AI Paper Atlas

Research map / Video / Action recognition

Ego-Only: Egocentric Action Detection without Exocentric Transferring

Huiyu Wang, Mitesh Kumar Singh, Lorenzo Torresani

ICCV 2023 · Video › Action recognition · approach: Temporal action segmentation · 31 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
replace K400 exocentric supervised pretraining with Ego4D MAE pretraining (ablation)egocentric action detection · Ego4D MQ valaverage mAP: 13.9 -> 16.3Improved
add MAE pretraining before temporal segmentation finetuning (ablation)Ego-Only · Ego4D MQ valaverage mAP: 4.2 -> 16.3Improved
add egocentric temporal segmentation finetuning to frozen MAE features (ablation)Ego-Only · Ego4D MQ valaverage mAP: 7.8 -> 16.3Improved
pretrain MAE on Ego4D instead of Kinetics-400 (ablation)Ego-Only · Ego4D MQ valaverage mAP: 13.4 -> 16.3Improved
add joint ego-exo MAE pretraining on K400 and Ego4D (ablation)Ego-Only · Ego4D MQ valaverage mAP: 16.3 -> 16.0No clear effect
add joint ego-exo finetuning with 515K labels (ablation)Ego-Only · EPIC-Kitchens-100 detectionverb mAP: 29.0 -> 28.4No clear effect
scale exocentric pretraining from K400 to K600 (ablation)exocentric transferring · EPIC-Kitchens-100 detectionverb mAP: 28.0 -> 27.1Hurt
increase MAE pretraining data from MQ clips to all Ego4D videos (ablation)Ego-Only · Ego4D MQ valaverage mAP: 14.5 -> 15.5Improved
use per-class reweighting instead of per-instance reweighting (ablation)Ego-Only · Ego4D MQ valaverage mAP: 16.3 -> 14.4Hurt
resample action centers instead of per-instance reweighting (ablation)Ego-Only · Ego4D MQ valaverage mAP: 16.3 -> 16.3No clear effect
scale backbone from ViT-B to ViT-L (ablation)Ego-Only · Ego4D MQ valaverage mAP: 16.3 -> 17.9Improved
concatenate features from last few blocksfrozen MAE features · Ego4D MQ valaverage mAPNo clear effect

Later papers that compared with this method

1 later accepted paper reports EgoOnly as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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