Rescaling Egocentric Vision: Collection, Pipeline and Challenges for EPIC-KITCHENS-100

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...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:International journal of computer vision Jg. 130; H. 1; S. 33 - 55
Hauptverfasser: Damen, Dima, Doughty, Hazel, Farinella, Giovanni Maria, Furnari, Antonino, Kazakos, Evangelos, Ma, Jian, Moltisanti, Davide, Munro, Jonathan, Perrett, Toby, Price, Will, Wray, Michael
Format: Journal Article
Sprache:Englisch
Veröffentlicht: New York Springer US 01.01.2022
Springer
Springer Nature B.V
Schlagworte:
Activity recognition
Annotations
Artificial Intelligence
Computer Imaging
Computer Science
Datasets
Image Processing and Computer Vision
Kitchens
Pattern Recognition
Pattern Recognition and Graphics
Pipelines
Rescaling
Vision
Annotation quality
Egocentric vision
Multi-benchmark large-scale dataset
First-person vision
Video dataset
Action understanding
ISSN:0920-5691, 1573-1405
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung: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 (Damen in Scaling egocentric vision: ECCV, 2018), 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.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0920-5691
1573-1405
DOI:10.1007/s11263-021-01531-2