AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Track2Act: Predicting Point Tracks from Internet Videos enables Generalizable Robot Manipulation

Homanga Bharadhwaj, Roozbeh Mottaghi, Abhinav Gupta, Shubham Tulsiani

ECCV 2024 · Reinforcement learning › Visual and representation RL · approach: Dexterous manipulation transfer · 105 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
predict point tracks instead of flow or generated video for goal-conditioned motion predictionTrack2Act track prediction · EpicKitchenstrack AUC Delta: 0.21 (Flow) / 0.30 (Video) -> 0.67Improved
add residual policy on top of open-loop plan (ablation)Track2Act · Robot manipulation, MGsuccess rate: 35% -> 70%Improved
add residual policy on top of open-loop plan (ablation)Track2Act · Robot manipulation, TGsuccess rate: 25% -> 40%Improved
predict residuals over the open-loop plan rather than actions directly (ablation)Track2Act residual policy · Robot manipulation, CGsuccess rate: 30% -> 55%Improved
predict residuals over the open-loop plan rather than actions directly (ablation)Track2Act residual policy · Robot manipulation, MGsuccess rate: 70% -> 70%No clear effect
use web-video-derived track plans instead of goal-conditioned BCTrack2Act · Robot manipulation, TGsuccess rate: 0% -> 40%Improved
use track-based plan instead of hand-object mask conditioningTrack2Act · Robot manipulation, MGsuccess rate: 70% -> 70%No clear effect
use track-based plan instead of hand-object mask conditioningTrack2Act · Robot manipulation, CGsuccess rate: 25% -> 55%Improved

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