AI Paper Atlas

Research map / Reinforcement learning / Imitation learning

ERA: Expert Retrieval and Assembly for Early Action Prediction

Lin Geng Foo, Tianjiao Li, Hossein Rahmani, Qiuhong Ke, Jun Liu

ECCV 2022 · Reinforcement learning › Imitation learning · approach: Behavior cloning theory and models · 23 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 ERA modules (expert retrieval and assembly) to the backbone (ablation)2s-AGCN baseline · NTU60AUC: 66.43 -> 71.62Improved
add Expert Learning Rate Optimization (ELRO) (ablation)ERA-Net w/o ELRO · NTU60AUC: 71.62 -> 73.87Improved
add ELRO (ablation)ERA-Net w/o ELRO · NTU60 (20% observed)accuracy: 43.94 -> 53.98Improved
add ELRO (ablation)ERA-Net w/o ELRO · UCF101AUC: 92.51 -> 93.64Improved
add ERA modules2s-AGCN baseline · NTU120AUC: 50.03 -> 57.02Improved
add ERA modules3D ResNeXt-101 baseline · UCF101AUC: 89.30 -> 93.64Improved
use 20:80 expert to non-expert split instead of all non-experts (0:100) (ablation)ERA module · NTU60AUC: 66.43 -> 73.87Improved
use 20:80 split instead of 100:0 experts only (ablation)ERA module · NTU60AUC: 70.12 -> 73.87Improved
increase Expert Bank size M from 2 to 5 (ablation)ERA module · NTU60AUC: 71.55 -> 73.87Improved
increase Expert Bank size M from 5 to 10 (ablation)ERA module · NTU60AUC: 73.87 -> 73.86No clear effect
replace more convolutional layers with ERA (25% to 100%) (ablation)ERA-Net · NTU60AUC: 73.87 -> 73.81No clear effect
set similarity loss weight to 0.1 instead of 0.05 (ablation)ERA-Net · NTU60AUC: 72.92 -> 73.87Improved

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