AI Paper Atlas

Research map / Label-efficient and robust learning / Self-supervised and contrastive

Learning to LEAP: Efficient Dense Point Tracking by Focusing Where It Matters

Chenzhi Zhao, Wufan Wang, Bo Zhang, Wendong Wang

AAAI 2026 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Invariance-based self-supervised learning · 2 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 CSA to GMRW baseline (ablation)GMRW · TAP-Vid Kubric (direct)AJ: 51.4 -> 54.9Improved
add PkT to GMRW baseline (ablation)GMRW · TAP-Vid Kubric (direct)AJ: 51.4 -> 54.0Improved
add adaptive training scheme on top of CSA+PkT (ablation)LEAP-Track · TAP-Vid Kubric (direct)AJ: 55.3 -> 57.2Improved
use direct instead of chained evaluation (ablation)LEAP-Track · TAP-Vid KubricAJ: 44.1 -> 57.2Improved
reduce evaluation stride from 2 to 1 (ablation)LEAP-Track · TAP-Vid Kubric (direct)AJ: 57.2 -> 58.6Improved
increase evaluation stride from 2 to 4 (ablation)LEAP-Track · TAP-Vid Kubric (direct)AJ: 57.2 -> 48.4Hurt
increase CSA key proportion beyond 75% (ablation)LEAP-Track · TAP-Vid KubricAJ: slight degradation after peak at 75%Hurt
increase PkT max neighbor size k beyond 64 (ablation)LEAP-Track · TAP-Vid KubricAJ: degrades after peak at k = 64Hurt
sparse attention and k-NN walk in training (training throughput)GMRW · Kinetics trainingclips/s: 0.3923 -> 0.5806Improved
LEAP-Track vs GMRW direct on DAVISGMRW · TAP-Vid DAVIS (direct)AJ: 30.3 -> 32.1Improved
LEAP-Track vs Flow-Walk on RGB-StackingFlow-Walk · TAP-Vid RGB-Stacking (direct)AJ: 66.3 -> 58.8Hurt

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