AI Paper Atlas

Research map / Label-efficient and robust learning / Semi-supervised learning

Real-World Point Tracking with Verifier-Guided Pseudo-Labeling

Görkay Aydemir, Fatma Güney, Weidi Xie

CVPR 2026 · Label-efficient and robust learning › Semi-supervised learning · approach: Pseudo-labeling for specialized tasks · 0 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
use verifier-guided per-frame selection instead of random teacher selection (5 teachers) (ablation)pseudo-label generation / inference ensemble · TAP-Vid DAVISdelta_avg: 77.7 -> 81.1Improved
use verifier-guided per-frame selection instead of random teacher selection (5 teachers) (ablation)pseudo-label generation / inference ensemble · RoboTAPdelta_avg: 78.0 -> 83.1Improved
add teacher D to teachers {A,B,C} (ablation)verifier · TAP-Vid DAVISdelta_avg: 80.6 -> 80.8Improved
add more teachers (3 to 5) (ablation)verifier · RoboTAPdelta_avg: 81.8 -> 83.1Improved
add synthetic data to real-only fine-tuning without schedule (ablation)Track-On-R fine-tuning · EgoPointsdelta_avg: 66.9 -> 65.6Hurt
add synthetic data to real-only fine-tuning without schedule (ablation)Track-On-R fine-tuning · EgoPointsOA: 90.2 -> 90.7Improved
add loss-weight schedule increasing real-sample weight to mixed training (ablation)Track-On-R fine-tuning · EgoPointsdelta_avg: 65.6 -> 67.3Improved
add schedule and synthetic mix compared with real-only (ablation)Track-On-R fine-tuning · TAP-Vid DAVISdelta_avg: 80.3 -> 80.3No clear effect
fine-tune Track-On2 with verifier-guided pseudo-labels on real videosTrack-On2 · EgoPointsdelta_avg: 61.7 -> 67.3Improved
fine-tune Track-On2 with verifier-guided pseudo-labels on real videosTrack-On2 · RoboTAPAJ: 68.1 -> 70.9Improved
fine-tune Track-On2 with verifier-guided pseudo-labels on real videosTrack-On2 · TAP-Vid KineticsAJ: 55.3 -> 57.8Improved
fine-tune Track-On2 with verifier-guided pseudo-labels on real videosTrack-On2 · TAP-Vid DAVISAJ: 67.0 -> 68.1Improved

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