AI Paper Atlas

Research map / Video / Action recognition

Path-JEPA: Path Signature Based Predictive Learning for Skeleton Action Recognition

Ashutosh Singh, Ashish Singh

ECCV 2026 · Video › Action recognition · approach: Skeleton-based action recognition · 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
add local window signatures to global signatures (ablation)Path-JEPA joint tokens · NTU60 X-Sub (linear eval)accuracy (%): 84.4 -> 85.8Improved
add edge tokens (ablation)Path-JEPA · NTU60 X-Sub (linear eval)accuracy (%): 85.8 -> 86.4Improved
add chain tokens (ablation)Path-JEPA · NTU60 X-Sub (linear eval)accuracy (%): 86.4 -> 87.6Improved
add global signature to local-only tokens (ablation)Path-JEPA · NTU60 X-Sub (linear eval)accuracy (%): 83.3 -> 85.8Improved
signature-augmented masking instead of random joint masking (ablation)Path-JEPA · NTU60 X-Sub (linear eval)accuracy (%): 84.1 -> 86.3Improved
add kinematic subtree expansion to masking (ablation)Path-JEPA · NTU60 X-Sub (linear eval)accuracy (%): 86.3 -> 87.6Improved
vary mask ratio from default (about 20-25%) to 10% or 40% (ablation)Path-JEPA · NTU60 X-Sub (linear eval)accuracy (%): 87.6 -> 85.1 (10%), 84.9 (40%)Hurt
use path-signature targets instead of S-JEPA latent targets (frame-rate robustness)Path-JEPA · NTU60 X-Sub (15fps resampled)accuracy (%): 82.4 -> 87.1Improved
Path-JEPA pretraining vs S-JEPA, 1% labelsPath-JEPA · NTU60 X-Sub (semi-supervised, 1% labels)accuracy (%): 67.5 -> 72.2Improved
Path-JEPA pretraining vs S-JEPA, 60% labelsPath-JEPA · NTU60 X-Sub (semi-supervised, 60% labels)accuracy (%): 92.1 -> 92.1No clear effect
Path-JEPA vs S-JEPA, transfer to PKU-IIPath-JEPA · PKU-II transfer (pretrain NTU60)accuracy (%): 71.4 -> 72.6Improved

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