Rescaling Egocentric Vision

Dima Damen, Hazel Doughty, Giovanni Maria Farinella, Antonino Furnari, Evangelos Kazakos +6 more
6/23/2020
cs.CVcs.LG

Official code: epic-kitchens/epic-kitchens-100-annotations (173 stars, last commit 2022-08-01). 1 more implementation below.

Abstract

This paper introduces the pipeline to extend the largest dataset in egocentric vision, EPIC-KITCHENS. The effort culminates in EPIC-KITCHENS-100, a collection of 100 hours, 20M frames, 90K actions in 700 variable-length videos, capturing long-term unscripted activities in 45 environments, using head-mounted cameras. Compared to its previous version, EPIC-KITCHENS-100 has been annotated using a novel pipeline that allows denser (54% more actions per minute) and more complete annotations of fine-grained actions (+128% more action segments). This collection enables new challenges such as action detection and evaluating the "test of time" - i.e. whether models trained on data collected in 2018 can generalise to new footage collected two years later. The dataset is aligned with 6 challenges: action recognition (full and weak supervision), action detection, action anticipation, cross-modal retrieval (from captions), as well as unsupervised domain adaptation for action recognition. For each challenge, we define the task, provide baselines and evaluation metrics

View on arXivView PDF

Code Implementations(2)

epic-kitchens/epic-kitchens-100-annotationsOfficial100%

:plate_with_cutlery: Annotations for the public release of the EPIC-KITCHENS-100 dataset

17334PythonMay 4, 20204 years agoNOASSERTION
epic-kitchens/epic-kitchens-100-narratorOfficial100%

Video narrator written in Python/GTK using vlc-lib

265CMake, ShellMay 1, 20194 years ago

Similar Papers

Action Scene Graphs for Long-Form Understanding of Egocentric Videos

87% match1 repo502023

Ego4D: Around the World in 3,000 Hours of Egocentric Video

86% match1 repo6562021

X-LeBench: A Benchmark for Extremely Long Egocentric Video Understanding

85% match2 repos102025

The Visual Experience Dataset: Over 200 Recorded Hours of Integrated Eye Movement, Odometry, and Egocentric Video

85% match1 repo2024

EgoXperience: Learning World-Grounded Egocentric Representations from Human Experience

85% match2026

Object Aware Egocentric Online Action Detection

85% match2024

Cite this paper

@article{damen2020rescaling,
  title  = {Rescaling Egocentric Vision},
  author = {Dima Damen and Hazel Doughty and Giovanni Maria Farinella and Antonino Furnari and Evangelos Kazakos and Jian Ma and Davide Moltisanti and Jonathan Munro and Toby Perrett and Will Price and Michael Wray},
  year   = {2020},
  eprint = {2006.13256},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/2006.13256}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2006.13256.svg)](https://codeofpaper.com/paper/2006.13256)

Discussion