AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Leveraging Synthetic Data for Enhancing Egocentric Hand-Object Interaction Detection

Rosario Leonardi, Antonino Furnari, Francesco Ragusa, Giovanni Maria Farinella

IJCV 2026 · Detection and segmentation › Open-set and few-shot detection · approach: Human-object interaction detection · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add unsupervised domain adaptation with unlabeled real data to synthetic trainingVISOR HOS · VISOR valOverall AP (Hand+Object): 09.88 -> 33.33Improved
add synthetic data with semi-supervised domain adaptation (SSDA) to 10% real labelsVISOR HOS · VISOR val (10% real labels)Overall AP (Hand+Object): 38.55 -> 44.22Improved
add SSDA to 25% real labelsVISOR HOS · VISOR val (25% real labels)Overall AP (Hand+Object): 37.90 -> 45.55Improved
add SSDA to 50% real labelsVISOR HOS · VISOR val (50% real labels)Overall AP (Hand+Object): 38.15 -> 46.47Improved
add synthetic pretraining without domain adaptation to 10% real labelsVISOR HOS · VISOR val (10% real labels)Overall AP (Hand+Object): 38.55 -> 37.62Hurt
add synthetic pretraining without adaptation, 100% real labelsVISOR HOS · VISOR val (100% real labels)Overall AP (Hand+Object): 45.33 -> 44.52Hurt
add FSDA with synthetic data to full real dataVISOR HOS · VISOR val (100% real labels)Overall AP (Hand+Object): 45.33 -> 46.48Improved
use ConvNeXt-S instead of ResNet101 backboneFSDA · VISOR val (100% real labels)Overall AP (Hand+Object): 46.48 -> 48.36Improved
use Adaptive Teacher instead of Mean Teacher for SSDASSDA · VISOR val (25% real labels)Overall AP (Hand+Object): 43.69 -> 45.55Improved
align synthetic objects to target objects (ablation)UDA (~5k images) · VISOR valOverall AP (Hand+Object): 31.52 -> 32.60Improved
align synthetic grasps to target grasps (ablation)UDA (~5k images) · VISOR valOverall AP (Hand+Object): 31.52 -> 31.84Improved
align synthetic environments to target environments (ablation)UDA (~5k images) · VISOR valOverall AP (Hand+Object): 31.52 -> 31.59No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy