AI Paper Atlas

Research map / Video / Video-language understanding

Scaling Egocentric Vision: The EPIC-KITCHENS Dataset

Dima Damen, Hazel Doughty, Giovanni Maria Farinella, Sanja Fidler, Antonino Furnari, Evangelos Kazakos, Davide Moltisanti, Jonathan Munro, Toby Perrett, Will Price, Michael Wray

ECCV 2018 · Video › Video-language understanding · approach: Egocentric video understanding

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
fuse spatial and temporal streams in TSN for action recognitionTSN · EPIC-KITCHENS action recognition S1 (seen kitchens)top-1 action accuracy: 19.86 -> 20.54Improved
fuse spatial and temporal streams in TSN for action recognitionTSN · EPIC-KITCHENS action recognition S2 (unseen kitchens)top-1 action accuracy: 10.11 -> 10.89Improved
use TSN (3 segments) instead of 2SCNN (1 segment)action recognition baseline · EPIC-KITCHENS action recognition S1 (seen kitchens)top-1 action accuracy: 13.23 -> 20.54Improved
test on unseen kitchens instead of seen kitchensTSN (FUSION) · EPIC-KITCHENS action recognitiontop-1 action accuracy: 20.5% -> 10.9%Hurt
test on unseen kitchens instead of seen kitchensFaster R-CNN · EPIC-KITCHENS object detection, all classesmAP at IoU>0.5: 35.41 -> 33.11No clear effect
evaluate few-shot instead of many-shot classesFaster R-CNN · EPIC-KITCHENS object detection S1mAP at IoU>0.5: 38.81 -> 20.72Hurt
raise IoU threshold from 0.5 to 0.75Faster R-CNN · EPIC-KITCHENS object detection S1, all classesmAP: 35.41 -> 8.69Hurt
anticipate next action instead of recognising itTSN (RGB) · EPIC-KITCHENS S1top-1 action accuracy: 19.86 -> 06.00Hurt
add flow stream and fusion to RGB TSN for anticipationTSN (RGB) · EPIC-KITCHENS action anticipation S1top-1 action accuracy: 06.00 -> 04.62Hurt
use TSN instead of 2SCNN for anticipationaction anticipation baseline · EPIC-KITCHENS action anticipation S1top-1 action accuracy: 04.32 -> 06.00Improved
lengthen observation time tau_o beyond 1sTSN anticipation · EPIC-KITCHENS action anticipationaccuracyHurt

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