AI Paper Atlas

Research map / Video / Action recognition

EAST: Early Action Prediction Sampling Strategy with Token Masking

Iva Sović, Ivan Martinović, Marin Oršić

ICLR 2026 · Video › Action recognition · approach: Action anticipation and latent actions · 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
train with randomly sampled observation ratio (EAST sampling) instead of standard classification finetuning (ablation)VideoMAE ViT-B/16 · SSv2 (rho=0.1)top-1 accuracy (%): 9.9 -> 23.9Improved
sampling strategy at high observation ratio (ablation)VideoMAE ViT-B/16 · SSv2 (rho=0.9)top-1 accuracy (%): 63.4 -> 60.7Hurt
add oracle-feature loss to encoder-only model (ablation)EAST_E · SSv2 (average)top-1 accuracy (%): 44.8 -> 46.3Improved
add oracle-feature loss to encoder-decoder model (ablation)EAST · SSv2 (average)top-1 accuracy (%): 46.2 -> 46.9Improved
add transformer decoder to encoder with both losses (ablation)EAST_E · SSv2 (average)top-1 accuracy (%): 46.3 -> 46.9Improved
use direct decoding instead of autoregressive decoding (ablation)EAST · SSv2 (rho=0.5)top-1 accuracy (%): 48.2 -> 49.0Improved
add L2 feature alignment loss (ablation)EAST · SSv2 (rho=0.5)top-1 accuracy (%): 49.0 -> 48.2Hurt
use shared classifier instead of separate heads (ablation)EAST · SSv2 (rho=0.5)top-1 accuracy (%): 48.3 -> 49.0Improved
use 4-layer decoder instead of 1 or 12 layers (ablation)EAST · UCF101 (average)top-1 accuracy (%): 94.1 -> 94.9Improved
use 4-layer decoder instead of 1 or 12 layers (ablation)EAST · SSv2 (average)top-1 accuracy (%): 46.8 -> 46.9No clear effect
train one model for all observation ratios instead of one per ratio (ablation)EAST · all datasetsaccuracyNo clear effect
difference token masking at k=0.5 for efficiency (ablation)EAST · UCF101 training epochseconds per epoch: 180 -> 80Improved

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