AI Paper Atlas

Research map / Video / Action recognition

EgoPCA: A New Framework for Egocentric Hand-Object Interaction Understanding

Yue Xu, Yong-Lu Li, Zhemin Huang, Michael Xu Liu, Cewu Lu, Yu-Wing Tai, Chi-Keung Tang

ICCV 2023 · Video › Action recognition · approach: Disentangled action recognition · 10 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
pre-train on balanced One4All-P-50K instead of a random 50K subset of the same sources (ablation)EgoPCA full model · EPIC-100 (one-for-all)top-1 accuracy: 34.6 -> 41.8Improved
add SVSA auxiliary loss (ablation)EgoPCA full model · Ego4D-ARtop-1 accuracy: 16.8 -> 17.6Improved
add counterfactual reasoning loss (ablation)EgoPCA full model · EGTEAtop-1 accuracy: 70.3 -> 70.8Improved
add linear probing (ablation)EgoPCA full model · Ego4D-ARtop-1 accuracy: 16.8 -> 17.6Improved
add 10% samples chosen by unified property selectionEgoPCA finetuning · Ego4D-ARtop-1 accuracy: 17.6 -> 18.5Improved
replace 20% of EGTEA training data with selected samples (ablation)EgoPCA finetuning · EGTEA Gaze+top-1 accuracy: 70.8 -> 68.4Hurt
replace 5-10% of samples with selected samples (ablation)EgoPCA finetuning · Ego4D-ARtop-1 accuracy: 17.6 -> 17.9 (-10% => +10%)Mixed
select added data by camera motion/hand location/object location instead of semantics or blurriness (ablation)EGTEA Gaze+ split 3 · EGTEA Gaze+ split 3 (+10%)top-1 accuracy: 70.1 (semantics) -> 71.0 (hand location)Improved
use unified weighted property criterion instead of random addition (ablation)EGTEA Gaze+ split 3 · EGTEA Gaze+ split 3 (+20%)top-1 accuracy: 69.6 -> 71.2Improved
pre-train on One4All-P instead of Kinetics-400 (ActionCLIP)ActionCLIP · EPIC-100 (one-for-all)top-1 accuracy: 8.8 -> 33.8Improved
increase pre-train set from 20K to 50K (ablation)EgoPCA full model · Ego4D-AR (one-for-all)top-1 accuracy: 6.6 (20K), 6.0 (30K), 7.2 (50K)Mixed

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