AI RESEARCH
Leveraging Synthetic Data for Enhancing Egocentric Hand-Object Interaction Detection
arXiv CS.CV
•
ArXi:2603.29733v1 Announce Type: new In this work, we explore the role of synthetic data in improving the detection of Hand-Object Interactions from egocentric images. Through extensive experimentation and comparative analysis on VISOR, EgoHOS, and ENIGMA-51 datasets, our findings nstrate the potential of synthetic data to significantly improve HOI detection, particularly when real labeled data are scarce or unavailable.