AI Paper Atlas

Research map / Video / Action recognition

LogFA: Efficient Feature-Space Data Augmentation for Egocentric Temporal Action Segmentation

Zijia Lu, Ehsan Elhamifar

ECCV 2026 · Video › Action recognition · approach: Action anticipation and latent actions

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 local text-guided augmentation (all four caption types) (ablation)FACT · EgoPER Coffee (3 training videos)F1@50: 32.2 -> 38.4Improved
add type3 texture/color caption changes vs type1 rephrasing (ablation)FACT · EgoPER Coffee (3 training videos)F1@50: 34.1 -> 36.8Improved
switch VLM backbone from SigLIP2 to EgoVLP (ablation)LogFA · EgoPER Coffee (3 training videos)F1@50: 38.4 -> 36.7Hurt
add dropout layers to base model (ablation)FACT · EgoPER Coffee (3 training videos)F1@50: 30.2 -> 32.2Improved
use GDAG instead of DAG for global augmentation (ablation)FACT · EgoProceL (3 training videos), GDAG studyF1@50: 28.8 -> 32.2Improved
generate GDAG with Qwen3-30B instead of GPT-5o (ablation)LogFA · EgoProceL (3 training videos), GDAG studyF1@50: 32.2 -> 31.7No clear effect
add LogFA (local + global)FACT · EgoPER in-domain videosF1@50: 64.1 -> 70.7Improved
add LogFA (local + global)FACT · EgoPER out-of-domain videosF1@50: 47.7 -> 57.0Improved
image transformation augmentationFACT · EgoPER out-of-domain videosF1@50: 47.7 -> 50.0Improved
add LogFA with MS-TCN++ backboneMS-TCN++ · EgoPER all tasks (MS-TCN++)F1@50: 54.5 -> 63.3Improved
add LogFA on EgoProceLFACT · EgoProceL (3 training videos)F1@50: 28.8 -> 35.0Improved
add LogFA with all training videosFACT · EgoPER (all training videos)F1@50: 63.1 -> 74.9Improved

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