AI Paper Atlas

Research map / Video / Video-language understanding

Learning Procedural-Aware Video Representations Through State-Grounded Hierarchy Unfolding

Jinghan Zhao, Yifei Huang, Feng Lu

AAAI 2026 · Video › Video-language understanding · approach: Event and anomaly reasoning in video · 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 State stage after Step (Path-3 vs Path-2) (ablation)progressive pre-training · COIN, MLP headstep recognition acc: 43.06 -> 41.28Hurt
add return to Step after State (Path-5 vs Path-3) (ablation)progressive pre-training · COIN, MLP headstep forecasting acc: 34.35 -> 38.07Improved
add State layer with step-return (Path-5 vs Path-2) (ablation)progressive pre-training · COIN, MLP headstep recognition acc: 43.06 -> 44.54Improved
go from State directly back to Task (Path-4 vs Path-3) (ablation)progressive pre-training · COIN, MLP headtask recognition acc: 80.73 -> 77.74Hurt
add final Task stage after Path-5 (Path-6) (ablation)progressive pre-training · COIN, MLP headstep forecasting acc: 38.07 -> 36.94No clear effect
replace joint training with progressive pathway (ablation)TSS pre-training · COIN, MLP headstep forecasting acc: 29.79 -> 38.07Improved
progressive Path-5 vs fusing three level features by average pooling (ablation)TSS pre-training · COIN, MLP headstep forecasting acc: 36.88 -> 38.07Improved
use Path-5 instead of Paprikapretraining method · COIN, Transformer headstep forecasting acc: 38.93 -> 40.40Improved
use Path-5 instead of Paprikapretraining method · CrossTask, MLP headtask recognition acc: 89.65 -> 89.44Hurt
add Task step pretraining (ablation)adapter pretraining · COIN, MLP headtask recognition acc: 2.09 -> 82.45Improved

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