AI Paper Atlas

Research map / Video / Action recognition

Self-Regulated Learning for Egocentric Video Activity Anticipation

Zhaobo Qi, Shuhui Wang, Chi Su, Li Su, Qingming Huang, Qi Chuan Tian

TPAMI 2021 · Video › Action recognition · approach: Disentangled action recognition · 67 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 representation revision (contrastive loss) to baseline (ablation)recursive GRU baseline · EPIC-Kitchens val, activity, tau_a=1stop-5 accuracy: 29.18 -> 30.27Improved
add dynamic reattending to baseline (ablation)recursive GRU baseline · EPIC-Kitchens val, activity, tau_a=1stop-5 accuracy: 29.18 -> 30.71Improved
add semantic context exploration to baseline (ablation)recursive GRU baseline · EPIC-Kitchens val, activity, tau_a=1stop-5 accuracy: 29.18 -> 30.39Improved
add all three components (full SRL) to baseline (ablation)recursive GRU baseline · EPIC-Kitchens val, activity, tau_a=1stop-5 accuracy: 29.18 -> 31.68Improved
add representation revision to reattending plus semantic context (ablation)SRL · EPIC-Kitchens val, activity, tau_a=1stop-5 accuracy: 30.77 -> 31.68Improved
sample negatives from all videos instead of same video (ablation)SRL contrastive loss · EPIC-Kitchens val, activity, tau_a=1stop-5 accuracy: 30.15 -> 30.31No clear effect
vary number of negative samples N (32 to 256) (ablation)SRL contrastive loss · EPIC-Kitchens val, activity, tau_a=1stop-5 accuracy: 30.15 -> 30.19No clear effect
use GRU instead of average pooling for aggregation (ablation)SRL · EPIC-Kitchens val, activity, tau_a=1stop-5 accuracy: 31.03 -> 31.68Improved
use GRU instead of LSTM for aggregation (ablation)SRL · EPIC-Kitchens val, activity, tau_a=1stop-5 accuracy: 30.79 -> 31.68Improved
add OBJ features to RGB (ablation)SRL · EPIC-Kitchens val, activity, tau_a=1stop-5 accuracy: 31.68 -> 35.32Improved
replace RU(Late) with SRL(Late) at 0.25slate-fusion model · EPIC-Kitchens val, activity, tau_a=0.25stop-5 accuracy: 37.61 -> 40.21Improved
add representation revision to baseline (ablation)recursive GRU baseline · 50 Salads (observed 20%, predict 10%)accuracy: 22.96 -> 27.87Improved

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