoroscopy under a Federated Learning Setting","created":"2026-09-06","cited_by_count":0,"area":null}],"next_cursor":null}