Scaling Egocentric Vision: The EPIC-KITCHENS Dataset

TL;DR

The paper introduces EPIC-KITCHENS, a large-scale egocentric video dataset capturing diverse daily kitchen activities, enabling advancements in understanding first-person interactions, actions, and object usage.

Contribution

It provides a comprehensive, annotated egocentric video dataset with diverse participants and environments, facilitating research in action recognition, object detection, and anticipation in first-person vision.

Findings

Established baseline results for action recognition and object detection.

Demonstrated the dataset's diversity and real-world applicability.

Highlighted challenges in egocentric video understanding.

Abstract

First-person vision is gaining interest as it offers a unique viewpoint on people's interaction with objects, their attention, and even intention. However, progress in this challenging domain has been relatively slow due to the lack of sufficiently large datasets. In this paper, we introduce EPIC-KITCHENS, a large-scale egocentric video benchmark recorded by 32 participants in their native kitchen environments. Our videos depict nonscripted daily activities: we simply asked each participant to start recording every time they entered their kitchen. Recording took place in 4 cities (in North America and Europe) by participants belonging to 10 different nationalities, resulting in highly diverse cooking styles. Our dataset features 55 hours of video consisting of 11.5M frames, which we densely labeled for a total of 39.6K action segments and 454.3K object bounding boxes. Our annotation is unique in that we had the participants narrate their own videos (after recording), thus reflecting true intention, and we crowd-sourced ground-truths based on these. We describe our object, action and anticipation challenges, and evaluate several baselines over two test splits, seen and unseen kitchens. Dataset and Project page: http://epic-kitchens.github.io